JP2005332119A - Spot image detecting method and spot image detecting program - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To easily detect each spot image from a photographic image including a spot image with low resolution obtained by photographing an automobile on a road. <P>SOLUTION: A group of extreme point pixels whose density is the maximum value (or minimum value) for the density of their peripheral pixels is detected. A group of monotone changing pixels whose density has in a monotone changing relation with the density of the extreme point pixels, which are within a predetermined distance depending on the size of a detection object from the respective extreme point pixels are detected. The minimum density (or maximum density) of the respective density of the group of monotone changing pixels detected for the respective extreme point pixels is detected, and whether or not an extreme point region including the extreme point pixels and the monotone changing pixel group detected for the extreme point pixels is a region included in a spot image representing the detection object is decided depending on whether or not the absolute value of a density difference between the density of the respective extreme point pixels and the minimum density is a predetermined threshold or more. <P>COPYRIGHT: (C)2006,JPO&NCIPI

Description

  The present invention is obtained by imaging a plurality of detection objects, and can detect spot image information such as positions or existing areas of the spot images from a captured image including a plurality of spot images representing the plurality of detection objects. The present invention relates to a spot image detection method and a spot image detection program.

  To automatically measure the traffic on the road, install sensors such as TV cameras, loop detectors, ultrasonic detectors, optical detectors along the road, A detection method is used, but this method greatly increases the cost of equipment required for measurement. For this reason, recently, a method for automatically detecting the number and positions of cars on a road using remote sensing images such as aerial photographs and satellite images has been studied. The advantage of this method is that the field of view of remote sensing images has a size of several tens of kilometers, so it is expected that the position and number of vehicles in a wide area can be observed from the same image. Secondly, the traffic observation system using remote sensing images is mainly composed of image data receiving facilities and computers, and requires much smaller facilities than conventional systems using sensors, so the cost is low. . Third, the capacity of remote sensing images is at most several tens of megabytes and can be processed at high speed by current computers.

  For example, in Patent Document 1, after applying an image enhancement process to a grayscale image obtained by photographing a road, a threshold process is performed with a certain threshold to detect a plurality of spot images representing an automobile. Here, the spot image refers to an image having a low resolution composed of a small number of pixels that is present at a position where a detection target, for example, an automobile is present, but does not clearly represent the outer shape of the detection target. In Non-Patent Document 1, first, a background image is generated by removing a spot image of a car from a plurality of road gray images, and then the gray image including the spot image of the car and the background image are subtracted to mainly perform the car. A grayscale image including the spot image is acquired, and threshold processing is performed on the grayscale image with a certain threshold value to detect a spot image of an automobile.

Although Patent Document 1 or Non-Patent Document 1 uses an image density threshold value, Non-Patent Document 2 does not use an image density threshold value, and uses a spot image representing an automobile as follows. The position of the car is detected. For a certain pixel p = (i, j), a square frame m (d) having a radius d is defined by the following equation.
m (d) = {(i + x, j + y) | max (| x |, | y |) = d}
The maximum value of the density of the pixels on the frame m (d) is defined as fmax (m (d)), and the minimum value of fmax (m (d)) in the range of the radius d from 1 to the maximum value D is defined as F. . That is,
F = min {fmax (m (d)) | 1 ≦ d ≦ D}

If the condition that the density of the pixel p is much larger than the minimum value F is satisfied, a bright spot image exists at the position of the pixel p. As the density of the pixel p, the density of the pixel p and the minimum value F are The density difference is set. When the condition that the density of the pixel p is much larger than the minimum value F is not satisfied, 0 is set as the density value of the pixel p. After executing such processing for all the pixels, a plurality of pixels determined to have spot images are grouped by a symbol inference system, and each vehicle has a substantially branch-like shape intersected in an X shape. An image representative of one automobile composed of two pixel columns is generated. The intersection position and direction of these two pixel columns represent the position and direction of the automobile. This automobile detection method uses an infrared image and makes it possible to distinguish between a moving car and a stopped car depending on the intensity of the infrared light.
JP 2003-030649 A SP Hoogendoorn, HJ Van Zuylen, M. Schreuder, B. Gorte, and G. Vosselman, "Microscopic Traffic Data Collection by Remote Sensing", Transporation Research Board (TRB) 82nd Annual Meeting, Washington DC, January 12-16, 2003, [online], [Search February 1, 2004], Internet <URL: http://www.geo.tudelft.nl/frs/papers/2003/Microscopic%20traffic%20Ben%20GeorgeV.pdf> U. Stilla and E. Michaelsen, "Estimating Vehicle Activity Using Thermal Image Sequences and Maps", ISPRS Symposium 2002, "Geospatial Theory, Processing and Applications", from 9 to 12 July, 2002 in Ottawa, Canada, [online], [ Search on February 1, 2004], Internet <URL: http://www.isprs.org/commission4/proceedings/pdfpapers/399.pdf>

  In a vehicle detection method such as Patent Document 1 or Non-Patent Document 1, a threshold value of density is determined in advance, and the density of a certain part in a captured image obtained by imaging a region where the vehicle travels is greater than or equal to a predetermined threshold value. Whether or not the portion represents an automobile is determined based on whether or not it is. In such a method, the detection result differs depending on how much the threshold is set. That is, the density of the automobile in the captured image is usually different from the density of the background, and the density of the automobile is higher (white) than the density of the background or vice versa. However, even if the density of the automobile is whiter than the background (the density is higher), the density varies depending on the automobile. That is, the density of the automobile in the captured image varies depending on the color and reflectance of the surface of the automobile, and also varies depending on the intensity of sunlight and the irradiation direction irradiated on the automobile. Furthermore, the density of the road serving as the background in the captured image varies depending on the color of the road surface and the reflectance.

  Therefore, there is a problem that it is difficult to appropriately determine the threshold value in the method of accurately detecting the portion representing the automobile from the captured image using the threshold value as described above. That is, if the threshold value is set to a bright value, a vehicle having a dark density cannot be detected. Conversely, if the threshold value is set to a dark value, an object in the background unrelated to the vehicle is also detected.

  On the other hand, as in Non-Patent Document 2, such a problem does not occur in a method that does not use an image density threshold for detecting the location of an automobile. However, in the method disclosed in Non-Patent Document 2, after detecting a plurality of pixel candidates included in a spot image, the position and the like of the spot image using a symbol inference system using the density and position of the pixels is detected. Since an image representative of one automobile composed of two substantially linear pixel rows intersecting in an approximate X shape is generated, the process of generating an automobile representative image is complicated.

  In an image such as a satellite image or an aerial photograph, the resolution of the image is low, and the position and shape of the car itself are usually not expressed so accurately. The resolution of a geographical image obtained by actually photographing the ground from an artificial satellite is, for example, about 50 to 60 cm, and an image representing one automobile is not clear. It is represented by a small white spot image or an image close thereto. The number of pixels constituting the spot image is as small as about 3 × 6 pixels, for example.

  Even if such a low-resolution image is used to detect the position or presence area of a small area such as a car on a road, it is difficult to increase the detection accuracy of those positions or existence areas. However, for the application of detecting the position and number of cars on the road and detecting the congestion state of the road, it is not always necessary to increase the detection accuracy of the position and area of the car. The process for detecting the position and the existing area is preferably a simple process that can be executed at high speed.

  Therefore, an object of the present invention is to detect the position of a spot image representing a detection object from a captured image including a spot image with a low resolution obtained by imaging a plurality of detection objects such as a car on a road. To provide a spot image detection method and a spot image detection program capable of detecting spot image information such as an existing region by a simple process.

  An outline of the principle of the spot image detection method according to the present invention for achieving the above object will be described first. The density of the spot image representing the detection target (for example, a car) in the captured image is different from the density of the background. That is, the density is higher than the background density (white) or vice versa. The concentration distribution of an automobile or the like is complicated and differs depending on the direction of the surface of the automobile or the irradiation direction of sunlight. The background density also varies depending on the color of the road surface and the reflectance. As a result, the difference between the density of the spot image of the car that is whiter (higher density) than the background and the density of the background changes depending on the car or the intensity of sunlight. Therefore, it is generally not always easy to distinguish a background from a spot image of a detection object such as an automobile using a threshold value.

  However, when the density of an automobile spot image is whiter than the background (the density is higher), the inventor has a certain pixel (maximum point pixel) as a density distribution portion that does not depend on the automobile. ) Has a maximum value, and a plurality of pixels (monotonously decreasing pixel group) whose density decreases monotonously exist around the pixel. An area where the maximal point pixel and the monotonously decreasing pixel group exist may be referred to as a maximal area. Similarly, when the density of an automobile is blacker than the background (the density is lower), the density of a certain pixel (minimum point pixel) has a minimum value as a density distribution part that does not depend on the automobile. Then, he noticed that there are a plurality of pixels (monotonically increasing pixel group) whose density increases monotonously around them. An area where the minimum point pixel and the monotonically increasing pixel group exist may be referred to as a minimum area. Hereinafter, the local maximum value and the local minimum value may be referred to as an extreme value without being distinguished from each other, the local maximum pixel and the local minimum pixel may be referred to as an extreme point pixel without being distinguished from each other, The monotonically increasing pixel group may be referred to as a monotonically changing pixel group without being distinguished, and the maximum region and the minimum region may be referred to as an extreme value region without being distinguished.

  In the following, detection of a local maximum region including local maximum pixels in the case of detecting a car having a density white (higher density) than the background will be described. Need only detect a minimum area including a minimum point pixel and a monotonically increasing pixel group around the minimum point pixel, and in this case also, the following explanation is based on the difference between the maximum value and the minimum value, It can be applied in the same way if it is read in consideration of the difference.

  In general, even on roads where there are no detection objects such as automobiles, there are many pixels where the density is a maximum point, and there are also monotonically decreasing pixel groups around each maximum point pixel, so the maximum region is There are many. However, in the vicinity of the maximal point pixel detected in a place where a detection object such as an automobile is present, the range occupied by the maximal point pixel and the surrounding monotonically decreasing pixel group (expansion of the maximal region) is almost the same. While the area occupied by a detection object such as an automobile is approximately represented, the local maximum pixel in the vicinity of the maximum pixel detected at a place on the road where the detection object such as an automobile does not exist In many cases, the area occupied by the monotonously decreasing pixel group in the vicinity thereof (expansion of the maximum area) is much wider than the area occupied by the detection target such as an automobile. Further, in the range occupied by the maximal point pixel detected in a place where there is no detection target such as an automobile and the monotonically decreasing pixel group around it, the minimum density value of the monotonically decreasing pixel group around the maximal point pixel is The absolute value of the density difference with the density of the local maximum pixel is found in the range occupied by the local maximum pixel detected in the place where the detection target such as an automobile exists and the monotonously decreasing pixel group around it. Usually, it is much smaller than the absolute value of the density difference between the minimum density of the monotonically decreasing pixel group around the maximum point pixel and the density of the maximum point pixel. Therefore, in a place on the road where a detection object such as an automobile does not exist, the range occupied by the maximum point pixel and the surrounding monotonously decreasing pixel group (the spread of the maximum area) is the same as the detection object such as an automobile. Even if it is almost the same as the range detected when it exists, the amount of decrease in density within that range is the range occupied by the maximum point pixel and the surrounding monotonically decreasing pixel group (expansion of the maximum region) Is different from the amount of decrease in density when a detection object such as an automobile exists and is included in the spot image.

  The present inventor found that the detection of an object to be detected such as an automobile is caused by the spread of the maximum region composed of such maximum point pixels and the surrounding monotonously decreasing pixel groups and the density difference between the maximum point pixels and the surrounding monotonously decreasing pixel groups. By using the difference between the case where it belongs to the spot image representing and the case where it does not, the maximum point pixel included in the spot image representing the detection object such as an automobile and the surrounding monotonously decreasing pixel group can be detected, The present invention has been achieved. That is, in the present invention, in order to detect each spot image from a captured image obtained by photographing a plurality of detection objects and including a plurality of spot images representing each detection object, the maximum point pixel from the captured image is detected. And a monotonously decreasing pixel group around the same are detected within a range corresponding to the normal size of the detection target. Further, whether or not the local maximum pixel is a local maximum belonging to the spot image representing the detection target is determined by calculating the minimum density of the monotonically decreasing pixel group around the local maximum pixel and the density of the local maximum pixel. It is said that the absolute value of the density difference is equal to or greater than a threshold value of the density difference that is determined in advance corresponding to the detection target, as is usually the case when the local maximum pixel belongs to the spot image of the detection target. Judgment is made based on whether or not the condition is satisfied.

  When this condition is satisfied, it can be determined that the maximum region including the detected maximum point pixel and the monotonously decreasing pixel group around the detected maximum point pixel belongs to the spot image representing the automobile that is the detection target. Furthermore, the position of the maximum point pixel can be used as the position of the spot image. Moreover, the processing for detecting the maximum point pixel and the monotonously decreasing pixel group around it is simple and can be executed at high speed.

  As described above, when the maximal point pixel and the maximal region including the maximal point pixel are detected, it is possible to prevent a pixel larger than the density of the maximal point pixel from being present in the maximal region, and the position of the maximal point pixel is It is suitable for use as a position of a spot image representing a detection target.

  Note that, in order for the detected maximum point pixel to belong to the spot image representing the detection target, the size of the spot image to which the maximum point pixel belongs corresponds to the width of the detection target. You must have at least. Otherwise, the detected maximum point pixel and the maximum region including the pixel may belong to a spot image representing an object much smaller than the detection target. In order to avoid such a case, there is also a condition that the width of the detected maximum region is larger than a predetermined threshold value depending on the width of the detection object. It is desirable to determine whether or not the pixel is satisfied, and when it is, it is preferable that the detected maximum pixel and the maximum region including the detected maximum pixel are regions included in the spot image representing the detection target.

Specifically, the spot image detection method according to the first aspect of the present invention includes an extreme point pixel detection step, a monotonous change pixel group detection step, a comparison target concentration detection step, and an area determination step. Is included.
The extreme point pixel detection step is obtained by photographing a plurality of detection objects, and from a captured image including a plurality of spot images representing the plurality of detection objects, the density thereof is relative to the density of surrounding pixels. A group of extreme point pixels having a density that is one of the predetermined extreme values of the maximum value or the minimum value is detected. Here, the extreme point pixel detected in the extreme point pixel detection step is detected as a pixel that may belong to a spot image representing a detection target (for example, an automobile). When the spot image representing the automobile to be detected is whiter than the background (the density is high), a maximum point pixel having a maximum density is detected as the extreme value pixel. In the opposite case, a minimum point pixel having a minimum density is detected as an extreme point pixel.

  When searching for the maximum point pixel as the extreme point pixel in the extreme point pixel detection step, the density of the pixel p selected from the captured image is the maximum point. It is not smaller than any of the density values of the eight neighboring pixels surrounding the pixel. In this definition, even if the density of the selected pixel p has the same density as any of the density of the eight neighboring pixels, is the density of any of the other pixels in the eight neighboring pixels the same as the density of the selected pixel p? If it is smaller, the density of the selected pixel p is regarded as a maximum value. Extremely, even if the density of the selected pixel p and the density of all the 8 neighboring pixels are the same, when searching for a maximal point pixel, the selected pixel p is regarded as a maximal point pixel. However, when the density of the selected pixel p is lower than any one of the densities of the eight neighboring pixels, the density of the selected pixel p is not a maximum value. It should be noted that the density of the selected pixel p is not compared with the density of pixels farther from the eight neighboring pixels of the selected pixel p. Minimal point pixels can be defined similarly.

  The monotonically changing pixel group detecting step is within a predetermined distance determined in advance depending on the size of the detection object from each of the detected group of extreme value point pixels, A group of monotonically changing pixels having a monotonous change relationship with respect to the density is detected from the photographed image. That is, the monotonic change pixel group detected in the monotonic change pixel group detection step satisfies the first condition that the density has a monotone change relationship with respect to the density of the detected extreme point pixel, and the extreme point A group of monotonically changing pixels that satisfy the second condition of being within a reference value of distance, which is determined depending on the size of the detection target from the pixel.

  The extreme value region including the extreme value point pixel p and the monotonically changing pixel group is a region that may represent the presence region of the spot image representing the detection target. Here, another pixel having a monotonous change relationship with respect to the density of the extreme point pixel is defined as a path from the maximum point pixel to the other pixel, assuming that the extreme point pixel is a maximum point pixel. That is, there is a path that satisfies the condition that the concentration of the monotonously decreases. A monotonically decreasing density is when the density is smaller or equal. Detecting a monotonically changing pixel group that satisfies the first and second conditions means detecting a local maximum region within an appropriate range determined based on the size of the detection target. Accordingly, even if a monotonically changing pixel group around a certain maximal point pixel actually exists beyond the reasonable range, only the monotonically changing pixel group within that range is detected. On the other hand, when the monotonically changing pixel group around a certain maximal point pixel exists only in a part of the appropriate range, all these monotonically changing pixel groups are detected.

  The comparison target density detection step includes the density of the extreme point pixel among the minimum density or the maximum density of the density of the group of monotonically changing pixels detected for each of the group of extreme point pixels One of the predetermined concentrations to be compared is detected as a comparison target concentration. Here, one density to be compared with the detected extreme point pixel is the detected monotonic change depending on whether the detected extreme point pixel is a maximum point pixel or a minimum point pixel. It is the minimum density or the maximum density of each density of the pixel group.

  In the extreme value region determination step, an absolute value of a density difference between the density of each of the group of extreme value point pixels and the comparison target density detected for the extreme value pixel corresponds to the detection object. An extreme value region including the extreme point pixel and the monotonically changing pixel group detected for the extreme point pixel, depending on whether or not the threshold value is equal to or greater than a predetermined threshold value of predetermined density difference Is an area included in one of the plurality of spot images representing the plurality of detection objects.

  As described above, in the spot image detection method according to claim 1, an extreme value region including an extreme value point pixel and a monotonically changing pixel group adjacent to the extreme value point pixel and within a predetermined distance from the extreme value point pixel is detected and detected. Since it is determined whether or not the extreme value region belongs to the spot image representing the detection target based on the amount of change in the pixel density within the extreme value region, it is relatively easy to select the desired detection target. A spot image to represent can be detected. At that time, it is possible to prevent erroneous detection of the position of the maximum point pixel of the spot image representing an object larger than the detection target. Furthermore, since it is not necessary to use a density threshold value for distinguishing and detecting a spot image representing a detection object from the background, it is difficult to determine the density threshold value that occurs in the prior art when using the density threshold value. Absent.

  Furthermore, the spot image detection method according to claim 2, wherein an extreme value region including any one of the group of extreme value point pixels and the monotonically changing pixel group detected for the extreme value point pixel is the plurality of detection points. A position storing step of storing the position of the extreme point pixel as the position of the one spot image when it is determined that the region is included in one of the plurality of spot images representing the object. It is a waste. As a result, the position of the detected extreme point pixel is stored as the position of the spot image representing the detection target, so that the position of the spot image can be detected by a relatively simple process, and the density is higher than that of the maximum point pixel. The case where the position of a low pixel is used as the position of the spot image does not occur, and the unnatural relationship between the position of the spot image and the density that occurs when such a case occurs can be avoided.

  Furthermore, the spot image detection method according to claim 3 is a width detection method according to claim 1 or 2, wherein a width of an existence area of the group of monotonically changing pixels detected for each extreme value pixel is detected. The extremum area determination step further includes an absolute value of the density difference detected for the extremum point pixel being equal to or greater than a threshold value of the density difference, and for the extremum point pixel. The detected width is determined in advance depending on the size of the object to be detected, and depending on whether the width is smaller than the width determined by the predetermined distance and is equal to or greater than a predetermined width threshold. An extreme value region including an extreme value point pixel and the monotonically changing pixel group detected for the extreme value pixel is a region included in one of the plurality of spot images representing the plurality of detection objects. It is determined whether or not there is. As a result, it is possible to prevent erroneously detecting a spot image to which an extreme value region having a width equal to or smaller than the width specified in relation to the search object belongs as a spot image representing the detection object. Here, the width of the extreme value region can be defined by various criteria. One example is the use of a certain number of pixels (for example, 60%) with respect to the number of pixels in the extreme value region.

  Furthermore, a spot image detection method according to a fourth aspect of the present invention is the spot image detection method according to any one of the first to third aspects, wherein any one of the extreme point pixels detected in the extreme point pixel detection step and the extreme point pixel is detected. On the other hand, the existence range of the monotonically changing pixel group detected in the monotonically changing pixel group detecting step is any other extreme point pixel detected in the extreme point pixel detecting step and the other extreme value An existence region overlap determination step for determining whether or not an existence range with the monotonous change pixel group detected in the monotone change pixel group detection step overlaps with a point pixel; and any one of the extreme point pixels When the existence range for the other extremal point pixel overlaps with the other existence point range, one of the extreme point pixel and the other extreme point pixel is selected according to a predetermined criterion. Was not selected And extreme point pixel disabling step disabling extreme point pixels square, and further comprising a. Thereby, even when a plurality of extreme point pixels are included in one spot image, each extreme point pixel is detected, and each extreme point pixel and a group of extreme point pixels corresponding thereto are present. If the range overlaps with the existence range for other extremal point pixels, it is possible to invalidate other than one of those extremal point pixels, and one extreme point pixel for one spot image. It becomes possible to be detected.

  According to the present invention, a spot image representing a desired detection target can be detected relatively easily. At that time, it is possible to prevent erroneous detection of the position of the maximum point pixel of the spot image representing an object larger than the detection target. Furthermore, since it is not necessary to use a density threshold value for distinguishing and detecting a spot image representing a detection object from the background, it is difficult to determine the density threshold value that occurs in the prior art when using the density threshold value. Absent.

  Furthermore, in a more specific aspect, since the position of the detected extreme point pixel is stored as the position of the spot image representing the detection target, the position of the spot image can be detected by a relatively simple process. . Furthermore, there is no case where the position of a pixel having a lower density than the maximum point pixel is used as the position of the spot image, and the unnatural relationship between the position of the spot image and the density that occurs when such a case occurs. Can be avoided.

  Furthermore, in a desirable mode, it is possible to prevent a spot image to which an extreme value region having a width equal to or smaller than the width specified in relation to the search object belongs, from being erroneously detected as a spot image representing the detection object. In another desirable aspect, even when a plurality of extreme point pixels are detected for one spot image, it is possible to invalidate other than one of these extreme point pixels, One extreme point pixel can be detected.

Embodiments of a spot image detection method and a spot image detection program according to the present invention will be described below in detail with reference to the drawings.
FIG. 1 is a schematic block diagram of one embodiment of a spot image detection apparatus according to the present invention. Reference numeral 1 denotes the whole of one embodiment of the apparatus. The apparatus 1 includes, for example, a processing device 10 realized by a personal computer or a workstation, and a RAM (Random Access Memory) (not shown) used as a main memory and an auxiliary storage device (not shown) such as a magnetic disk storage device. And the input / output device 30. The input / output device 30 includes an input device 31 including a keyboard and a pointing device such as a mouse, a display device 32 such as a CRT display device, or an output device such as a printer 33. The input device 31 is used for inputting parameters and starting commands. The display device 32 or the printer 33 displays or prints an image such as a captured image obtained by imaging a plurality of detection objects, an image with a spot image marker generated by the device 1, or data generated by the device 1. Used for. When data is stored in the storage device 20, it is determined in advance for each piece of data whether the data is stored in a RAM (not shown) or an auxiliary storage device (not shown). The processing device 10 incorporates a spot image detection program 40 for detecting each detection target from a captured image obtained by imaging a region including a plurality of detection targets.

  Before further describing the embodiment of the spot image detection method and spot image detection program according to the present invention, the principle of processing executed in this embodiment will be described. In the following, the case of detecting the maximum point pixel will be described, but the same applies to the case of detecting the minimum value pixel.

The maximum point pixel p is detected from the captured image, and the maximum region M (p) with respect to the detected maximum point pixel p can be obtained inductively as follows. Let M0 (p) be the 0th-order maximum region composed of the maximum point pixels p. Starting from the 0th-order maximum region M0 (p) of the local maximum pixel p, the region growth of only the (n + 1) th-order incremental region Bn + 1 (p) is repeatedly determined for the n-th maximum region Mn (p). Then, the (n + 1) th order maximum region Mn + 1 (p) is obtained by the following equation 1.
Mn + 1 (p) = Mn (p) ∪Bn + 1 (p) (1)

Here, the (n + 1) th order increment region Bn + 1 (p) has a condition that the pixel q is adjacent to the nth order maximum region Mn (p) and the density of the pixel q is the nth order maximum region Mn (p). Is a region including a pixel q that satisfies the condition that the pixel q is not larger than the density of at least one adjacent pixel (has a monotonous decrease relationship). The following equation 2 is established for the smallest m in which the (m + 1) th order increment region Bm + 1 (p) is an empty set.
M (p) = Mm (p) (2)
Therefore, when the (m + 1) th increment region Bm + 1 (p) first becomes an empty set, the mth order maximum region Mm (p) obtained so far becomes the maximum region M (p).

  The above repeating process will be described in detail. The first-order incremental region B1 (p) is obtained for the 0th-order maximum region M0 (p) consisting only of the maximum point pixel p. That is, the first increment region B1 (p) including all the pixels q that satisfy the condition that the pixel q is adjacent to the pixel p and the density of the pixel q is not higher than the density of the pixel p (monotonic decrease relationship) is obtained. . At this stage, the only pixels on the path from the maximal point pixel p to the arbitrary pixel q in the first incremental region B1 (p) are these two pixels p and q, and the density monotonously decreases between these pixels. The condition to do is satisfied. Further, the first local maximum region M1 (p) is determined by the logical sum of the original pixel p and the newly obtained first incremental region B1 (p) using Equation 1.

  Thereafter, a second incremental region B2 (p) is obtained. That is, the condition that the pixel q is adjacent to any pixel in the primary maximum region M1 (p) and the density of the pixel q is at least one adjacent to the pixel q in the primary maximum region M1 (p). The region of all the pixels q that satisfy the condition that the density is not larger than the density of one pixel (monotonic decrease relationship) is determined as the second incremental region B2 (p). Further, the second maximum region M2 (p) is determined by the logical sum of the first maximum region M1 (p) and the newly obtained second increment region B2 (p) according to Equation 1. At this stage, the pixels on the path from the maximum point pixel p to any pixel q in the second increment region B2 (p) are the pixel p and any of the first increment regions B1 (p) in the increment first increment region B1 (p). 1 pixel and the second pixel in the second incremental region B2 (p) adjacent to the first pixel, and the density between the first pixel and the second pixel is increased from the pixel p. The condition of monotonically decreasing is established.

  Similarly, the maximum region Mn (p) (n = 1, 2,...) Can be obtained by repeating the above processing. If any pixel belonging to the (m + 1) th order increment region Bm + 1 (p) cannot be detected for the first time with respect to any integer m, the processing is terminated, and the calculation is performed up to that time according to Equation 2. The m-th maximum region Mm (p) may be used as the maximum region M (p).

  In order to satisfy the second condition that the size of the maximum region M (p) includes only pixels within a predetermined distance from the pixel p, for example, one of the incremental regions ((n + 1) th) ) The next incremental region Bn + 1 (p)) is determined by sequentially selecting all the pixels within the predetermined distance from the pixel p, and all pixels within the same range are also determined when determining the next incremental region. What is necessary is just to repeat selecting all the pixels within the same range sequentially so that a pixel may be selected sequentially. When the incremental regions are sequentially obtained in this way to obtain the maximum region M (p), an arbitrary pixel q belonging to the maximum region M (p) has a pixel density on the route as a route from the pixel p to the pixel q. The condition that there is a monotonically decreasing path is satisfied. This can be proved.

  After obtaining the maximum region M (p) in this way, it is determined whether or not the absolute value of the difference between the density of the maximum point pixel and the minimum value of the density in the maximum region is equal to or greater than a predetermined lower limit value of the density difference. If so, it can be determined that the detected maximum region M (p) is included in the spot image representing the detection target. As a result, the position of the detected maximum point pixel can be used as the presence position of the spot image representing the detection target, and the detected maximum area can be used as a representative area of the spot image representing the detection target. can do.

  Whether or not the obtained maximum region M (p) satisfies the third condition that it is equal to or greater than a predetermined threshold value is determined after determining the maximum region M (p). It may be determined whether the width of M (p) is equal to or greater than a threshold value related to the width. Various amounts can be used for the width of the maximum region M (p). For example, the number of pixels included in the maximum region M (p) or the maximum distance between arbitrary pixels included in the maximum region M (p) can be used. Alternatively, the determination may be made based on whether or not the number of repetitions of the determination of the (m + 1) -th incremental region Bm + 1 until the determination is made after the maximum region M (p) is determined is greater than or equal to a predetermined value.

Hereinafter, the details of the embodiments of the spot image detection method and the spot image detection program according to the present invention will be further described.
The spot image detection program 40 is stored in the storage device 20 and executed by the processing device 10, but for the sake of clarity, the spot image detection program 40 and a plurality of modules constituting the spot image detection program 40 are shown in the processing device 10 in the figure. It is written inside the block. The spot image detection program 40 includes modules of an initial value setting unit 100, an extreme point pixel search unit 200, an extreme value region growth unit 300, an extreme value region determination unit 400, and a spot image related data generation unit 500. . Furthermore, the spot image detection program 40 includes an extreme point pixel search success / failure determination step S250 and an extreme value region pass / fail determination step S450. The extreme point pixel search success / failure determination step S250 is performed after the extreme point pixel search unit 200 executes, and determines whether or not the extreme point pixel search unit 200 has successfully searched for the extreme point pixel. The extreme value region acceptance / rejection determination step S450 is executed after the execution of the extreme value region determination unit 400, and determines whether or not the determination result in the extreme value region determination unit 400 for the detected extreme value region is acceptable.

  The plurality of modules 100, 200, 300, 400, and 500 are sequentially executed in this order. After the execution of the spot image related data generation unit 500, the processing moves to the initial value setting unit 100, and the processing after this processing is repeated. However, the extreme value region growing unit 300 is executed when it is determined in the extreme success point pixel search success / failure determination step S250 that the extreme value pixel search is successful, and the spot image related data generating unit 500 is detected. This is executed when it is determined in the extreme value region pass / fail determination step S450 that the extreme value region is acceptable. When it is determined that the extreme value region detected in the extreme value region acceptance / rejection determination step S450 is unacceptable, the processing moves to the initial value setting unit 100. When the extreme point pixel search is determined to be unsuccessful in the extreme point pixel search success / failure determination step S250, the processing of the spot image detection program 40 ends.

  In the processing apparatus 10, the initial value setting unit 100, the extreme point pixel search unit 200, the extreme value region growing unit 300, the extreme value region determining unit 400, and the spot image related data generating unit 500 in the spot image detection program 40 are executed. Function block for setting initial values, function block for searching for extreme point pixels, function block for growing an extreme region starting from the searched extreme point, and extreme value obtained by region growth A functional block for determining whether or not an area is an extremum area belonging to a spot image of a detection object, and when it is determined that the extremum area belongs to a spot image representing the detection object, the spot image It operates as a plurality of functional blocks called functional blocks for generating related spot image related data. Therefore, a plurality of functional blocks corresponding to each module is realized by these modules of the processing device 10, the storage device 20, the input / output device 30, and the spot image detection program 40. Therefore, the processing device 10, the storage device 20, the input / output device 30, and the spot image detection program 40 realize one embodiment of the spot image detection device according to the present invention.

  The spot image detection program 40 implements one embodiment of the spot image detection program according to the present invention, and is recorded on a recording medium (not shown) or stored in the storage device 20 via a network (not shown). It is executed by the processing device 10. The spot image detection program 40 is recorded on a recording medium (not shown) or can be sold via a network (not shown). The procedure in which the processing device 10 executes the spot image detection program 40 to detect an object from the captured image realizes one embodiment of the spot image detection method according to the present invention.

  The storage device 20 stores the captured image data 21 in advance before the spot image detection program 40 is executed. The captured image data 21 is data representing an image obtained by capturing an area including the detection target. The region attribute data 22 includes region attribute values related to whether or not each pixel in the extreme value region growth range described later belongs to an extreme value region including an extreme value point pixel detected from the captured image data 21. This is data to be held, set to an initial value when the execution of the spot image detection program 40 is started, and updated to the spot image detection program 40 during execution.

  The extreme value region data 23 and the image data 24 with the spot image marker are data generated as a result of execution of the spot image detection program 40. The extreme value region data 23 includes data related to each of a plurality of extreme value regions that are detected by the spot image detection program 40 and are determined to be included in the spot image representing the detection target. The image data 24 with the spot image marker is obtained by superimposing a predetermined spot image marker indicating a spot image of the detection target on the spot image including the detected extreme value region in the captured image data 21. Data representing an image. In the following, when referring to a process for generating image data or a process stored in the storage device 20, an image is simply generated or stored in the storage device 20 for simplicity. There is.

  FIG. 2A is a diagram schematically showing the captured image data 21. As shown in the figure, the captured image data 21 is rectangular (square or rectangular), the origin O is defined at the upper left corner of the captured image, the x axis in the vertical downward direction and the horizontal right direction in the figure, Assume that the y-axis is defined. In the following, it is assumed that the captured image data 21 is a geographical image obtained by photographing the ground surface from an artificial satellite or an aircraft, and the detection target is an automobile traveling on the road or stopping on the road. Furthermore, it is assumed that the captured image data 21 is image data representing a black and white grayscale image. Further, it is assumed that the captured image data 21 represents an image in which the density becomes higher (whiter) in the area where the automobile is present. On the contrary, the present invention can be similarly applied to the case where the captured image data 21 represents an image whose density is low (blackened) in the region where the object exists. Note that the relationship between density and white is referred to as higher or higher density for white pixels.

  In the figure, 210 schematically represents one road on the ground. Reference numeral 220 schematically shows a spot image representing one of a plurality of automobiles traveling on the road 210. FIG. 2B shows an example of an actual geographic image obtained by actually photographing the ground from an artificial satellite. The resolution of this type of geographic image is generally low, for example, about 50 to 60 cm. As shown in the figure, the automobile is represented by a very small white island-like spot image, and the outline of the automobile is not clear. The number of pixels constituting a spot image representing an automobile is as small as about 3 × 6 pixels, for example.

  FIG. 2C schematically shows region attribute data 22 corresponding to the captured image data 21. In the present embodiment, the region attribute data 22 has a field that stores region attribute values corresponding to all the pixels of the captured image data 21. Since the region attribute data 22 includes the region attribute of the pixel corresponding to each pixel of the captured image data 21, the region attribute data 22 also represents an image having the value of the region attribute as an image value, like the captured image data 21. Since it can be considered image data, as shown in FIG. 2C, the region attribute data 22 is considered to be image data having a rectangular region, and, like the captured image data 21, is displayed in the upper left corner of the figure. Assume that the origin 0 is defined, and the x-axis and y-axis are defined in the vertical downward direction and horizontal right direction in the figure. As will be described later, the region attribute value for each pixel included in the region attribute data 22 is a value indicating that the pixel does not belong to the extreme value region, for example, “0”, indicating that the pixel belongs to the extreme value region. A value indicating, for example, “1”, or a value indicating that the pixel is a candidate belonging to the extreme value region, for example, “0.5”.

  Even if the region attribute data 22 has a field that holds the region attribute values for all the pixels of the captured image data 21 as in the present embodiment, in practice, any one of the road regions 210 in the captured image data 21 is present. It suffices to have a field for holding a region attribute value for each of a plurality of pixels belonging to (FIG. 2A), but here, which pixel in the captured image data 21 belongs to the road region Since the region attribute data 22 varies depending on the region represented by the image 21, it is assumed that the region attribute data 22 has a field that holds a region attribute value corresponding to each of all the pixels of the captured image data 21.

  Returning to FIG. 1, when the spot image detection program 40 is executed, the setting unit 100 is executed first. The initial value setting unit 100 sets the region attribute of the region attribute data 22 for each of all the pixels of the captured image data 21 to an initial value. Here, the initial value is a value “0” indicating that the corresponding pixel does not belong to the extreme value region.

  The spot image detection program 40 executes the extreme point pixel search unit 200 after the execution of the initial value setting unit 100. FIG. 3 is a schematic flowchart of an example of processing of the extreme point pixel search unit 200. The extreme point pixel search unit 200 sequentially selects pixels of the captured image 21 in a certain order, and determines whether the selected pixel is a pixel having an extreme value in density (referred to as an extreme point pixel). The extreme point pixel is detected as a pixel that may belong to any spot image representing the detection target in the captured image 21. As in the current assumption, when detecting a spot image of an automobile that is whiter (higher density) than the background, a maximum point pixel having a maximum density is detected as an extreme point pixel. Conversely, when detecting a spot image of a car that is blacker than the background (smaller in density), a minimum point pixel having a minimum value is detected as an extreme point pixel.

  An extreme point pixel, for example, a maximum point pixel, means that the density of the maximum point pixel is a maximum point compared to the density value of eight neighboring pixels surrounding the pixel. Therefore, in order to determine whether a certain pixel is an extreme point pixel, the density of the target pixel is compared with the density of eight neighboring pixels of the pixel.

  Specifically, the extreme point pixel search unit 200 is executed as follows. First, it is determined whether or not the selection of pixels from the captured image 21 is completed (step S201). If the pixel selection is not completed, the pixel to be processed next is selected (step S202). The spot image detection program 40 does not need to process all the pixels of the captured image 21 in order to detect a spot image representing a car that is a search target, and belongs to a road region in which the road in the captured image 21 exists. Only a plurality of pixels need be processed. Therefore, in step S202, a plurality of pixels belonging to the road region may be sequentially selected in a certain order, and pixels that do not belong to the road region may not be selected. Selection of a plurality of pixels belonging to a road area in the captured image 21 can be performed based on data indicating a road area (not shown) stored in advance in the storage device 20.

  Alternatively, all the pixels of the captured image 21 shown in FIG. 2A are sequentially selected, and whether or not the selected pixel is a pixel belonging to the road area is determined based on the data indicating the road area. When it is determined that the pixel belongs to the road area, a process related to the pixel may be executed. When it is determined that the selected pixel does not belong to the road area, the processing relating to the pixel may be skipped. Alternatively, in step S202, all the pixels of the captured image 21 are sequentially selected in a certain order, and the subsequent processing of the spot image detection program 40 is executed for the selected pixels. It can be determined whether or not the image belongs to a region, and when it is determined that the pixel does not belong, a processing result relating to the pixel can be invalidated. In the following, all pixels belonging to the road area in the captured image 21 are targeted for processing by the spot image detection program 40, and other pixels not belonging to the road area in the captured image 21 are not processed. Accordingly, in step S202, a plurality of pixels belonging to the road area are sequentially selected.

  More specifically, the extreme point pixel search unit 200 compares the density of the pixel selected in step S202 with the density of adjacent pixels of the pixel in order to search for extreme point pixels. In step S203, it is determined whether or not the pixel is an extreme point pixel. Here, the adjacent pixels of the selected pixel are eight adjacent pixels (eight neighboring pixels) surrounding the selected pixel. Therefore, in order to determine whether or not the selected pixel is an extreme point pixel, the density of pixels around that pixel is also necessary. Therefore, in the extreme point pixel search unit 200, the width of one pixel around the road region is determined. It is determined whether or not the pixels belonging to the internal area excluding the area are extreme point pixels. Therefore, in step S202, all the pixels in the region one pixel inside the road region in the captured image 21 may be sequentially selected in a certain order. The order of selection may be, for example, the x coordinate order and the y coordinate order. That is, a plurality of pixels having the same y coordinate may be selected in ascending order of the x coordinate, and a plurality of pixels having different y coordinates may be selected in the ascending order of the y coordinate.

  Hereinafter, the pixel selected in step S202 is referred to as a pixel p. After the pixel p is selected, it is determined whether or not the selected pixel p is an extreme point pixel (step S203). In the present example, the extreme point pixel is a maximum point pixel. Here, the selected pixel p is a maximal point pixel whose density is a maximal point when the density of the selected pixel p is not smaller than any of the density values of the eight neighboring pixels surrounding the pixel. In this definition, even if the density of the selected pixel p has the same density as any of the density of the eight neighboring pixels, is the density of any of the other pixels in the eight neighboring pixels the same as the density of the selected pixel p? If it is smaller than that, the density of the selected pixel p is regarded as a maximum value. Extremely, even when the density of the selected pixel p and the density of all eight neighboring pixels are the same, the selected pixel p is regarded as the maximum point pixel when searching for the maximum point pixel. However, when the density of the selected pixel p is lower than any one of the densities of the eight neighboring pixels, the density of the selected pixel p is not a maximum value. It should be noted that the density of the selected pixel p is not compared with the density of pixels farther than the eight neighboring pixels of the selected pixel p.

  If it is determined in step S203 that the selected pixel p is not an extreme point pixel (maximum point pixel), the process returns to step S201, and it is determined whether the pixel selection is completed. That is, it is determined whether or not a pixel that has not been determined whether or not it is an extreme point pixel is in an area one pixel inside the road area. If there are still unselected pixels, the next pixel p is selected in step S202, and it is determined in step S203 whether the new selected pixel p is an extreme point pixel. Such pixel selection end determination step S201, pixel selection step S202, and extreme point pixel determination step S202 are repeated until an extreme point pixel is detected.

  As a result of the above repetition, when it is determined that any selected pixel p is an extreme point pixel, it represents that the region attribute value in the region attribute data 22 relating to the pixel p belongs to the extreme value region. The attribute value is changed to “1” (step S204). When the extreme point pixel is selected, the extreme point pixel search unit 200 ends the process, returns to “success”, and returns to the main routine of the spot image detection program 40.

  Returning to FIG. 1, in the spot image detection program 40, after the extreme point pixel search unit 200 is executed, the extreme point pixel search unit 200 searches for the extreme point pixel in the extreme point pixel search success / failure determination step S 250. Is determined based on a return value from the extreme point pixel search unit 200. As assumed now, when the return value from the extreme point pixel search unit 200 is “success”, the extreme value region growing unit 300 is executed. The extreme region growing unit 300 detects an extreme region including the extreme point using the detected extreme point as a starting point. Here, the extreme value region is a region composed of the extreme value point pixel (maximum point pixel in the present example) and one or a plurality of peripheral pixels that are in a monotonous change relationship with the pixel. Here, a pixel that is in a monotonic change relationship with an extreme point pixel indicates a monotone decreasing relationship when the extreme point pixel is a local maximum point pixel as assumed now, and the extreme point pixel is a local minimum. In the case of a point pixel, it indicates a monotonically increasing relationship.

  A peripheral pixel having a monotonic change relationship with an extreme point pixel means that there is a path from the extreme point pixel to the surrounding pixel via a pixel whose density is monotonously changing. . When the extreme point pixel is a local maximum pixel, the surrounding pixels that are monotonically decreasing with respect to the local maximum pixel are referred to as the peripheral pixels via the pixels whose density is monotonously decreasing from the local maximum pixel. That is, there is a path to the pixel. Here, the monotonic decrease means that it is smaller or equal. Similarly, when the extreme point pixel is a minimum point pixel, the surrounding pixels that are in a monotonically increasing relationship with the minimum point pixel are connected via a pixel whose density is monotonically increasing from the minimum point pixel. This means that there is a route to the surrounding pixels. Here, the monotonous increase means that it is larger or equal.

  Here, the above-described path with respect to the maximal point pixel means that, for example, the maximal point pixel (first pixel), the second pixel adjacent thereto, and the third pixel adjacent to the second pixel are included. In some cases, the density of the second pixel is equal to or less than the density of the maximum point pixel from the definition of the maximum point pixel, and the density of the second pixel inevitably has a monotonically decreasing relationship with the density of the maximum point pixel. Even when the density of the second pixel is the same as the density of the maximum point pixel, it is still considered that the density of the second pixel is monotonously decreased with respect to the density of the maximum point pixel. Furthermore, when the density of the third pixel is equal to or lower than the density of the second pixel, the density of the third pixel is in a monotonically decreasing relationship with the density of the second pixel. Even when the density of the third pixel is the same as the density of the second pixel, it is assumed that the density of the third pixel is in a monotonically decreasing relationship with the density of the second pixel. Is no different. After all, on the path from the maximum point pixel to the third pixel via the second pixel, the pixel density is in the order of the maximum point pixel density, the second pixel density, and the third pixel density. As a result, the density of these three pixels is monotonically decreasing.

  Alternatively, there is a fourth pixel adjacent to both the second and third pixels, the density of the fourth pixel is equal to or lower than the density of the second pixel, and the density of the third pixel is the fourth pixel. If the pixel density is equal to or lower than the pixel density, the density of the third pixel is monotonically decreased with respect to the density of the fourth pixel, and the density of the fourth pixel is monotonous with respect to the density of the second pixel. It is in a decreasing relationship. In the end, on the path from the maximum point pixel to the third pixel via the second and fourth pixels, the pixel density is the maximum pixel density, the second pixel density, and the fourth pixel density. The density changes in the order of the density of the third pixel, and the density of these four pixels decreases monotonously.

  FIG. 4 is a schematic flowchart of an example of processing of the extreme value region growing unit 300. The extreme value region growth unit 300 detects a plurality of pixels that are in a monotonic change relationship (in this example, a monotonous decrease relationship) from the searched extreme point pixel (maximum point pixel in the present assumption) as a starting point. Then, region growth is performed so as to determine the extreme value region including the extreme point pixel. The region growth is performed within a maximum distance designated in advance from the detected extreme point pixel.

The distance may be any as long as it satisfies the distance axiom shown in Equation 3 below. Here, p, q, and r represent pixels, and d (p, q) and the like represent distances between the pixels p and q.
d (p, q) ≦ d (p, r) + d (r, q) (3)
For example, d1, d2, and d3 shown below can all be used as the distance between the pixels p and q.

Here, xp and yp are the x and y coordinates of the pixel p, and xq and yq are the x and y coordinates of the pixel q.

  In the present embodiment, the distance between the extreme point pixel p and the difference between the absolute value and the y coordinate of the detected difference between the extreme point pixel p and the x coordinate is defined as in the above equation 4b. The larger absolute value is used, and the reference value of the distance is S. Therefore, the region growing range is a square region having both the width and the height, including the detected extreme point pixel as the center, and 2S + 1.

  FIG. 5A is a diagram illustrating an extreme value region growth range used in the present embodiment. Reference numeral 25 denotes an example of a region growing range when the coordinates of the detected extreme point pixel are p (x, y). In the figure, the reference value S for the distance is 2. In general, the coordinates of the pixels A, B, C, and D at the vertices of the range 25 are (x−S, y−S), (x + S, y−S), (x + S, y + S), (x−, respectively). S, y + S). Therefore, the size of the region to which the region growing pixel belongs is (2S + 1) × (2S + 1). This size (2S + 1) is determined in advance depending on the length of the detection object, for example, the automobile. Since the length of the automobile differs depending on the vehicle, for example, it may be determined based on the maximum value among the lengths of various current automobiles. Note that the size (2S + 1) may be adjusted so that a desired result can be obtained by applying the detection method according to the present embodiment to the actual captured image while changing the size (2S + 1) to various values. desirable. For example, if the number of pixels constituting a spot image representing an automobile is about 3 × 6 pixels as described above, the reference value S of the distance for determining the extreme value region growth range can be set to 2. At this time, the size of the extreme value region growth range is 5 × 5 pixels.

  The distance reference value S may be changed between the vertical direction and the horizontal direction of the extreme value region growth range. The extreme value region growth range may be determined in accordance with the extension direction of the road. For example, the x axis can be a direction perpendicular to the road direction and the y axis can be a direction parallel to the road direction. Alternatively, the range of the spread of each spot image is detected in advance, and for example, the direction of the longest spread is estimated as the direction of the corresponding vehicle body assuming that the spot image represents the vehicle, and the direction of the vehicle body The x-axis may be defined in a direction perpendicular to the vertical axis, and the y-axis may be defined in a direction parallel to the vehicle body direction. In this case, the x-axis and y-axis directions are determined for each local maximum point. Further, in this case, the reference value S of the distance defining the extreme value region growth range is set to different values Sx and Sy depending on the x axis and the y axis, for example, Sx is set to 1, Sy is set to 2, and the extreme value It is also possible to make the size of the region growth range different from the x-axis direction and the y-axis direction to 3 × 5 pixels.

  FIG. 5B shows the relationship between the x-coordinate and y-coordinate change amounts i and j of the pixel in the extreme value region growth range 25 and the extreme value pixel p (x, y) in FIG. It is a figure which shows a relationship. In this figure, qm (m = 1 to 8 or 21 to 36) shown in each square is a pixel number used for explanation. In the following description, FIG. 5B is mainly used instead of FIG. FIG. 5C is a diagram illustrating an example of the density of pixels within the extreme value region growth range 25. The density values shown here are numerical values for explanation, and do not represent the actual image density.

  Returning to FIG. 4, the extreme value region growing unit 300 first sets the region growth success flag flag to the initial value NO in step S <b> 301. This value NO represents unsuccessful region growth. Next, the extreme value region adjacent pixel search unit 350 is executed. The extreme value area adjacent pixel searching unit 350 is activated by the extreme value area growing unit 300 and is an unprocessed pixel adjacent to the detected extreme value pixel p or adjacent to the extreme value pixel p. When a pixel determined to exist in the value area has already been detected, an unprocessed pixel adjacent to the pixel determined to be in the extreme value area and within a predetermined distance range from the extreme value pixel p Are detected.

  In the present embodiment, the extreme value region neighboring pixel search unit 350 starts from the pixel q21 in the upper left corner of FIG. 5B and starts to display pixels in the extreme value region growth range 25 from the left when activated for the first time. Search sequentially from right to top to bottom. That is, if the coordinates of the pixel to be searched are (x + i, y + j), i is changed from −S to + S in the state of j = −S, j is then increased by 1, and i is increased within the same range. Change with. Similarly, repeat until j exceeds S.

  FIG. 6 is a schematic flowchart of an example of processing performed by the extreme value region adjacent pixel search unit 350. Specifically, when activated, the extreme value region adjacent pixel search unit 350 determines whether or not the value of the region growth success flag flag is YES in step S351. When the extreme value region neighboring pixel search unit 350 is first activated by the extreme value region growth unit 300, the value of the region growth success flag flag is set to NO in step S301 of FIG. In this case, since the value of the region growth success flag flag is not YES, the search pixel is initially set in step S352. In the present embodiment, the pixel q21 at the upper left corner of the extreme value region growth range 25 shown in FIG. 5B is set as the initial value of the search pixel. In step S353, the region attribute value of the search pixel is read from the region attribute data 22, and it is determined whether or not the region attribute value is “0”.

  FIG. 7 is a diagram illustrating a change example of the region attribute data 22 with respect to the pixels in the extreme value region growth range 25. In the figure, instead of the coordinates (x, y) of the corresponding pixel, the coordinates of the region attribute data 22 are derived from the x coordinate and y coordinate of the extreme point pixel p (x, y) as in FIG. The coordinate change amount (i, j) is shown. FIG. 11A shows a state in which the initial value setting unit 100 (FIG. 1) sets a value “0” indicating that the extreme region does not belong as the initial value of the region attribute data 22 for all the pixels of the captured image 21. Indicates. FIG. 5B shows an extreme value as an area attribute value for the extreme point pixel p in step S204 (FIG. 3) when the extreme point pixel p is detected by the extreme point pixel search unit 200. It is a figure which shows the state where the value "1" which shows area | region affiliation was set. The region of the extreme point pixel p is the 0th-order maximum region M0 (p) referred to in Equation 1.

  As assumed now, the extreme value region adjacent pixel search unit 350 is activated first, and when the pixel q21 (FIG. 5B) is a search pixel, the region attribute of the pixel is “0”. Returning to FIG. 6, when it is determined in step S353 that the region attribute of the search pixel is “0”, in step S354, the region attribute value “adjacent to the search pixel (that is, one of the eight neighboring pixels)” It is determined whether or not there is a pixel “1”. When the extreme region neighboring pixel search unit 350 is first activated as assumed now, the pixel having the region attribute value “1” is only the detected extreme point pixel p. Therefore, since the search pixel q21 is not a pixel adjacent to the extreme point pixel p, it is determined in step S354 that there is no adjacent pixel having the region attribute value “1”.

  In this case, in step S355, the next pixel, that is, the right adjacent pixel q22 is set as a search pixel. Thereafter, in step S356, it is determined whether or not the increment j of the y coordinate of the new search pixel q22 has exceeded the distance limit value S. If not, the processes in and after step S353 are repeated. As a result, in the case of FIG. 5B, when the pixel q1 becomes the search pixel, the region attribute value that is adjacent to the pixel p becomes the pixel having the value “1” for the first time. Therefore, the determination is Yes in both steps S353 and S354. In that case, the extreme value region adjacent pixel search unit 350 succeeds in searching for an adjacent pixel, and returns to the extreme value region growth unit 300 with a return value “success” in step S357.

  Returning to FIG. 4, in the extreme value region growing unit 300, in step S <b> 302, it is determined whether or not the search for the adjacent pixel is successful. The density of all the pixels (extreme region belonging pixels) r having the region attribute value “1” adjacent to (that is, 8 neighboring pixels) is obtained. In the present assumption, when the pixel q1 is a search success pixel, the adjacent extreme value region belonging pixel detected in step S303 is only the extreme value point pixel p. In step S304, it is determined whether or not the condition that at least one pixel equal to or higher than the density of the search pixel q1 is present among the obtained densities of all the extreme value region belonging pixels r is satisfied. When this condition is satisfied, the search success pixel q1 has a monotonously decreasing relationship with the adjacent extreme value region belonging pixel.

  As described above, in the present assumption, the extreme value region belonging pixel adjacent to the pixel q1 is only the extreme value pixel p, and the density thereof is the density of the pixel q1 in view of the definition of the extreme value pixel p. Not lower. Accordingly, in step 304, it is determined that the pixel q1 satisfies the monotonous change relationship. When the search pixel satisfies the monotonous change relationship, in step S305, the region attribute value of the pixel is changed to a value “0.5” representing the extreme region belonging candidate. Further, in step S306, the region growth success flag flag is set to YES, and the process returns to the extreme value region adjacent pixel search unit 350.

  Referring to FIG. 6, in the case of the current assumption, the extreme value region adjacent pixel search unit 350 determines that the region growth success flag flag is YES in step S <b> 351. In this case, the process proceeds to step S355, and the next pixel q2 of the immediately previous search pixel (q1 in FIG. 5B under the current assumption) is set as the search pixel. Thereafter, in step S356, it is determined that the difference between the y coordinate of the new search pixel q2 and the y coordinate of the extreme point pixel p is not greater than the distance limit value S, and the processing from step S353 onward is executed for the search pixel q2. The Since the search pixel q2 is also a pixel that does not belong to the extreme value region and is adjacent to the extreme value point pixel p, the extreme value region adjacent pixel search unit 350 succeeds in searching for an adjacent pixel, and the extreme value region growth unit 300 Return to.

  The extreme value region growing unit 300 (FIG. 4) executes the processing from step S303 onward for this pixel q2 as well as the processing for the pixel q1. The pixel belonging to the adjacent region with respect to the pixel q2 is only the extreme point pixel p, and the pixel q2 is in a monotonous change relationship with the pixel p, which is the same as the pixel q1. Therefore, as in the case of the pixel q1, in step S305, the region attribute value of the searched adjacent pixel q2 is changed to “0.5”, and in step S306, the region growth success flag flag is set to YES again. Since the region growth success flag flag has already been set to YES, it is needless to say that the second and subsequent executions of step S306 may be omitted.

  The extreme value region growing unit 300 then executes the extreme value region adjacent pixel searching unit 350 again. In 350, each of the pixels q3 to q8 in FIG. The extreme value region growing unit 300 similarly performs the processing after step S303 for each of the pixels q3 to q8. In step S304, these pixels are determined to be pixels having a monotonous change relationship for the same reason as described for the pixel q1, and therefore, the region attributes of the pixels are set to “0.5” as in the pixels q1 and q2. Be changed. FIG. 7C shows an example of region attribute data for pixels in the extreme value region growth range 25 at this stage. In this way, the pixels q1 to q8 adjacent to the maximum point pixel p and in a monotonously decreasing relationship are detected. The area occupied by these pixels q1 to q8 is the first-order incremental area B1 (p) described in Expression 1.

  Returning to FIG. 4, after the pixel q8 is processed as described above, the processing returns to the extreme value region adjacent pixel search unit 350 again. In FIG. 6, the extreme value region adjacent pixel search unit 350 repeats the processing from step S355 onward, but in this case, as can be seen from FIG. 5B, in step S354, the extreme value point pixel p is adjacent. It is determined that no other pixel exists. Therefore, when other pixels are sequentially determined as search pixels in step S355, and finally a pixel outside the search range (pixel (x−S, y + S + 1) in FIG. 5A) is set as the search pixel, Since it is determined in step S356 that the increment j of the y coordinate of the search pixel has become larger than the distance limit value S, the search for the adjacent pixel is unsuccessful, and the extreme value adjacent pixel search unit 350 sets the return value to The process returns to the extreme value region growth unit 300 as “unsuccessful”.

  Returning to FIG. 6, when the extreme value region growing unit 300 determines that the search for the adjacent pixel is unsuccessful in step S <b> 302, in step S <b> 307, it is determined whether or not the region growth success flag flag is YES. If so, in step S308, the pixel having the region attribute value “0.5”, in this example, all the region attribute values of the pixels q1 to q8 are changed to the value “1” representing the extreme region belonging. change. FIG. 7D shows an example of region attribute values for pixels in the extreme value region growth range 25 at this stage. Thus, at this stage, the region including the maximum point pixel p and the adjacent pixels q1 to q8 that are monotonously decreasing is detected as the extreme value region (maximum region in this example). The region occupied by these pixels p, q1 to q8 is the first maximum region M1 (p) described in Expression 1.

  Returning to FIG. 4, the extreme value region growing unit 300 thereafter repeats the processing from step S <b> 301 onward. That is, in step S301, the region growth success flag flag is changed to NO again, and the extreme value region adjacent pixel search unit 350 is activated. Referring to FIG. 7, when the extreme value region neighboring pixel search unit 350 is called from the extreme value region growth unit 300 and determines that the value of the region growth success flag flag is NO in step S <b> 351, it has already been described. In the same manner as described above, adjacent pixels are searched for all the pixels in the extreme value region growth range 25. However, in this case, as shown in FIG. 7D, the region attribute data for the pixels in the extreme value region growth range 25 is the extreme value point pixel p and the eight pixels q1 to q8 surrounding it. On the other hand, the value is “1”. As a result, the search for adjacent pixels succeeds for the pixels adjacent to these eight pixels having the region attribute value “1”. That is, in the example of FIG. 5B, the adjacent pixel search is successful for each of the pixels q21 to q36.

  Returning to FIG. 4, the extremum region growing unit 300 performs the processing from step S303 on each search pixel in the same manner as when the adjacent pixel search is successful for each of the pixels q2 to q8. However, as illustrated in FIG. 7D, when each of the pixels q21 to q36 is a search pixel, the pixel adjacent to the pixels q21 to q36 is not the extreme point pixel p but the pixels q2 to q8. It differs from the case of pixels q2 to q8 in that it is one, two or three. Accordingly, the determination result of whether or not the search pixel is in a monotonous change relationship in steps S303 and S304 differs depending on each of the pixels q21 to q36. For example, when the pixel q21 is an adjacent pixel, only the pixel q1 is a pixel adjacent to the pixel and having a region attribute value “1”. In the example of FIG. 5C, since the densities of the pixels q1 and q21 are both 1, it can be seen that the pixel q21 is in a monotonous decreasing relationship, and the determination result in step S304 is YES. The region attribute value is set to a value “0.5” indicating the extreme region affiliation candidate. Thereafter, the region growth success flag flag is set to YES in step S306, the process returns to the extreme value region adjacent pixel search unit 350, and the extreme value region adjacent pixel search unit 350 is executed.

  Referring to FIG. 6, since the region growth success flag flag is set to YES, the extreme region adjacent pixel search unit 350 is executed for the pixel q22 subsequent to the pixel q21 processed last. . The pixel subsequent to the pixel q22 is processed in the same manner. However, if it is determined in step S304 in the extreme value region growing unit 300 that the pixel searched for as an adjacent pixel by the extreme value region adjacent pixel search unit 350 is determined not to satisfy the monotonic decrease relationship, No change is made to the region attribute data corresponding to the pixel, and the process moves to the extreme value region adjacent pixel search unit 350 again. For example, when the pixel q25 is selected as a search pixel by the extreme value region adjacent pixel search unit 350, in the extreme value region growth unit 300, the extreme value region belonging pixel adjacent to the pixel q25 is only the pixel q4. In the example of 5 (c), since the density of the pixel q25 is higher than the density of the pixel q4, it is determined that the pixel q25 is not in a monotonously decreasing relationship. Therefore, the region attribute value corresponding to the pixel q25 remains “0”. As for the pixel located at the boundary of the extreme value region growth range 25, such as the pixel q25, the extreme value region growth is not included in the other adjacent pixels whose density is compared with respect to whether the pixel is monotonously decreasing or monotonically increasing. Only pixels within the range 25 (only q4 in the above example) are used.

  On the other hand, in the density example of FIG. 5C, all the pixels other than the pixel q25 are in a monotonously decreasing relationship. Therefore. After each of the pixels q21 to q36 is searched as an adjacent pixel and steps S304 to S306 are performed on the pixel, the region attribute values for the pixels q21 to q36 are “0.5” except for the region attribute value of the pixel q25. Changed to FIG. 7E shows region attribute data at this stage. That is, the region attribute values for the pixels q21 to q24 and q26 to q36 are changed to “0.5”. The area occupied by these pixels is the second incremental area B2 (p) described in Equation 1.

  In the extreme value region growing unit 300, after executing steps S305 and S306 for the pixel q36, the extreme value region adjacent pixel searching unit 350 is executed again. Referring to FIG. 6, in the extreme value region adjacent pixel search unit 350, after processing the pixel q <b> 36, a pixel adjacent to a pixel whose region attribute value is “1” is behind the pixel q <b> 36. Since it is not within the growth range 25, it is determined in step S356 that the increment j of the search pixel is larger than the distance limit value S. And the return value is set to “unsuccessful” and the process returns to the extreme value region growing unit 300. Since the region growth success flag flag is YES in this state, the region attribute value “0.5” for the pixels q21 to q24 and q26 to q38 is changed to the value “1” in step S308 as described above. FIG. 7F shows the value of the region attribute data 22 at this stage. In the extreme value region growth range 25, the region attribute value is 1 for pixels other than the pixel q25. The area occupied by the pixel having the attribute value “1” is an example of the second maximum area M2 (p) in Expression 1.

  Thereafter, in the extreme value region growing unit 300, the region growth success flag flag is set to NO in step S301, and the extreme value region adjacent pixel searching unit 350 is executed again. However, in the extreme value region adjacent pixel search unit 350, since the processing for all the pixels in the extreme value region growth range 25 has been completed, in step S356, the increment of the y coordinate of the search pixel is the distance reference value S. In step S358, the return value is set to “unsuccessful” and the process returns to the extreme value region growing unit 300. This means that the third incremental region B3 (p) in Equation 1 is an empty region. Therefore, as shown in Expression 2, it means that the pixel region (M2 (p)) having the value “1” shown in FIG. 7F becomes the final maximum region M (p). In the extreme value region growing unit 300, it is determined in step S302 that the search for adjacent pixels is unsuccessful, and if it is determined in step S307 that the region growth success flag flag is not YES, it is determined that the region growth has ended and spot image detection is performed. Return to program 40. Thus, the processing of the extreme value region growing unit 300 for the detected extreme value point pixel p is completed.

  FIG. 8A is a diagram illustrating another example of the captured image 21. (B) is a figure which shows the example of the area | region attribute data with respect to the captured image. The state of execution of region growth processing in the extreme value region growth unit 300 will be described more specifically with reference to these drawings. FIG. 6A shows the pixels in the extreme value region growth range 25 with respect to the maximum point pixel (the pixel surrounded by a double circle) having the maximum value “5” at the center, and FIG. The attribute values for the pixels in the value area growth range 25 are shown.

  In the captured image of FIG. 9A, a plurality of pixels having a pixel value “5” are arranged. In the following, a pixel is designated by its coordinates (i, j). The local maximum pixel is the pixel (0, 0), and it is determined in step S203 (FIG. 3) of the extreme point pixel search unit 200 that this pixel is the local maximum pixel. As in (b), it is assumed that the value “1” is set in step S204 (FIG. 3) of the extreme point pixel search unit 200. When the extreme value region growth unit 300 (FIG. 4) is executed for this pixel, the pixel having the region attribute value “0” in the extreme value region growth range 25 is changed from the pixel (−2, −2) in the upper left corner. It is determined whether the pixel is adjacent to a pixel having a region attribute value of “1” (only pixel (0, 0) at this stage) and the density is monotonously decreasing. Each of the eight pixels around (0,0) is determined to have a monotonic change relationship with respect to the maximum point pixel (0,0), and the region attribute of each pixel is the extreme value region as in FIG. The area attribute value “0.5” representing the affiliation candidate is changed, and thereafter, the area attribute value “0.5” is changed to the value “1” as in FIG. At this stage, the region attribute value for the pixel having the value “5” in the pixel (0, 1) is also “1”.

  Thereafter, when the processing of the extreme value region growing unit 300 is repeated again, the pixels having the region attribute value “0” in the extreme value region growing range 25 are sequentially selected from the pixels (−2, −2) in the upper left corner. Then, it is determined whether or not the pixel having the region attribute value “1” (at this stage, the maximum pixel (0, 0) and the surrounding eight pixels) is monotonously decreasing. At this stage, the above determination is made for each of the 16 pixels around the 8 pixels, and as a result, the pixels (−2, −2) to (−2, 2), (−1, −2), ( -1, 2), (0, -2), (0, 2), (1, -2), (1, 2), (2, -2) are determined as extreme value region affiliation candidates, and the region The attribute value is changed to “0.5”. For example, the pixels (0, 2), (1, 2) having a density value of 5 are both adjacent to the pixel (0, 1) having a region attribute value “1”, and the density is the pixel. It is judged that there is a monotonically decreasing relationship with respect to the concentration of This is because the density values of the pixels (0, 2) and (1, 2) are the same as the density value “5” of the pixel (1, 2).

  On the other hand, the leftmost pixel (2, -1) among the four pixels having the value 5 surrounded by a square is not in a monotonously decreasing relationship with the adjacent pixel having the region attribute value "1". To be judged. The same applies to the two pixels (2, 0) and (2, 1) on the right side. The pixel (2, 2) is also not determined to be in a monotonous decreasing relationship. This is because the density of this pixel is higher than the density of any of the adjacent inner pixels whose area attribute value is “1”. It should be noted that this pixel (2, 2) is adjacent to the pixel (1, 2) one level above it, and the density is equal to the density, but at this time, the region attribute of the pixel (1, 2) The value is “0.5”, and even if it is adjacent to the pixel (2, 2), the extreme value region growing unit 300 does not make it a target for comparing the density with the pixel (2, 2). Thus, whether or not the pixel (1, 2) belongs to the extreme value region even if the pixel (1, 2) is an extreme value region affiliation candidate and the region attribute value is set to “0.5”. When determining, it is not determined whether or not there is a simple decrease relationship with the density of the pixel.

  As described above, when the extreme value region growing unit 300 determines whether or not the pixels around the maximum point pixel belong to the extreme value region, the density of the adjacent pixel whose region attribute value is “0.5” is determined. Whether or not there is a monotonic change relationship is determined by not determining whether the region attribute value is adjacent to a pixel having a value of “0.5”, but the pixel density on the path is a monotonous change relationship as a path from the maximum point p. This is because it can be surely prevented that a pixel having no path exists in the extreme value region by mistake. Accordingly, in the present embodiment, a pixel (for example, (1,2,1) whose density is monotonously changed with respect to the pixel adjacent to the pixel (for example, the pixel (0,1)) whose region attribute value is “1”. ) Is detected, the region attribute value of the detected pixel (1, 2) is temporarily set to “0.5”, and the region growth is successful (step S306 (FIG. 4)). When the processing of 350 is repeated and the search for adjacent pixels for the extreme value region is completed, the region attribute value of the pixel (1, 2) or the like whose region attribute value is “0.5” is changed to “1”. (Step S308 (FIG. 4)), and then the process of the extreme value region growing unit 300 is repeated again.

  In the present example, at this stage, the area attribute values of four pixels (2, -1) to (2, 2) having a value of 5 surrounded by a square are "0", and areas for all other pixels are displayed. The attribute value is “1”. In this state, when the processing of the extreme value region growing unit 300 is repeated, the rightmost pixel (2, 2) among the above four pixels has the region attribute value “1” immediately above it. The density of the pixel (1,2) is monotonously decreased with respect to the density of the pixel (1,2) because the density of these two pixels is equal to 5 It is determined that there is a relationship and is detected as an extreme value region pixel, and the region attribute value of the pixel (2, 2) is set to a value “0.5” indicating an extreme value region affiliation candidate. The region attribute values of the other three pixels (2, −1), (2, 0), and (2, 1) remain “0”. Thereafter, the process of the extreme value region growing unit 300 is repeated, and the region attribute value of the pixel (2, 2) having the region attribute value “0.5” is set to “1”.

  Thereafter, the processing of the extreme value region growing unit 300 is repeated, and this time, the pixel (2, 1) is adjacent to the pixel (2, 2) having the region attribute value “1”, and the density is monotonously decreasing. And the region attribute value of the pixel (2, 1) is set to “0.5”. The region attribute values of the other two pixels (2, −1) and (2, 0) remain “0”. Thereafter, in the extreme value region growing unit 300, the region attribute value of the pixel (2, 1) having the region attribute value “0.5” is set to “1”. Thereafter, the processing of the extreme value region growing unit 300 is repeated. As a result, the pixel (2, 0) is adjacent to the pixel (2, 1) whose region attribute value is “1”, and the density monotonously decreases. It is determined that there is a relationship, and the region attribute value of the pixel (2, 0) is set to “0.5”. The area attribute values of the other pixels (2, −1) remain “0”.

  Thereafter, the processing of the extreme value region growing unit 300 is repeated, the region attribute value of the pixel (2, 0) having the region attribute value “0.5” is set to “1”, and the processing of the extreme value region growing unit 300 is repeated. It is. Thereafter, similarly, the region attribute value of the pixel (2, −1) is set to “1”, and then the processing of the extreme value region growing unit 300 is finished. As a result, for the captured image shown in FIG. 8A, the region attribute is “1” for all pixels in the extreme value region growth range 25 as shown in FIG. As can be seen from the above processing, every time the processing of the extreme value region growth unit 300 is repeated, the extreme value region growth unit 300 searches for the pixel again from the initial value pixel in the extreme value region growth range 25. The process is repeated for the pixel having the region attribute value “0” in the entire growth range 25. In this manner, by repeatedly executing the pixel search for the pixel having the region attribute value “0” in the entire extreme value region growth range 25, the region attribute value of the pixel at the special position becomes “1”. Even after this, it is possible to prevent the pixel having the region attribute value “0” adjacent to the pixel from becoming the search target.

  As described above, when the processing of the extreme value region growing unit 300 ends, the processing returns to the main routine of the spot image detection program 40. Referring to FIG. 1, in the spot image detection program 40, an extreme value region determination unit 400 is executed. FIG. 9 is a schematic flowchart of an example of processing of the extreme value region determination unit 400. Here, it is determined whether or not the detected extreme value region is a region included in the spot image representing the automobile that is the detection target. First, in step S401, when the detected extreme value region is a maximum region, the minimum value m of the density of the pixels belonging to the maximum region is obtained. If the detected extreme value region is a minimal region, the maximum density m of the pixels belonging to the minimal region may be obtained.

  In step S402, it is determined whether or not the absolute value of the difference between the density of the extreme point pixel p and the detected minimum density value m is greater than or equal to the threshold value Tw. The threshold value Tw is determined in advance by trial and error depending on the density difference that normally occurs with respect to the spot image that represents the detection object so that the density difference that normally occurs with respect to the spot image that represents the detection object is equal to or greater than the threshold value. To be determined. The threshold value Tw changes depending on the reference value S of the distance when searching for a monotonically changing pixel belonging to the extreme value region. Therefore, it is necessary to change the reference value S of the distance depending on the size of the detection object. The threshold value Tw is desirably determined based on the distance reference value S thus determined.

  When the result of determination in step S402 is YES, in step S403, the size of the detected extreme value region is detected. In the present embodiment, for example, as an example of the width of the extreme value region, the total number n of pixels included in the detected extreme value region is detected. In step S404, it is determined whether or not the width of the extreme value region is larger than a predetermined width depending on the detection target. Therefore, specifically, it is determined whether or not the number of pixels n detected in step S403 is equal to or greater than the width threshold Ns. This threshold value Ns is determined in advance so that an extreme value region belonging to a small spot image representing an object smaller than the detection target is not erroneously detected when included in the spot image representing the detection target. For example, when using a captured image in which a spot image representing an automobile is about 3 × 6 pixels, as described above, the reference value S of the distance that determines the extreme value region growth range is set to 2, and the extreme value region growth range is set. When the size is 5 × 5, 3 × 3 = 9 pixels can be used as the number of pixels for determining the width threshold Ns. Further, as described above, when the size of the extremum region growth range is varied in the x-axis and y-axis directions according to the direction of the car body, such as 3 × 5, the width threshold Ns is determined. The number of pixels can be 2 × 3 = 6 pixels

  When the determination result in step S404 is YES, it is determined that the detected extreme value region is an extreme value region included in the spot image representing the detection target, and in step S405, the extreme value region determination unit 400 is determined. Returns to the main routine of the spot image detection program 40 with the return value “pass”.

  When the result of determination in step S402 is NO, it is determined that the detected extreme value region is not included in the spot image representing the detection target, and similarly, the result of determination in step S404 is NO. When it is, it is determined that the detected extreme value region is not included in the spot image representing the detection target. When the determination result in any of steps S402 and S404 is NO, in step S407, the extreme value area determination unit 400 sets the return value to “fail” and returns to the main routine of the spot image detection program 40.

  Returning to FIG. 1, in the spot image detection program 40, after the execution of the extreme value region determination unit 400, the detected extreme value region is detected in the extreme value region pass / fail determination step S 450 based on the return value therefrom. It is determined whether or not it has passed as an extreme value region included in the spot image for use. If it is acceptable, the spot image related data generation unit 500 is executed. The spot image related data generation unit 500 generates spot image related data for the extreme value area determined to be acceptable and stores it in the storage device 20. The spot image related data generated by the spot image related data generation unit 500 includes extreme value region data 23 and image data 24 with a spot image marker.

FIG. 10A is a diagram illustrating an example of the extreme value region data 23. As will be described later, the identification information of the extreme value region is determined for the extreme value region determined to be acceptable, and the minimum rectangular region ABCD (square or square) surrounding the extreme value region is determined as the existence range of the extreme value region. The extreme area data 23 includes the determined extreme area identification information 231, the coordinates (x, y) 232 of the extreme point pixel p, and the vertices A, B, C, and D of the rectangle ABCD. Coordinates (x, y) 233 are stored. FIG. 6B is a diagram schematically showing the image data 24 with spot image markers.
The example of the region attribute data obtained for the case of FIG. 5C has the value “1” for the pixels other than the pixel q25 shown in FIG. 5B as shown in FIG. . Therefore, the extreme value region is an extreme value region 241 including pixels p, q1 to q8, q21 to q24, and q26 to q36 excluding the pixel q25. Assuming that the extreme value region 241 is determined to be acceptable as an extreme value region belonging to the spot image representing the detection target, the rectangle determined for the extreme value region 241 is an extreme value region including the pixel q25. A rectangle 242 including 241 is formed.

  The marker graphic 243 is added in the vicinity of the passed extreme value region on the copy image of the captured image 21 in order to clearly indicate that the passed extreme value region is the extreme value region belonging to the spot image representing the detection target. The figure is drawn. In the example of FIG. 10B, a white band-like figure with a width of one pixel located closest to the outside of the rectangle 242 is used as the marker figure. In the figure, the marker graphic 243 is hatched for easy understanding, but here is a graphic representing a white region. As the marker graphic, a white band-shaped graphic having a width of 1 pixel or 2 pixels located inside the outer periphery of the rectangle 242 may be used. FIG. 10C illustrates an example of spot image marker-added image data 24 in which a marker graphic is added to an extreme value region detected as belonging to a spot image representing a car included in the captured image 21 of FIG. 2B. Indicates. In this figure, the size of the extreme value region growth range is 5 × 5 pixels. As the marker graphic, a white band-shaped graphic with a width of one pixel located inside the outer periphery of a rectangle including the detected extreme value region is displayed.

  FIG. 11 is a schematic flowchart of an example of processing of the spot image related data generation unit 500. First, an extremum area composed of the detected extremum point pixel and its monotonically changing pixel group overlaps with another extremum area consisting of another already detected extremum point pixel and its monotonically changing pixel group. It is determined whether or not. If they overlap, two extreme point pixels are detected for the same spot image, and one of the maximum point pixels is invalidated. Thereby, one extreme point pixel is detected for one spot image. In the present embodiment, when determining the overlap of the extreme value region, the smallest rectangle that includes the extreme value region is determined, and it is determined whether or not it overlaps with the rectangles of other extreme value point pixels. Whether or not the rectangles overlap can be determined by comparing the vertices, which is simpler than accurately determining the overlap of the extreme value regions. Of course, it is needless to say that overlapping of extreme value regions may be directly determined without using the rectangle.

In the present embodiment, in step S501, the minimum rectangular area ABCD that includes the extreme value area is determined. In step S502, when the determined rectangle and the already detected data of another extreme value region are stored in the extreme value region data 23, it is determined whether or not the other rectangle overlaps. The case where the rectangle overlaps with another rectangle will be described later.
If no overlap is detected, identification information is determined for the extreme value region determined to be acceptable in step S503, stored in the field 231 of the extreme value region data 23, and detected in step S504. The x and y coordinates of the point pixel p are stored in the field 232 of the extreme value region data 23. In step S 505, the x and y coordinates of the newly determined rectangular vertices A, B, C, and D are stored in the field 233 of the extreme value region data 23. In step S506, the position and size of the detected marker pattern for the extreme value area are determined, and the resultant is superimposed and drawn on the image data 24 with the spot image marker. By executing the spot image-related data generation unit 500 in this way for a plurality of extreme value regions detected and determined to be acceptable, image data 24 with spot image markers as illustrated in FIG. 10C is generated. Is done.

  When the rectangle generated for the newly detected extremum area determined in step S502 of FIG. 11 is superimposed on another extremum area inclusion rectangle already registered in the extremum area data 23, Occurs when extreme points are located in the vicinity of the same image. The case where such extreme value area inclusion rectangles overlap will be described later.

  In FIG. 11, when the determination result in step S502 is YES, in step S507, one of the two overlapping rectangles is selected based on a predetermined criterion. An example of the reference will be described later. It is determined in step S508 whether another previously generated rectangle has been selected. If the determination result is No, in step S509, the image is attached to the other extreme value region from the spot image marker-added image 24. The value of the pixel constituting the marker graphic is rewritten to the value of the corresponding pixel in the original captured image 21. Thus, the marker graphic attached to the other extreme value area is deleted. In step S510, data related to the other extreme value region is deleted from the extreme value region data 23.

  By these processes, the other extreme value areas detected earlier are invalidated and are regarded as not detected. Thereafter, the process proceeds to step S503, and as described above, steps S503 to S506 are executed for the extreme value region related to the newly determined rectangle, and the process returns to the main routine of the spot image detection program 40.

  If the determination result in step S508 is Yes, the process returns to the main routine of the spot image detection program 40. As a result, the extreme value region detected this time is regarded as not detected. Thus, the process of the spot image related data generation unit 500 is completed. Returning to FIG. 1, in the spot image detection program 40, the process proceeds to the initial value setting unit 100. When the initial value setting unit 100 is repeated after the second time, the extreme value centered on the extreme point pixel processed by the extreme value region growing unit 300 in the imaging data 21 is different from the case of being executed first. Only the region attribute value in the region attribute data 22 is set to the initial value 0 for all pixels in the region growth range. This is because only the region attribute values for all the pixels within the extreme value region growth range may be changed when the extreme value region growth unit 300 is executed. Thereafter, the search for new extreme pixels is continued by the extreme point pixel search unit 200. When a new extreme value pixel is found, the processing after the extreme value region determination unit 400 is executed as described above. As a result of repeating the above processing, when it is determined in search success / failure determination step S250 that a new extreme pixel has not been detected, the spot image detection program 40 ends the processing. As described above, as illustrated in FIG. 10C, the spot image marker-added image data 24 in which the marker graphic is added to the plurality of spot images representing the detection target is generated.

  FIG. 12 is a diagram showing some other examples of the captured image 21 and the corresponding region attribute data 22. The captured image 21 mainly shows a portion within the extreme value region growth range, and the coordinate of the pixel is changed from the maximum point coordinate (x, y), i, j, instead of the (x, y) coordinate. It is shown. The area attribute data 22 also indicates area attribute values corresponding to pixels in the same range of the captured image 21. The region attribute data 22 also shows the coordinate changes i, j used to display the captured image 21. In (a), two pixels having the same density “5” are adjacent to each other. That is, the pixels on the upper side of density 5 surrounded by circles and the pixels on the lower side of density 5 surrounded by squares. Since these pixels are adjacent to each other, this corresponds to a case where adjacent pixels in the same car spot image have the same density. In the extreme point pixel search unit 200, the upper density “5” pixel is not lower than the density of the adjacent pixels, and is therefore detected as a maximum point pixel. The pixel group in the extreme value region growth range 25 of this pixel is shown in FIG. Thereafter, when the extreme value region processing is executed in the extreme value region growing unit 300, the pixel having the lower density 5 is adjacent to the extreme point pixel having the upper density 5, and the density is the upper density 5 Therefore, it is determined that the pixel belongs to the extreme value region including the upper extreme value pixel. As a result, the region attribute data 22 is as shown in FIG. As described above, even if pixels having the same density as the extreme point pixels are adjacent to each other, the pixels are determined to belong to the same extreme value region.

  FIG. 12C is a diagram illustrating still another example of the captured image 21. In the case of the figure, two pixels of different densities are present apart in the vertical direction. That is, the upper pixel of density 5 surrounded by a circle and the lower pixel of density 6 surrounded by a square. Since these pixels are separated by only two pixels, the distance between them is determined by the extreme value region growth determined by the distance reference value S (which is assumed to be 2 here) that specifies the extreme value region growth range. It is below the range (2S + 1). Therefore, these pixels belong to a spot image representing the same car, and are considered to be pixels showing two peak points at very close positions. In the extreme point pixel search unit 200, each of these pixels is detected as a maximum point pixel. Reference numerals 25a and 25b respectively show an example of the extreme value region growth range for the first local maximum pixel having the upper density 5 and an example of the extreme value region growth range for the second local maximum pixel having the lower density 6.

  FIG. 6D shows an extreme value region 241 a detected by the extreme value region growing unit 300 and the spot image related data generating unit 500 for the first maximum point pixel having the density 5 on the upper side of FIG. It is a figure which shows the minimum rectangle (extreme value area | region inclusion rectangle) 242a surrounding the produced | generated extreme value area | region 241a. It can be seen that the extreme value region 241a does not include the second maximum point pixel (2, 0) and the adjacent pixels (2, -1) and (2, 1).

  FIG. 6E shows an extreme value region 241b detected by the extreme value region growing unit 300 for the second maximum point pixel having a density of 5 at the lower side of FIG. It is a figure which shows the minimum rectangle (extreme value area | region inclusion rectangle) 242b surrounding the extreme value area | region 241b produced | generated by the production | generation part 500. FIG. In FIG. 9E, the same value is displayed for the same coordinate value i in the vertical direction as the vertical coordinate value i in FIG. It can be seen that the extreme value region 241b does not include the first maximum point pixel (0, 0).

These two extreme value regions 241a and 241b overlap each other except for the pixel (0, 0) with respect to the pixel with i = 0. The rectangles 242a and 242b also overlap. When the extreme value regions 241a and 241b are both determined to be acceptable by the extreme value region determination unit 400, one of the extreme value region inclusion rectangles corresponding to them is previously determined in step S507 of the spot image related data generation unit 500 (FIG. 11). Selected according to established criteria.
For example, when the concentrations of the maximum points of the extreme value regions 241a and 241b are different, a rectangle including the higher concentration (in this case, the second maximum point of the concentration 6) can be selected. Alternatively, a rectangle including a larger number of pixels (extreme value region 241b in this case) included in each of the extreme value regions 241a and 241b can be selected. Alternatively, the one having a larger difference between the density of the maximum point pixel and the minimum value of the pixels in the extreme value region can be selected. Furthermore, by combining several selection criteria as described above, a criterion for selecting two extreme value regions where the extreme value region inclusion rectangles overlap may be determined. For example, when the densities of the maximum points are different, a rectangle including the higher density can be selected, and when the densities of the maximum points are the same, a rectangle including the larger number of pixels contained therein can be selected.

  As is clear from the above, in this embodiment, it is possible to easily detect an extreme value region including a maximum point pixel that is considered to be included in a spot image of a detection object such as an automobile, and the proximity. Even if two extreme point pixels are detected and the extreme value region inclusion rectangles overlap, one of the maximum point pixels and the extreme value region and extreme value region inclusion rectangle can be selected. It becomes possible to detect one maximum point pixel that is considered to be representative of a spot image of an object, an extreme value region, and an extreme value region-containing rectangle.

  Needless to say, the present invention is not limited to the following embodiments. For example, in the above embodiment, the example in which the region attribute data 22 has a field that holds the region attribute value corresponding to all the pixels of the captured image data has been described. Each may have a field for holding a region attribute value. In this case, the region attribute data 22 is used in common for the extreme value region growth range of all extreme value point pixels. Therefore, the area attribute data having such an aspect requires less data. In order to detect a car having a darker density than the background, the minimum area may be detected in the same manner as the maximum area described above. Further, when the captured image is a color image, lightness data generated from the color image may be used as the density data.

1 is a schematic block diagram of an embodiment of a spot image detection device according to the present invention. (A) is a figure which shows captured image data typically. (B) is a figure which shows the example of the actual geographic image obtained by actually image | photographing the ground from an artificial satellite. (C) is a figure which shows typically the area | region attribute data corresponding to captured image data. It is a schematic flowchart of an example of a process of an extreme point pixel search part. It is a schematic flowchart of an example of the process of an extreme value area | region growth part. (A) is a figure which illustrates the extreme value region growth range. (B) is a figure which shows the relationship between the coordinate change amount i and j from the x coordinate of a pixel in the extreme value area growth range, and the extreme value point pixel p (x, y), y coordinate. (C) is a figure which shows the example of the density | concentration of the pixel in an extreme value area | region growth range. It is a schematic flowchart of an example of a process of the adjacent pixel search part for extreme value areas. It is a figure which shows an example of the change of the area | region attribute data in the extreme value area growth range. It is a figure which shows the other example of a captured image, and the example of the area | region attribute data with respect to it. It is a schematic flowchart of an example of a process of an extreme value area | region determination part. (A) is a figure showing an example of extreme value field data. (B) is a figure which shows typically the image data with a spot image marker. (C) is a figure which shows the example of image data with a spot image marker. It is a schematic flowchart of the example of a process of a spot image relevant data generation part. It is a figure which shows the example of the area | region attribute data corresponding to the other some examples of a captured image.

Explanation of symbols

  241, 241 a, 241 b... Extreme value area, 242, 242 a, 242 b... Extreme area including rectangular area, 243, 243 a, 243 b.

Claims (8)

From a photographed image including a plurality of spot images representing a plurality of detection objects obtained by photographing a plurality of detection objects, the density is a maximum value or a minimum value with respect to the density of surrounding pixels. An extreme point pixel detection step for detecting a group of extreme point pixels having a density that is one of the predetermined extreme values;
There is a predetermined distance depending on the size of the detection object from each of the detected group of extreme point pixels, and the density monotonously changes with respect to the density of the extreme point pixels. A monotonic change pixel group detecting step for detecting a group of monotone change pixels in the captured image;
Of the minimum density or the maximum density of the density of the group of monotonically changing pixels detected for each of the group of extreme value point pixels, a predetermined density to be compared with the density of the extreme value pixel is predetermined. A comparison target concentration detection step for detecting any one of the concentrations as a comparison target concentration;
An absolute value of a density difference between each density of the group of extreme value point pixels and the comparison target density detected with respect to the extreme value pixel is a predetermined value corresponding to the detection object. An extreme value region including the extreme value pixel and the monotonically changing pixel group detected with respect to the extreme value pixel, depending on whether or not the density difference is equal to or greater than a threshold value, is the plurality of detection targets. An extreme value region determination step for determining whether the region is included in one of the plurality of spot images representing an object;
A spot image detection method comprising: One of the plurality of spot images in which an extreme value region including any one of the group of extreme value point pixels and the monotonically changing pixel group detected with respect to the extreme value point pixel represents the plurality of detection objects. A position storage step of storing the position of the extreme point pixel as the position of the one spot image when it is determined that the region is included in
The spot image detection method according to claim 1, further comprising: A width detecting step of detecting a width of an existing area of the group of monotonically changing pixels detected for each extreme point pixel;
In the extreme value region determination step, the absolute value of the density difference detected for the extreme value point pixel is equal to or greater than a threshold value of the density difference, and the wide area value detected for the extreme value pixel is detected. Is determined in advance depending on the size of the object to be detected, and depending on whether or not the threshold value is equal to or larger than a threshold of a predetermined width that is narrower than the width determined by the predetermined distance, Whether or not an extreme value region including the monotonically changing pixel group detected for the extreme point pixel is a region included in one of the plurality of spot images representing the plurality of detection objects. judge,
The spot image detection method according to claim 1 or 2, wherein The existence range of any extreme point pixel detected in the extreme point pixel detection step and the monotone change pixel group detected in the monotone change pixel group detection step with respect to the extreme point pixel, Existence range of any other extreme point pixel detected in the extreme point pixel detection step and the monotone change pixel group detected in the monotone change pixel group detection step with respect to the other extreme point pixel And an existing region overlap determination step for determining whether or not and
When the existence range for any one of the extreme point pixels overlaps the existence range for the other extreme point pixel, one of the extreme point pixel and the other extreme point pixel is An extreme point pixel invalidation step of invalidating the other extreme point pixel that is selected according to a predetermined criterion and not selected;
The spot image detection method according to claim 1, further comprising: From a photographed image including a plurality of spot images representing a plurality of detection objects obtained by photographing a plurality of detection objects, the density is a maximum value or a minimum value with respect to the density of surrounding pixels. Extreme point pixel detection means for detecting a group of extreme point pixels having a density which is one extreme value determined in advance;
There is a predetermined distance depending on the size of the detection object from each of the detected group of extreme point pixels, and the density monotonously changes with respect to the density of the extreme point pixels. A monotonous change pixel group detecting means for detecting a group of monotone change pixels in the captured image;
Of the minimum density or the maximum density of the density of the group of monotonically changing pixels detected for each of the group of extreme value point pixels, a predetermined density to be compared with the density of the extreme value pixel is predetermined. A comparison target concentration detection means for detecting any one of the concentrations as a comparison target concentration;
An absolute value of a density difference between each density of the group of extreme value point pixels and the comparison target density detected with respect to the extreme value pixel is a predetermined value corresponding to the detection object. An extreme value region including the extreme value pixel and the monotonically changing pixel group detected with respect to the extreme value pixel, depending on whether or not the density difference is greater than or equal to a threshold value, the plurality of detection targets Extreme value region determination means for determining whether or not the region is included in one of the plurality of spot images representing an object;
A spot image detection program for causing a computer to function. One of the plurality of spot images in which an extreme value region including any one of the group of extreme value point pixels and the monotonically changing pixel group detected with respect to the extreme value point pixel represents the plurality of detection objects. Position storage means for storing the position of the extreme point pixel as the position of the one spot image when it is determined that the region is included in
The spot image detection program according to claim 5, further causing a computer to function as the program. Further causing the computer to function as an area detecting means for detecting the area of the existence area of the group of monotonically changing pixels detected for each extreme point pixel;
The extreme value region determination means has an absolute value of the density difference detected for the extreme value point pixel equal to or greater than a threshold value of the density difference, and the wide area value detected for the extreme value point pixel. Is determined in advance depending on the size of the object to be detected, and depending on whether or not the threshold value is equal to or larger than a threshold of a predetermined width that is narrower than the width determined by the predetermined distance, Whether or not an extreme value region including the monotonically changing pixel group detected for the extreme point pixel is a region included in one of the plurality of spot images representing the plurality of detection objects. judge,
The spot image detection program according to claim 5 or 6, characterized by the above. The existence range of any extreme point pixel detected by the extreme point pixel detection means and the monotone change pixel group detected by the monotone change pixel group detection means for the extreme value pixel is Existence range of any other extreme point pixel detected by the extreme point pixel detection means and the monotonous change pixel group detected by the monotone change pixel group detection means with respect to the other extreme point pixel Presence region overlap determination means for determining whether or not and
When the existence range for any one of the extreme point pixels overlaps the existence range for the other extreme point pixel, one of the extreme point pixel and the other extreme point pixel is Extreme point pixel invalidating means for invalidating the other extreme point pixel that is selected according to a predetermined criterion and is not selected;
The spot image detection program according to claim 5, further causing a computer to function as the computer program.