JP2009222529A - Reflection characteristic evaluation device, reflection characteristic evaluation method and reflection characteristic evaluation program - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide a reflection characteristic evaluation device for stably and precisely judging the reflection characteristics of a surface without requiring cost in a case that the image photographed by a camera is inputted and the reflection characteristics of the surface part in the inputted image are outputted. <P>SOLUTION: The reflection characteristic evaluation device constituted so as to determine a threshold value for judging whether the surface part is mirror reflection or diffused reflection by the dispersion of the brightness variation of a circumferential part in the case that the image photographed by a camera is inputted and the reflection characteristics of the surface part in the inputted image are outputted and the surface part is set as the mirror reflection if the brightness variation of the surface part is more than the determined threshold value and outputted as the diffused reflection if the brightness variation of the surface part is below the determined threshold value. <P>COPYRIGHT: (C)2010,JPO&INPIT

Description

  The present invention relates to a reflection characteristic evaluation apparatus, a reflection characteristic evaluation method, and a reflection characteristic evaluation program for inputting an image photographed by a camera and outputting the reflection characteristic of a surface portion in the input image.

  Conventionally, a technique for evaluating the reflection characteristics of a surface portion in an image taken by a camera has been used for various purposes. For example, grasping the wet state of the road surface during vehicle travel is very useful for the vehicle to travel safely. To understand the wet condition of the road surface, photograph the road surface with an on-board camera to determine the wet state. If the road surface is wet, warn the driver or notify the vehicle control device etc. The vehicle can travel safely by making it run. And various techniques which image a road surface with a vehicle-mounted camera and determine a wet state are disclosed.

  For example, in Patent Document 1 (Japanese Patent No. 3438368), the wet state is determined by integrating the absolute value difference of the luminance fluctuation of the road surface image, and when the luminance difference is large, the wet state is determined. Specifically, in Patent Document 1, as shown in FIG. 13-1, one point on the road surface is tracked in accordance with the progress of the vehicle (see (1) in FIG. 13-1), and the luminance of the tracked point is determined. By accumulating the change, it is determined whether or not the wet state is determined by the magnitude of the change in luminance (see (2) in FIG. 13-1). That is, in Patent Document 1, a point in the image is in a wet state when there is a variation in luminance (see FIGS. 13-1 and 13-2), and is in a dry state when there is no variation in luminance (see FIG. 13). 13-3 and FIG. 13-4). 13A to 13D are diagrams for explaining the wet state determination process according to the related art.

  Further, for example, in Patent Document 2 (Japanese Patent Laid-Open No. 11-211659), a wet state is determined by comparing two images having different polarization components. Specifically, in Patent Document 2, a vertical polarization image and a horizontal polarization image are compared to determine whether it is specular reflection or diffuse reflection, and in the case of specular reflection, the wet state It is said.

Japanese Patent No. 3438368 Japanese Patent Laid-Open No. 11-211659

  However, the above-described conventional technique has a problem that a wet state cannot be detected when there is little variation in ambient luminance. In addition, the above-described conventional technique has a problem in that it is expensive because an apparatus capable of acquiring a plurality of polarization states is necessary.

  Specifically, in Patent Document 1, in order to determine the wet state based only on the luminance change at one point on the road surface, in a prairie or the like where the luminance variation is small, the surrounding luminance variation is small. Cannot be detected. In addition, it is conceivable to reduce the parameter for detecting the wet state so that it can be used even when there is little fluctuation in ambient brightness. It will be detected as a state.

  Further, in Patent Document 2, since two images, a vertically polarized image and a horizontally polarized image, are necessary, it is expensive to use a plurality of imaging devices. Note that, when two images are shot using one imaging device, the shooting is performed while changing the shooting direction, and thus costs are increased.

  Accordingly, the present invention has been made to solve the above-described problems of the prior art, and it is possible to stably and accurately determine the reflection characteristic of the surface without incurring cost. An object is to provide an apparatus, a reflection characteristic evaluation method, and a reflection characteristic evaluation program.

  In order to solve the above-described problems and achieve the object, a reflection characteristic evaluation apparatus disclosed in the present application is a reflection characteristic evaluation apparatus that receives an image captured by a camera and outputs a reflection characteristic of a surface portion in the input image. A first analyzing means for analyzing an image characteristic of a peripheral portion showing an upper portion in the input image, and tracking the same position of a surface portion showing a lower portion in the input image, Reflection of the surface portion based on the tracking means for acquiring the luminance fluctuation of the portion, the image characteristics of the surrounding portion obtained by the first analyzing means, and the luminance fluctuation of the surface portion obtained by the tracking means. And a second analyzing means for evaluating and outputting the characteristics.

  According to the reflection characteristic evaluation apparatus disclosed in the present application, it is possible to stably and accurately determine the reflection characteristic of the surface without incurring costs.

  Embodiments of a reflection characteristic evaluation apparatus according to the present invention will be described below in detail with reference to the accompanying drawings. In the following, the outline and features of the reflection characteristic evaluation apparatus according to the present invention, the configuration of the reflection characteristic evaluation apparatus, and the flow of processing will be described in order, and finally the effects of this embodiment will be described.

[Overview and Features]
First, the outline and characteristics of the reflection characteristic evaluation apparatus according to the first embodiment will be described with reference to FIGS. 1-1 and 1-2. FIGS. 1-1 and 1-2 are diagrams illustrating an overview and features of the reflection characteristic evaluation apparatus according to the first embodiment.

  This reflection characteristic evaluation apparatus uses an image taken by a camera mounted on a predetermined apparatus as an input image, and evaluates and outputs the reflection characteristic of a surface portion such as a road surface, the ground, or a floor in the input image. The evaluation of the reflection characteristics is output to a monitor, notified to the user by voice, or the operation of a predetermined device is controlled.

  In such a configuration, the reflection characteristic evaluation apparatus is an outline in which an image captured by a camera is input, and the reflection characteristic of the surface portion in the input image is output, and particularly without cost. The main feature is that the surface reflection characteristics can be determined stably and accurately. In the following, a case will be described in which the road surface reflection characteristics in an image taken by an in-vehicle camera are evaluated.

  Specifically explaining the main feature, the reflection characteristic evaluation apparatus extracts the horizontal plane of the input image, tracks the same position of the surface portion indicating the portion below the extracted horizontal plane, and determines the luminance of the surface portion. Fluctuations are acquired (see (1) in FIG. 1-1). In this embodiment, the upper and lower portions are extracted from the image with reference to the horizontal plane extracted from the image. However, the upper and lower portions are extracted from the image without extracting the horizontal plane. Also good. For example, the camera is installed in advance so that the Y coordinate (the center in the vertical direction of the camera) is approximately the horizontal plane, that is, the position of the horizontal line, and the screen is separated vertically from the center of the captured screen. Alternatively, the upper part may be extracted with the upper part as the upper part and the lower part with respect to the center as the lower part. Further, for example, the upper 1/3 region of the screen may be extracted as the upper portion, and the lower 1/3 region of the screen may be extracted as the lower portion.

  More specifically, when an image photographed by a vehicle-mounted camera is input, the reflection characteristic evaluation apparatus extracts a horizontal plane indicating a boundary between a road surface portion and a road surface upper portion of the input image. Then, the reflection characteristic evaluation device performs tracking to follow the same position of the surface portion (road surface portion) indicating the portion below the extracted horizontal plane in accordance with the progress of the vehicle. Get brightness variation.

  In addition, as shown in FIG. 1-2, the brightness | luminance fluctuation | variation of the surface part in FIG. 1-1 has a low brightness | luminance when a mountain is reflected in the puddle in the position far from a vehicle, and exists in the position close | similar to a vehicle. The brightness increases when the sky is reflected in the puddle. That is, it can be seen that when a mountain and sky as shown in FIG. 1-1 are reflected in a puddle on the surface portion, the luminance fluctuation of the surface portion is larger than that on a dry road surface.

  Then, the reflection characteristic evaluation apparatus analyzes the image characteristics of the surrounding portion indicating the portion above the extracted horizontal plane (see (2) in FIG. 1-1). Specifically, in the above example, the reflection characteristic evaluation apparatus acquires a spatial luminance variation of a surrounding portion (upper portion) indicating a portion above the extracted horizontal plane, and image characteristics of the surrounding portion are obtained. Analyze. Then, the reflection characteristic evaluation apparatus determines a large threshold value when the luminance change of the surrounding portion is large, and determines a small threshold value when the luminance change of the peripheral portion is small, based on the obtained variance of the luminance variation.

  Subsequently, the reflection characteristic evaluation apparatus evaluates and outputs the reflection characteristic of the surface portion based on the obtained image characteristic of the surrounding portion and the obtained luminance fluctuation of the surface portion (FIG. 1-1). (See (3)). Specifically, in the above example, the reflection characteristic evaluation apparatus is configured to determine the threshold value for determining the luminance variation of the surface portion based on the obtained image characteristics of the surrounding portion and the acquired luminance variation of the surface portion. It is determined whether it is above or below the threshold.

  Then, the reflection characteristic evaluation apparatus determines that the surface portion is in a wet state and outputs it when the luminance variation of the surface portion is equal to or greater than the threshold value, assuming that the luminance variation is due to water accumulation (specular reflection). In addition, when the luminance fluctuation of the surface portion is less than the threshold, the reflection characteristic evaluation apparatus determines that the surface portion is in a dry state and outputs the luminance fluctuation due to the normal road surface (diffuse reflection).

  In addition, when the surface portion is wet due to water accumulation, the reflection of the light source occurs because it is a glossy surface, and the brightness changes greatly due to specular reflection, and the surface portion becomes a normal road surface. In the dry state due to the above, since the surface is rough, the light source is not reflected, and the luminance fluctuation is reduced by diffuse reflection.

  That is, the reflection characteristic evaluation apparatus uses a difference in luminance variation depending on the surface state and determines a threshold value for determining whether the surface state is specular reflection or diffuse reflection based on the surrounding luminance variation. . In other words, in the reflection characteristic evaluation apparatus, when the surface portion is a puddle and the variance of the luminance fluctuation is small like a prairie in the surrounding portion, the luminance fluctuation due to the reflection of the puddle on the surface portion is also small. Even in such a case, it is determined with high accuracy whether the surface portion is specular reflection or diffuse reflection by reducing the threshold value determined from the luminance fluctuation of the surrounding portion.

  For this reason, the reflection characteristic evaluation apparatus according to the first embodiment receives the image captured by the camera and outputs the reflection characteristic of the surface portion in the input image. As a result, it is possible to determine the reflection characteristic of the surface stably and accurately without cost.

  In other words, when an image captured by a camera is input and the reflection characteristic of the surface portion in the input image is output, the reflection characteristic evaluation apparatus determines whether the surface portion is specular reflection or diffusion due to dispersion of luminance fluctuations in the surrounding portion. Since a threshold value for determining whether it is reflection or not is determined, if the luminance fluctuation of the surface portion is equal to or greater than the determined threshold value, it is specular reflection, and if it is less than the determined threshold value, it is output as diffuse reflection. As described above, it is possible to determine the surface reflection characteristics stably and accurately compared to outputting whether the reflection is specular reflection or diffuse reflection based only on the luminance fluctuation of the road surface.

  In addition, the reflection characteristic evaluation apparatus evaluates and outputs the reflection characteristic of the surface portion from an image photographed by a general camera, so that a plurality of cameras are used or a complicated photographing process is performed as in the prior art. It is possible to determine the surface reflection characteristics stably and accurately without incurring costs, as compared with the need for.

[Configuration of Reflection Characteristic Evaluation Apparatus According to Example 1]
Next, the configuration of the reflection characteristic evaluation apparatus according to the first embodiment will be described with reference to FIG. FIG. 2 is a diagram illustrating the configuration of the reflection characteristic evaluation apparatus according to the first embodiment.

  As shown in FIG. 2, the reflection characteristic evaluation apparatus 10 includes a storage unit 20 and a control unit 30. An image captured by the connected camera 1 is input, and the reflection characteristic of the surface portion in the input image is displayed. Is output.

  The storage unit 20 stores data necessary for various processes by the control unit 30 and various processing results by the control unit 30, and has an image storage unit 21 particularly closely related to the present invention.

  The image storage unit 21 stores an input image taken by the camera 1. For example, the image storage unit 21 stores an input image captured by the camera 1 and received by an image receiving unit 31 described later.

  The control unit 30 includes an internal memory for storing a control program, a program that defines various processing procedures, and necessary data, and is particularly closely related to the present invention. An extraction unit 32, an upper image luminance variance calculation unit 33, a tracking unit 34, a luminance acquisition unit 35, a reflection characteristic evaluation unit 36, and an accuracy determination unit 37 are included, and various processes are executed using these units.

  The image receiving unit 31 receives an image taken by the camera 1. Specifically, the image receiving unit 31 receives an image captured by the camera 1 and stores the received input image in the image storage unit 21.

  The horizontal plane extraction unit 32 extracts the horizontal plane (horizontal line position) of the input image. To give a specific example in the above example, the horizontal plane extraction unit 32 in the input image stored in the image storage unit 21 has a surface portion (for example, a road surface portion) and a surrounding portion (for example, above the road surface). To extract the horizontal plane that becomes the boundary with the This horizontal plane extraction is performed using a technique such as Reference 1, for example.

  Reference 1: (Yinghua He, Hong Wang, and Bo Zhang, “Color-Based Road Detection in Urban Traffic Scenes”, IEEE Transactions on Intelligent Transportation Systems, Vol. 5, No. 4, December 2004)

  The image upper luminance variance calculating unit 33 acquires a spatial luminance variation in a peripheral portion that indicates a portion above the horizontal plane extracted by the horizontal plane extracting unit 32, and analyzes the image characteristics of the peripheral portion. To give a specific example in the above example, the image upper luminance dispersion calculating unit 33 is a spatial luminance variation (peripheral portion) of a surrounding portion (upper portion) indicating a portion above the horizontal plane extracted by the horizontal plane extracting unit 32 ( Dispersion) is obtained, and the image characteristics of the surrounding portion are analyzed.

  As shown in FIG. 3, this spatial luminance fluctuation is obtained by camera calibration (reference document 2) in advance, 1/10 above the vertical “H” of the image from the line “Z = 0” on the horizontal plane, A rectangular area of half of the horizontal “W” × H / 5 is set as the upper part of the road surface. Further, the spatial luminance fluctuation is 1/10 above the vertical “H” of the image and half the horizontal “W” of the image × H / 5 with reference to the uppermost coordinate of the processing result by the horizontal plane extraction unit 32. It is good also as a rectangular area. In addition to the dispersion of the brightness fluctuation in this space, any index can be used as long as it can evaluate the dispersion of pixels in the space, such as the number of pixels having a certain value larger or smaller than the average value of the brightness fluctuation. May be. FIG. 3 is a diagram for explaining a space in dispersion acquisition of luminance fluctuations in the surrounding area.

  Reference 2: (Berthold K. P. Horn, “Robot Vision”, MIT Press (March 1986) [ISBN-10: 0-262-08159-8, ISBN-13: 978-0-262-08159-7] )

  The tracking unit 34 tracks the same position of the surface portion that indicates a portion below the horizontal plane extracted by the horizontal plane extraction unit 32. To give a specific example in the above-described example, the tracking unit 34 performs tracking that follows the same position of the surface portion indicating the portion below the horizontal plane extracted by the horizontal plane extraction unit 32, and Get the brightness fluctuation of the surface part.

  This tracking will be described in detail. As shown in FIG. 4, the tracking unit 34 uses the horizontal line “Z = 0” as a reference, and the range from H / 20 to H / 40 from the horizontal line as a sampling point generation line. , Generate 8 sampling points. And the tracking part 34 respond | corresponds to the change of the visual field accompanying movement of a vehicle etc. about the produced | generated eight sampling points, and makes the end line the image lower part H / 10 for the movement in the image of all the sampling points. Tracking (reference 3).

  Reference 3: (Tomoaki Teshima, Hideo Saito, Shinji Ozawa, Keiichi Yamamoto, Toru Ihara: “Vehicle Horizontal Position Estimation Based on Overhead Image Matching”, MIRU2006 Image Recognition and Understanding Symposium (Sendai), IS3-58, (Jul. 2006))

  Thereafter, the tracking unit 34 excludes sampling points exceeding the end line from the subsequent tracking targets, and newly generates sampling points corresponding to the position of the image. In addition, the sampling points generated by the tracking unit 34 are not limited to the above-described eight points, and may be any number, and the sampling area that is a sampling range is limited to the above-described range and shape. However, it may be made wider or narrower than the above range. FIG. 4 is a diagram for explaining the generation of sampling points by the tracking unit 34 and the sampling end line.

  The luminance acquisition unit 35 acquires the luminance fluctuation at the same position on the surface portion tracked by the tracking unit 34. To give a specific example in the above example, the luminance acquisition unit 35 acquires time-series variation data of the luminance level for each tracking point tracked by the tracking unit 34. In this luminance variation, the amount of data accumulated varies depending on the tracked period.

  For example, as illustrated in FIG. 5A, the luminance acquisition unit 35 acquires a luminance variation as illustrated in FIG. 5B when there is a puddle on the surface (road surface) surrounded by a mountain. . The time variation of the luminance fluctuation may be time on the horizontal axis, but when the vehicle or the like stops, there is no change in the image, and the y coordinate of the screen is used so that the time without change is not used for processing. The value may be used as a reference. FIG. 5B is a diagram illustrating the luminance fluctuation acquired by the luminance acquisition unit 35 when there is a water pool on the surface surrounded by mountains.

  In addition, as illustrated in FIG. 5C, the luminance acquisition unit 35 acquires a luminance variation as illustrated in FIG. 5-4 when there is a puddle on the surface (road surface) whose surrounding is a prairie. In addition, as illustrated in FIG. 5-5, the luminance acquisition unit 35 acquires luminance fluctuations as illustrated in FIG. 5-6 when the surface (road surface) is dry. FIG. 5-4 is a diagram illustrating the luminance fluctuation acquired by the luminance acquisition unit 35 when there is a puddle on the surface where the surrounding area is a prairie, and FIG. 5-6 is a diagram illustrating that the surface is dry. It is a figure which shows the brightness | luminance fluctuation | variation acquired by the brightness | luminance acquisition part 35 in a case.

  The reflection characteristic evaluation unit 36 determines a threshold value based on the image characteristics of the surrounding portion according to the luminance variation of the surrounding portion acquired by the image upper luminance dispersion calculating unit 33, and the luminance variation of the surface portion acquired by the luminance acquiring unit 35. Depending on whether it is greater than or less than the determined threshold value, the reflection characteristic of the surface portion is evaluated and output.

  As a specific example in the above example, the reflection characteristic evaluation unit 36 makes the proportionality to the square root of the variance of the luminance fluctuation based on the image characteristics of the surrounding portion acquired by the image upper luminance variance calculation unit 33. Thus, the threshold is increased when the variance of the luminance fluctuation in the surrounding portion is large, and the threshold is determined to be small when the variance of the luminance fluctuation in the surrounding portion is small.

  And the reflection characteristic evaluation part 36 is specular reflection (wet state) when the maximum amplitude of the brightness | luminance fluctuation | variation of the surface part acquired by the brightness | luminance acquisition part 35 is more than a threshold value compared with the determined threshold value. It determines and outputs, and when it is less than a threshold value, it determines with it being diffuse reflection (dry state), and outputs.

  The accuracy determination unit 37 determines and outputs a high estimation accuracy when the luminance variation is large according to the surrounding spatial luminance variation acquired by the image upper luminance variance calculation unit 33, and the luminance variation is small. In this case, the estimated accuracy is determined to be small and output.

  To give a specific example in the above example, the accuracy determination unit 37 has a larger variance of the surrounding spatial luminance fluctuation acquired by the image upper luminance variance calculation unit 33 compared to a preset threshold value. In this case, the estimation accuracy indicating the certainty degree is determined to be high and output, and the estimation accuracy indicating the certainty degree is determined to be low and output if the estimation accuracy is smaller than a preset threshold value.

  In other words, the accuracy determination by the accuracy determination unit 37 is performed when the surface (road surface) is in a wet state and the luminance variation is large in the surroundings reflected on the surface (for example, the mountainous portion described above). Since it increases, the accuracy of specular reflection increases (see FIG. 6). Similarly, the accuracy determination by the accuracy determination unit 37 is specular reflection because the luminance variation on the surface is small when the luminance variation is small around the image reflected on the surface (for example, the above-mentioned prairie). Accuracy decreases (see FIG. 6). FIG. 6 is a diagram illustrating an example of the relationship between the luminance change in the upper part of the image, the threshold value, and the accuracy.

  The reflection characteristic evaluation result output by the reflection characteristic evaluation unit 36 and the accuracy determination unit 37 and the accuracy of the reflection characteristic evaluation result are output to a vehicle control unit or a monitor connected to the reflection characteristic evaluation device 10. Or As described above, the accuracy determination unit 37 is for further improving the reliability of the reflection characteristic evaluation result. Therefore, the accuracy determination unit 37 is not necessarily processed in this embodiment, and the output of the reflection characteristic evaluation result is not necessary. It may be only.

[Processing by Reflection Characteristic Evaluation Apparatus According to Example 1]
Next, the reflection characteristic evaluation process performed by the reflection characteristic evaluation apparatus 10 according to the first embodiment will be described with reference to FIG. FIG. 7 is a flowchart for explaining the reflection characteristic evaluation process performed by the reflection characteristic evaluation apparatus 10 according to the first embodiment. In the following, the detailed processing content described above will be omitted, and the flow of processing by the reflection characteristic evaluation apparatus 10 will be described.

  As shown in FIG. 7, when the reflection characteristic evaluation apparatus 10 extracts a horizontal plane serving as a boundary between the surface portion and the surrounding portion in the input image taken by the camera 1 (Yes in step S101), the luminance variation of the surrounding portion is detected. The variance is calculated, and it is determined whether there are 8 sampling points in the sampling range from H / 20 below to H / 40 from the extracted horizontal plane (step S102).

  Then, when all eight sampling points do not exist in the sampling range (No in step S102), the reflection characteristic evaluation apparatus 10 newly generates eight sampling points in the sampling range (step S103). Subsequently, the reflection characteristic evaluation apparatus 10 performs tracking that follows the generated sampling points (step S104), and acquires the luminance fluctuation of the surface portion (step S105).

  After that, the reflection characteristic evaluation apparatus 10 performs reflection characteristic evaluation based on the acquired luminance of the surface portion and the image characteristics of the surrounding portion (step S106), and the sampling points beyond the sampling end line are thereafter determined. Are excluded from the tracking / reflection characteristic evaluation process (step S107).

[Reflection Characteristic Evaluation Processing According to Example 1]
Next, details of the reflection characteristic evaluation processing according to the first embodiment will be described with reference to FIG. FIG. 8 is a flowchart for explaining the details of the reflection characteristic evaluation processing according to the first embodiment. The following process corresponds to the process in step S106 shown in FIG.

  As shown in FIG. 8, the reflection characteristic evaluation apparatus 10 calculates the variance value of the luminance fluctuation in the upper part of the acquired image (Step S201 and Step S202). Then, the reflection characteristic evaluation apparatus 10 determines a large threshold value when the luminance fluctuation at the upper part of the screen is large, and determines the threshold value when the luminance fluctuation at the upper part of the screen is small, based on the obtained variance value of the luminance fluctuation at the upper part of the screen. The threshold value is determined to be small (step S203).

  Subsequently, the reflection characteristic evaluation apparatus 10 determines that the maximum amplitude of the luminance fluctuation of the acquired surface portion is a specular reflection (wet state) when the maximum amplitude is greater than or equal to the determined threshold value, When it is less than the threshold value, it is determined that it is diffuse reflection (dry state) (step S204). After that, the reflection characteristic evaluation apparatus 10 determines that the estimation accuracy is high when the variance of the luminance fluctuation at the upper part of the acquired screen is larger than the preset threshold value, and compares the estimated accuracy with the preset threshold value. If it is smaller, the estimation accuracy is judged to be low and output (step S205).

[Effects of Example 1]
As described above, according to the first embodiment, the reflection characteristic evaluation apparatus 10 receives an image captured by the camera and outputs the reflection characteristic of the surface portion of the input image. Analyze the image characteristics of the surrounding area, and track the same position of the surface area that represents the lower part of the input image to obtain the luminance fluctuation of the surface area, and obtain the image characteristics of the analyzed surrounding area Since the reflection characteristic of the surface portion is evaluated based on the luminance fluctuation of the surface portion, it is possible to determine the reflection characteristic of the surface stably and accurately without cost.

  That is, when the image captured by the camera is input and the reflection characteristic of the surface portion in the input image is output, the reflection characteristic evaluation apparatus 10 not only detects the luminance variation of the surface portion but also the luminance variation of the surface portion. The surface reflection characteristics are evaluated and output based on the luminance fluctuations in the surrounding area that can affect the luminance fluctuations in the surface area, so the surface reflection characteristics are stable and accurate without cost. Can be determined.

  By the way, in the first embodiment, the case where the reflection characteristics of the surface portion are evaluated based on the luminance fluctuation of the surface portion to be evaluated for the reflection characteristics and the luminance fluctuation of the surrounding portion at a predetermined upper position in the input image. Although described, the present invention is not limited to this, based on the luminance variation of the surface portion to be evaluated for reflection characteristics, and the luminance variation in the reflector (upper position) corresponding to the surface portion, The reflection characteristics of the surface portion can also be evaluated.

  Therefore, in the following second embodiment, processing performed by the reflection characteristic evaluation apparatus 10 according to the second embodiment will be described with reference to FIGS. FIG. 9A to FIG. 9C are diagrams illustrating an overview and features of the reflection characteristic evaluation apparatus 10 according to the second embodiment. In addition, about each structure and one part function of the reflection characteristic evaluation apparatus 10 which concerns on Example 2, since it is the same as that of Example 1, the description is abbreviate | omitted, Especially the evaluation object of the surface part different from Example 1 A reflection characteristic evaluation process using a reflector for the above will be described.

[Outline and Features of Example 2]
The reflection characteristic evaluation apparatus 10 extracts the horizontal plane of the input image, tracks the same position of the surface portion indicating the portion below the extracted horizontal plane, and acquires the luminance fluctuation of the surface portion (FIG. 9-1). (See (1)).

  More specifically, when an image captured by the in-vehicle camera is input, the reflection characteristic evaluation apparatus 10 extracts a horizontal plane indicating a boundary between a road surface portion and a road surface upper portion of the input image. And the reflection characteristic evaluation apparatus 10 implements the tracking which tracks the same position of the surface part (road surface part) which shows the part below the extracted horizontal surface according to advancing of a vehicle, The said surface part Brightness fluctuation (see FIG. 9-2).

  Then, the reflection characteristic evaluation apparatus 10 estimates the position of the surrounding portion corresponding to the position of the surface portion to be tracked, which is a surrounding portion that indicates a portion above the extracted horizontal plane, and the estimated The luminance fluctuation of the position of the surrounding portion is acquired, and the image characteristic of the surrounding portion is analyzed (see (2) in FIG. 9-1).

  Specifically, in the above example, the reflection characteristic evaluation apparatus 10 estimates the position of the reflector in the surrounding portion that is in line symmetry with the position of the surface portion to be subjected to tracking processing with respect to the extracted horizontal plane. Then, the luminance fluctuation (see FIG. 9-3) at the estimated position of the object is acquired, and the image characteristics of the position of the object in the surrounding portion are analyzed.

  Subsequently, the reflection characteristic evaluation apparatus 10 evaluates and outputs the reflection characteristic of the surface portion based on the correlation between the acquired luminance fluctuation of the position of the surrounding portion and the acquired luminance fluctuation of the surface portion (see FIG. (Refer to 9-1 (3)).

  More specifically, in the above example, the reflection characteristic evaluation apparatus 10 calculates the luminance fluctuation at the position of the acquired reflecting object in the surrounding portion and the luminance fluctuation at the position of the surface portion to be acquired for tracking processing. Based on the correlation, it is compared with a predetermined threshold value. Then, based on the correlation between the two luminance fluctuations, the reflection characteristic evaluation device 10 determines that the surface portion is in a moist state when it is equal to or greater than the threshold value, and outputs the result. Moreover, the reflection characteristic evaluation apparatus 10 judges that it is diffuse reflection when it is less than the threshold value, and determines that the surface portion is in a dry state and outputs the result.

  For this reason, the reflection characteristic evaluation apparatus 10 according to the second embodiment becomes an evaluation target of the surface portion when an image captured by the camera is input and the reflection characteristic of the surface portion in the input image is output. Reflective characteristics can be evaluated on the basis of the luminance variation of the position, and the luminance variation of the position of the reflecting object that is line-symmetric in the horizontal plane, and the surface portion to be evaluated. It is possible to determine the reflection characteristics of the surface.

  That is, when the image captured by the camera is input and the reflection characteristic of the surface portion in the input image is output, the reflection characteristic evaluation apparatus 10 detects the luminance fluctuation at the position to be evaluated for the surface portion and the surface portion. Based on the correlation with the brightness fluctuation of the position that is directly reflected in the position to be evaluated, the specular reflection is output if it is greater than or equal to a predetermined threshold value, and diffuse reflection is output if it is less than the threshold value. It is possible to determine the reflection characteristics of the surface with higher accuracy.

[Processing by Reflection Characteristic Evaluation Apparatus According to Example 2]
Next, the reflection characteristic evaluation process performed by the reflection characteristic evaluation apparatus 10 according to the second embodiment will be described with reference to FIG. FIG. 10 is a flowchart for explaining the reflection characteristic evaluation process performed by the reflection characteristic evaluation apparatus 10 according to the second embodiment.

  As illustrated in FIG. 10, when the reflection characteristic evaluation apparatus 10 extracts a horizontal plane serving as a boundary between the surface portion and the surrounding portion in the input image captured by the camera 1 (Yes in step S301), the reflection characteristic evaluation apparatus 10 generates H from the extracted horizontal plane. It is determined whether or not there are 8 sampling points in the sampling range from below / 20 to H / 40 (step S302).

  Then, when all eight sampling points do not exist in the sampling range (No in step S302), the reflection characteristic evaluation apparatus 10 newly generates eight sampling points in the sampling range (step S303). Subsequently, the reflection characteristic evaluation apparatus 10 performs tracking to follow the generated sampling points (step S304), and acquires the luminance fluctuation of the surface portion (step S305).

  After that, the reflection characteristic evaluation apparatus 10 estimates the position of the target object in the surrounding part located in line symmetry with the position of the surface part to be tracked with respect to the extracted horizontal plane. The luminance fluctuation at the position is acquired (step S306).

  Then, the reflection characteristic evaluation apparatus 10 calculates the reflection characteristic based on the correlation between the acquired luminance fluctuation at the position of the object in the surrounding portion and the acquired luminance fluctuation at the position of the surface portion to be subjected to the tracking process. Evaluation is performed (step S307), and sampling points exceeding the sampling end line are excluded from the subsequent tracking / reflection characteristic evaluation processing (step S308).

[Reflection Characteristic Evaluation Processing According to Example 2]
Next, details of the reflection characteristic evaluation processing according to the second embodiment will be described with reference to FIG. FIG. 11 is a flowchart for explaining the details of the reflection characteristic evaluation processing according to the second embodiment. The following process corresponds to the process in step S307 shown in FIG.

  As shown in FIG. 11, the reflection characteristic evaluation apparatus 10 calculates the correlation between the luminance fluctuation at the sampling point in the tracking process and the luminance fluctuation of the reflector located in line symmetry with respect to the sampling point in the horizontal plane (step). S401). Then, the reflection characteristic evaluation apparatus 10 compares the calculated correlation with a predetermined threshold value, and determines that the surface portion is in a wet state when it is equal to or greater than the threshold value, and is less than the threshold value. If it is, it is determined that the reflection is diffuse reflection, and it is determined that the surface portion is in a dry state (step S402).

  Subsequently, the reflection characteristic evaluation apparatus 10 calculates a luminance variance value in the obtained luminance fluctuation of the reflecting object (step S403), and if the variance value is larger than a preset threshold value, the estimation accuracy is obtained. If it is determined to be high and is smaller than a preset threshold value, the estimation accuracy is determined to be low and output (step S404). The accuracy is for improving the reliability of the reflection characteristic evaluation result as in the case of the first embodiment. Therefore, the accuracy is not necessarily processed in this embodiment, and only the output of the reflection characteristic evaluation result is obtained. But you can.

[Effects of Example 2]
As described above, according to the second embodiment, the reflection characteristic evaluation apparatus 10 estimates the position of the reflecting object reflected at the point to be evaluated for the reflection characteristic, the luminance fluctuation at the position of the reflecting object, and the reflection characteristic. Based on the luminance fluctuation at the position to be evaluated, the reflection characteristic at the position to be evaluated is output and evaluated, so that it is possible to stably and accurately determine the surface reflection characteristics. .

Although the embodiments of the present invention have been described so far, the present invention may be implemented in various different forms other than the embodiments described above. Therefore, (1) Reflector position, (2) Luminance fluctuation correlation-1, (3) Luminance fluctuation correlation-2, (4) Luminance fluctuation correlation-3, (5) Configuration of reflection characteristic evaluation device, (6) A different embodiment in the program will be described.

(1) Reflector Position In the second embodiment, a case has been described in which the position of a surrounding reflector located in line symmetry with the position of the surface portion to be tracked is estimated with respect to the extracted horizontal plane. However, the present invention is not limited to this, and the position of the surrounding portion corresponding to the position of the surface portion to be tracked can also be estimated from the three-dimensional shape. For example, the reflection characteristic evaluation apparatus 10 estimates the position of the reflection object with respect to the position of the tracking target of the surface portion based on the three-dimensional shape in Reference Document 4.

  Reference 4: (A. Akbarzadeh, J.-M. Frahm, P. Mordohai, B. Clipp, C. Engels, D. Gallup, P. Merrell, M. Phelps, S. Sinha, B. Talton, L. Wang, Q. Yang, H. Stewenius, R. Yang, G. Welch, H. Towles, D. Nister and M. Pollefeys, “Towards Urban 3D Reconstruction From Video”)

(2) Correlation between luminance fluctuations-1
In the second embodiment, the reflection characteristics at the position of the surface portion are evaluated based on the correlation between the luminance fluctuation at the position of the surrounding reflector and the luminance fluctuation at the position of the surface portion to be tracked. However, the present invention is not limited to this, and the reflection characteristics of the position of the surface portion can be evaluated based on the cross-correlation between the luminance variation of the surrounding position and the luminance variation of the surface portion. it can. For example, the reflection characteristic evaluation apparatus 10 obtains the correlation between the luminance fluctuation at one point on the surface shown in FIG. 9-2 and the luminance fluctuation at one peripheral point shown in FIG. In this case, the specular reflection component becomes large, so that it is determined to be in a wet state.

(3) Correlation between luminance fluctuations-2
In the second embodiment, the reflection characteristic of the position of the surface portion is evaluated based on the correlation between the luminance variation at the position of the reflecting object in the surrounding portion and the luminance variation at the position of the surface portion to be tracked. Although the present invention has been described, the present invention is not limited to this, and after removing the noise of the luminance fluctuation of the surrounding position and the luminance fluctuation of the surface portion, the luminance fluctuation of the surrounding position excluding the noise. It is also possible to evaluate the reflection characteristics of the position of the surface portion based on the correlation between and the luminance fluctuation of the surface portion. For example, the reflection characteristic evaluation apparatus 10 performs low-frequency transmission filter processing on the luminance fluctuation at one point on the surface shown in FIG. 9-2 and the luminance fluctuation at one point around shown in FIG. 9-3 in advance. Based on the correlation between the two luminance fluctuations, the reflection characteristic of the position of the surface portion is evaluated.

(4) Correlation between luminance fluctuations-3
In the second embodiment, the reflection characteristics at the position of the surface portion are evaluated based on the correlation between the luminance fluctuation at the position of the surrounding reflector and the luminance fluctuation at the position of the surface portion to be tracked. However, the present invention is not limited to this, and it is also possible to evaluate the reflection characteristics of the position of the surface portion based on the magnitude of the amplitude of the surrounding luminance variation and the luminance variation of the surface portion. it can. For example, the reflection characteristic evaluation apparatus 10 compares the amplitude of the luminance fluctuation at one point on the surface shown in FIG. 9-2 with the luminance fluctuation at one peripheral point shown in FIG. Evaluate reflection characteristics.

(5) Configuration of Reflection Characteristic Evaluation Device Also, the processing procedure, control procedure, specific name, information including various data and parameters shown in the document and drawings (for example, “horizontal plane as shown in FIG. 2” The processing procedure such as the extraction unit 32 "that is not limited to a single process can be arbitrarily changed unless otherwise specified.

  Further, each component of each illustrated apparatus is functionally conceptual, and does not necessarily need to be physically configured as illustrated. That is, the specific form of distribution / integration of each device is not limited to the one shown in the figure. For example, the tracking unit 34 and the luminance acquisition unit 35 are integrated as a luminance variation acquisition unit that acquires a luminance variation by performing tracking processing. For example, all or a part thereof can be configured to be functionally or physically distributed / integrated in an arbitrary unit according to various burdens or usage conditions. Furthermore, all or a part of each processing function performed in each device may be realized by a CPU and a program that is analyzed and executed by the CPU, or may be realized as hardware by wired logic.

(6) Program In the above embodiment, the case where various processes are realized by hardware logic has been described. However, the present invention is not limited to this, and a program prepared in advance is executed by a computer. It may be realized by this. Therefore, an example of a computer that executes a reflection characteristic evaluation program having the same function as that of the reflection characteristic evaluation apparatus 10 shown in the above embodiment will be described below with reference to FIG. FIG. 12 is a diagram illustrating a computer that executes a reflection characteristic evaluation program.

  As shown in FIG. 12, a computer 110 as a reflection characteristic evaluation apparatus is configured by connecting an HDD 130, a CPU 140, a ROM 150, and a RAM 160 through a bus 180 or the like.

  The ROM 150 has a reflection characteristic evaluation program that exhibits the same function as the reflection characteristic evaluation apparatus 10 shown in the first embodiment, that is, a horizontal plane extraction program 150a and an image upper luminance dispersion calculation program 150b as shown in FIG. In addition, a tracking program 150c, a luminance acquisition program 150d, and a reflection characteristic evaluation program 150e are stored in advance. Note that these programs 150a to 150e may be appropriately integrated or distributed in the same manner as each component of the reflection characteristic evaluation apparatus 10 shown in FIG.

  Then, the CPU 140 reads and executes these programs 150a to 150e from the ROM 150, and as shown in FIG. 12, the programs 150a to 150e include a horizontal plane extraction process 140a, an image upper luminance variance calculation process 140b, It functions as a tracking process 140c, a luminance acquisition process 140d, and a reflection characteristic evaluation process 140e. The processes 140a to 140e correspond to the horizontal plane extraction unit 32, the image upper luminance variance calculation unit 33, the tracking unit 34, the luminance acquisition unit 35, and the reflection characteristic evaluation unit 36 illustrated in FIG. .

  Then, the CPU 140 executes a reflection characteristic evaluation program based on the image data 160 a recorded in the RAM 160.

  The above-described programs 150a to 150e are not necessarily stored in the ROM 150 from the beginning. For example, a flexible disk (FD), a CD-ROM, a DVD disk, and a magneto-optical disk inserted into the computer 110. Connected to the computer 110 via a "portable physical medium" such as an IC card, or a "fixed physical medium" such as an HDD provided inside or outside the computer 110, and further via a public line, the Internet, a LAN, a WAN, etc. Each program may be stored in “another computer (or server)” or the like, and the computer 110 may read and execute each program from now on.

  The following appendices are further disclosed with respect to the embodiments including the first to third embodiments.

(Appendix 1) A reflection characteristic evaluation apparatus that receives an image captured by a camera and outputs a reflection characteristic of a surface portion of the input image,
First analysis means for analyzing image characteristics of a peripheral portion indicating an upper portion in the input image;
Tracking means for tracking the same position of the surface portion indicating the lower portion in the input image, and obtaining luminance fluctuation of the surface portion;
A second analysis that evaluates and outputs the reflection characteristics of the surface portion based on the image characteristics of the surrounding portion obtained by the first analysis means and the luminance fluctuation of the surface portion obtained by the tracking means. Means,
A reflection characteristic evaluation apparatus comprising:

(Additional remark 2) It further has the horizontal surface extraction means which extracts the horizontal surface of the said input image,
The first analyzing means analyzes an image characteristic of the peripheral portion with the portion above the horizontal plane extracted by the horizontal plane extracting means as the peripheral portion,
2. The reflection characteristic evaluation apparatus according to appendix 1, wherein the tracking unit obtains a luminance variation of the surface portion using a portion below the horizontal plane extracted by the horizontal plane extraction unit as the surface portion.

(Supplementary Note 3) The first analyzing means acquires a spatial luminance variation of the surrounding portion and analyzes image characteristics of the surrounding portion,
According to the spatial luminance fluctuation of the surrounding portion acquired by the first analysis means, when the luminance fluctuation is large, the estimation accuracy is determined to be high and output, and when the luminance fluctuation is small, the estimation accuracy is reduced. The reflection characteristic evaluation apparatus according to appendix 1, further comprising accuracy determination means for determining and outputting.

(Appendix 4) The first analyzing means acquires a spatial luminance variation of the surrounding portion, analyzes image characteristics of the surrounding portion,
The second analyzing means determines a threshold value based on the image characteristics of the surrounding portion according to the luminance fluctuation of the surrounding portion acquired by the first analyzing means, and the luminance fluctuation of the surface portion acquired by the tracking means is The reflection characteristic evaluation apparatus according to appendix 1, wherein the reflection characteristic of the surface portion is evaluated and output depending on whether the threshold value is greater than or less than the determined threshold value.

(Additional remark 5) Said 1st analysis means estimates the position of the said surrounding part corresponding to the position of the surface part used as tracking object in the said tracking means, and acquires the brightness | luminance fluctuation | variation of the position of the said estimated surrounding part. And analyze the image characteristics of the position of the surrounding part,
The second analyzing unit is configured to detect the surface portion based on the correlation between the luminance variation of the position of the surrounding portion acquired by the first analyzing unit and the luminance variation of the surface portion acquired by the tracking unit. The reflection characteristic evaluation apparatus according to appendix 1, wherein the reflection characteristic is evaluated and output.

(Supplementary Note 6) The first analyzing unit estimates the position of the surrounding portion corresponding to the position of the surface portion to be tracked by the tracking unit by a three-dimensional shape, and the luminance of the estimated position of the surrounding portion. 6. The reflection characteristic evaluation apparatus according to appendix 5, wherein the fluctuation is acquired and the image characteristic of the position of the surrounding portion is analyzed.

(Supplementary note 7) The second analyzing means is based on the cross-correlation between the luminance fluctuation of the position of the surrounding portion acquired by the first analyzing means and the luminance fluctuation of the surface portion acquired by the tracking means. The reflection characteristic evaluation apparatus according to appendix 5 or appendix 6, wherein the reflection characteristic of the surface portion is evaluated and output.

(Supplementary Note 8) The second analyzing unit removes noise between the luminance variation of the position of the surrounding portion acquired by the first analyzing unit and the luminance variation of the surface portion acquired by the tracking unit. The appendix 5 or the appendix 6 is characterized in that the reflection characteristic of the surface portion is evaluated and output based on the correlation between the luminance variation of the position of the surrounding portion excluding the noise and the luminance variation of the surface portion. Reflection characteristic evaluation device.

(Supplementary Note 9) The second analysis unit is configured to increase the amplitude of the luminance variation of the position of the surrounding portion acquired by the first analysis unit and the luminance variation of the surface portion acquired by the tracking unit. The reflection characteristic evaluation apparatus according to appendix 5 or appendix 6, wherein the reflection characteristic of the surface portion is evaluated based on the output.

(Supplementary Note 10) A reflection characteristic evaluation method suitable for a reflection characteristic evaluation apparatus that receives an image captured by a camera and outputs a reflection characteristic of a surface portion in the input image,
A first analysis step of analyzing an image characteristic of a surrounding portion indicating an upper portion in the input image;
Tracking the same position of the surface portion showing the lower portion in the input image, and obtaining a luminance variation of the surface portion,
Second analysis for evaluating and outputting the reflection characteristics of the surface portion based on the image characteristics of the surrounding portion obtained by the first analysis step and the luminance fluctuation of the surface portion obtained by the tracking step. Process,
A method for evaluating reflection characteristics, comprising:

(Supplementary Note 11) A reflection characteristic evaluation program for causing a computer to input an image captured by a camera and to output a reflection characteristic of a surface portion in the input image,
A first analysis procedure for analyzing an image characteristic of a surrounding portion indicating an upper portion in the input image;
A tracking procedure for tracking the same position of the surface portion indicating the lower portion in the input image and obtaining luminance fluctuations of the surface portion;
A second analysis that evaluates and outputs the reflection characteristics of the surface portion based on the image characteristics of the surrounding portion obtained by the first analysis procedure and the luminance fluctuation of the surface portion obtained by the tracking procedure. Procedure and
A reflection characteristic evaluation program for causing a computer to execute.

It is a figure which shows the outline | summary and characteristic of the reflection characteristic evaluation apparatus which concern on Example 1. FIG. It is a figure which shows the outline | summary and characteristic of the reflection characteristic evaluation apparatus which concern on Example 1. FIG. 1 is a diagram illustrating a configuration of a reflection characteristic evaluation apparatus according to Example 1. FIG. It is a figure for demonstrating the space in dispersion | distribution acquisition of the brightness | luminance fluctuation | variation of a surrounding part. It is a figure for demonstrating the production | generation of the sampling point by a tracking part, and a sampling end line. It is a figure which shows the brightness | luminance fluctuation | variation acquired by a brightness | luminance acquisition part, when there exists a water pool in the surface surrounded by the mountain | mounting. It is a figure which shows the brightness | luminance fluctuation | variation acquired by a brightness | luminance acquisition part, when there exists a water pool in the surface surrounded by the mountain | mounting. It is a figure which shows the brightness | luminance fluctuation | variation acquired by the brightness | luminance acquisition part when there exists a water pool in the surface where the circumference | surroundings are a prairie. It is a figure which shows the brightness | luminance fluctuation | variation acquired by the brightness | luminance acquisition part when there exists a water pool in the surface where the circumference | surroundings are a prairie. It is a figure which shows the brightness | luminance fluctuation | variation acquired by the brightness | luminance acquisition part when the surface is dry. It is a figure which shows the brightness | luminance fluctuation | variation acquired by the brightness | luminance acquisition part when the surface is dry. It is a figure which shows an example of the relationship between the luminance change of an upper part of an image, a threshold value, and a precision. 6 is a flowchart for explaining a reflection characteristic evaluation process performed by the reflection characteristic evaluation apparatus according to the first embodiment. 6 is a flowchart for explaining details of a reflection characteristic evaluation process according to Embodiment 1; It is a figure which shows the outline | summary and the characteristic of the reflection characteristic evaluation apparatus which concerns on Example 2. FIG. It is a figure which shows the outline | summary and the characteristic of the reflection characteristic evaluation apparatus which concerns on Example 2. FIG. It is a figure which shows the outline | summary and the characteristic of the reflection characteristic evaluation apparatus which concerns on Example 2. FIG. 10 is a flowchart for explaining a reflection characteristic evaluation process by a reflection characteristic evaluation apparatus according to Example 2; 10 is a flowchart for explaining details of a reflection characteristic evaluation process according to the second embodiment. It is a figure which shows the computer which performs a reflection characteristic evaluation program. It is a figure for demonstrating the wet condition determination process which concerns on a prior art. It is a figure for demonstrating the wet condition determination process which concerns on a prior art. It is a figure for demonstrating the wet condition determination process which concerns on a prior art. It is a figure for demonstrating the wet condition determination process which concerns on a prior art.

Explanation of symbols

DESCRIPTION OF SYMBOLS 1 Camera 10 Reflection characteristic evaluation apparatus 20 Memory | storage part 21 Image memory | storage part 30 Control part 31 Image reception part 32 Horizontal surface extraction part 33 Image upper part brightness | luminance dispersion | distribution calculation part 34 Tracking part 35 Luminance acquisition part 36 Reflection characteristic evaluation part 37 Accuracy determination part

Claims (7)

A reflection characteristic evaluation apparatus that receives an image captured by a camera and outputs a reflection characteristic of a surface portion in the input image,
First analysis means for analyzing image characteristics of a peripheral portion indicating an upper portion in the input image;
Tracking means for tracking the same position of the surface portion indicating the lower portion in the input image, and obtaining luminance fluctuation of the surface portion;
A second analysis that evaluates and outputs the reflection characteristics of the surface portion based on the image characteristics of the surrounding portion obtained by the first analysis means and the luminance fluctuation of the surface portion obtained by the tracking means. Means,
A reflection characteristic evaluation apparatus comprising: A horizontal plane extracting means for extracting a horizontal plane of the input image;
The first analyzing means analyzes an image characteristic of the peripheral portion with the portion above the horizontal plane extracted by the horizontal plane extracting means as the peripheral portion,
2. The reflection characteristic evaluation apparatus according to claim 1, wherein the tracking unit obtains a luminance variation of the surface portion using a portion below the horizontal plane extracted by the horizontal plane extracting unit as the surface portion. The first analysis means acquires a spatial luminance variation of the surrounding portion, analyzes the image characteristics of the surrounding portion,
According to the spatial luminance fluctuation of the surrounding portion acquired by the first analysis means, when the luminance fluctuation is large, the estimation accuracy is determined to be high and output, and when the luminance fluctuation is small, the estimation accuracy is reduced. The reflection characteristic evaluation apparatus according to claim 1, further comprising accuracy determination means for determining and outputting. The first analysis means acquires a spatial luminance variation of the surrounding portion, analyzes the image characteristics of the surrounding portion,
The second analyzing means determines a threshold value based on the image characteristics of the surrounding portion according to the luminance fluctuation of the surrounding portion acquired by the first analyzing means, and the luminance fluctuation of the surface portion acquired by the tracking means is The reflection characteristic evaluation apparatus according to claim 1, wherein the reflection characteristic of the surface portion is evaluated and output depending on whether the threshold value is equal to or greater than the determined threshold value or less than the threshold value. The first analyzing means estimates the position of the surrounding portion corresponding to the position of the surface portion to be tracked in the tracking means, acquires the luminance fluctuation of the estimated position of the surrounding portion, and Analyzing the image characteristics of the position of the part,
The second analyzing unit is configured to detect the surface portion based on the correlation between the luminance variation of the position of the surrounding portion acquired by the first analyzing unit and the luminance variation of the surface portion acquired by the tracking unit. The reflection characteristic evaluation apparatus according to claim 1, wherein the reflection characteristic is evaluated and output. A reflection characteristic evaluation method suitable for a reflection characteristic evaluation apparatus that receives an image captured by a camera and outputs a reflection characteristic of a surface portion of the input image,
A first analysis step of analyzing an image characteristic of a surrounding portion indicating an upper portion in the input image;
Tracking the same position of the surface portion showing the lower portion in the input image, and obtaining a luminance variation of the surface portion,
Second analysis for evaluating and outputting the reflection characteristics of the surface portion based on the image characteristics of the surrounding portion obtained by the first analysis step and the luminance fluctuation of the surface portion obtained by the tracking step. Process,
A method for evaluating reflection characteristics, comprising: A reflection characteristic evaluation program that causes a computer to input an image captured by a camera and output a reflection characteristic of a surface portion in the input image,
A first analysis procedure for analyzing an image characteristic of a surrounding portion indicating an upper portion in the input image;
A tracking procedure for tracking the same position of the surface portion indicating the lower portion in the input image and obtaining luminance fluctuations of the surface portion;
A second analysis that evaluates and outputs the reflection characteristics of the surface portion based on the image characteristics of the surrounding portion obtained by the first analysis procedure and the luminance fluctuation of the surface portion obtained by the tracking procedure. Procedure and
A reflection characteristic evaluation program for causing a computer to execute.

Images