JP2016025615A - Information processing device, information processing method and program - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a technique for accurately selecting parameters for detecting a vehicle from a photographed image.SOLUTION: An information processing device 20 includes: a change amount detection part 215 for detecting an entire luminance change amount Vt in a photographed image by making the whole of a predetermined reference image to be a reference and a luminance change amount Vr of a setting region R in a photographed image by making a predetermined setting region R of the reference image to be a reference; and a parameter selection part 216 for selecting a luminance range for detecting a vehicle from the photographed image on the basis of the luminance change amount Vt and the luminance change amount Vr.SELECTED DRAWING: Figure 3

Description

  The present invention relates to an information processing apparatus, an information processing method, and a program.

  In recent years, techniques for detecting vehicles from captured images have been developed. Here, the degree of reflection of the vehicle in the captured image is not necessarily constant, and can be changed according to changes in the environment (such as weather), for example. Therefore, a technique for changing a parameter for detecting a vehicle from a captured image according to a change in environment is known. For example, a technique is disclosed in which information regarding environmental changes is acquired via a network, and a region for detecting a moving object is changed according to the information regarding environmental changes (see, for example, Patent Document 1).

JP 2009-27651 A

  However, the cause of the change in the appearance of the vehicle in the captured image may exist in addition to the change in the environment. As an example, the degree of reflection of the vehicle on the captured image can be changed by a change in a parameter (hereinafter also referred to as “imaging condition”) set in the imaging apparatus itself that captures the captured image. Therefore, it is difficult to select a parameter for detecting a vehicle with high accuracy only by considering changes in the environment.

  Accordingly, the present invention has been made in view of the above problems, and an object of the present invention is to provide a technique for selecting a parameter for detecting a vehicle from a captured image with higher accuracy. .

  In order to solve the above problem, according to an aspect of the present invention, the luminance change amount of a captured image based on a predetermined reference image and the setting in the captured image based on a predetermined setting area in the reference image A change amount detection unit that detects a luminance change amount of a region, and a predetermined parameter for detecting a vehicle from the captured image, the luminance change amount of the captured image, and the luminance change amount of the setting region in the captured image And an information processing apparatus including a parameter selection unit that performs selection based on the information.

  Alternatively, a change amount detection unit that detects a luminance change amount of a predetermined setting area in the captured image, and a predetermined parameter for detecting a vehicle from the captured image are set as the luminance change amount of the setting area in the captured image. There is provided an information processing apparatus including a parameter selection unit that selects based on a luminance range.

  The parameter selection unit is configured such that when the luminance change amount of the setting area in the captured image exceeds a first specified range, and when the luminance change amount of the captured image falls within a second specified range, One parameter may be selected.

  The parameter selection unit may select a second parameter different from the first parameter when the luminance change amount of the captured image exceeds the second specified range.

  The captured image is captured by an imaging device whose imaging conditions are automatically adjusted, and the parameter selection unit corresponds to the luminance change amount of the setting region and the luminance change amount of the captured image in the captured image. The parameter corresponding to the imaging condition may be selected.

  The imaging condition may include at least one of ISO sensitivity, aperture, and shutter speed.

  The luminance change amount of the setting region in the captured image is a change amount of the average luminance of the setting region in the captured image with reference to the average luminance of the setting region in the reference image, and the luminance of the captured image The change amount may be a change amount of the average luminance of the captured image with reference to the average luminance of the reference image.

  The parameter may include at least a luminance range for detecting the vehicle from the captured image.

  With reference to the threshold value of the luminance range included in the parameter for detecting the vehicle from the reference image, the threshold value of the luminance range included in the first parameter is the threshold value of the luminance range included in the second parameter. It may be a value that is changed more than the threshold value.

  With reference to the width of the luminance range included in the parameter for detecting the vehicle from the reference image, the width of the luminance range included in the first parameter is the width of the luminance range included in the second parameter. It may be a value changed more than the width.

  The information processing apparatus may include a region setting unit that sets a predetermined region including a region where the vehicle travels as the setting region.

  The area setting unit may set the setting area based on an optical flow extracted from a group of captured images captured in the past or a background difference method applied to the group of captured images.

  The information processing apparatus may include a reference value calculation unit that calculates the luminance of the reference image and the luminance of the setting area in the reference image.

  The reference value calculation unit may calculate the luminance of each pixel of the reference image by calculating an average luminance for each corresponding pixel in the captured image group captured in the past.

  Further, according to an aspect of the present invention, the luminance change amount of the captured image with reference to a predetermined reference image and the luminance change amount of the setting region in the captured image with reference to the predetermined setting region in the reference image are determined. Detecting, and selecting a predetermined parameter for detecting a vehicle from the captured image based on the luminance change amount of the captured image and the luminance change amount of the setting region in the captured image. An information processing method is provided.

  Further, according to an aspect of the present invention, a computer is used to change the luminance change amount of a captured image with reference to a predetermined reference image and the luminance of the setting region in the captured image with reference to a predetermined setting region in the reference image. A change amount detection unit that detects a change amount, and a predetermined parameter for detecting a vehicle from the captured image, based on the brightness change amount of the captured image and the brightness change amount of the setting area in the captured image. A program for functioning as an information processing apparatus is provided, including a parameter selection unit to select.

  As described above, according to the present invention, it is possible to select a parameter for detecting a vehicle from a captured image with higher accuracy.

It is a figure which shows the structural example of the vehicle detection system which concerns on embodiment of this invention. It is a figure showing an example of functional composition of an imaging device concerning the embodiment. It is a figure showing an example of functional composition of an information processor concerning the embodiment. It is a figure which shows the example of the captured image imaged with the imaging device which concerns on the embodiment. It is a flowchart which shows the flow of the setting operation | movement of a setting area | region. It is a figure which shows the example of the luminance change of the whole image when an imaging condition is changed. It is a figure which shows the example of the brightness | luminance change of the setting area | region when an imaging condition is changed. It is a figure which shows the example of the luminance change of the whole image when environmental light is changed. It is a figure which shows the example of the luminance change of a setting area | region when environmental light is changed. It is a figure which shows the example of the luminance range selected when an imaging condition is changed. It is a figure which shows the example of the luminance range selected at the time of change of ambient light. It is a flowchart which shows the flow of vehicle detection operation | movement.

  Exemplary embodiments of the present invention will be described below in detail with reference to the accompanying drawings. In the present specification and drawings, components having substantially the same functional configuration are denoted by the same reference numerals, and redundant description is omitted.

  In the present specification and drawings, a plurality of constituent elements having substantially the same functional configuration may be distinguished by attaching different alphabets or numbers after the same reference numeral. However, when it is not necessary to particularly distinguish each of a plurality of constituent elements having substantially the same functional configuration, only the same reference numerals are given.

[Description of configuration]
First, the configuration of the embodiment of the present invention will be described. FIG. 1 is a diagram illustrating a configuration example of a vehicle detection system 1 according to an embodiment of the present invention. As shown in FIG. 1, a vehicle detection system 1 according to an embodiment of the present invention includes an imaging device 10 and an information processing device 20. The imaging device 10 and the information processing device 20 are connected by wire or wireless.

  As illustrated in FIG. 1, the imaging device 10 is installed so as to be able to capture a road plane, and can provide the captured image to the information processing device 20. In the example shown in FIG. 1, the vehicle M is traveling on a road plane. The information processing apparatus 20 detects the vehicle M from the captured image provided from the imaging apparatus 10.

  Here, the degree of reflection of the vehicle on the captured image is not necessarily constant, and can be changed according to a change in the environment, for example. Therefore, a technique is known in which a parameter for detecting the vehicle M from the captured image is changed according to a change in the environment. For example, a technique is disclosed in which information related to environmental changes is acquired via a network, and an area for detecting a moving object is changed according to the information related to environmental changes.

  However, the cause of the change in the appearance of the vehicle M in the captured image may exist in addition to the change in the environment. As an example, the appearance of the vehicle M in the captured image can be changed by changing the imaging condition. Therefore, it is difficult to select a parameter for detecting the vehicle M with high accuracy only by considering changes in the environment.

  Therefore, in the present specification, a technique for selecting a parameter for detecting the vehicle M from the captured image with higher accuracy is mainly proposed. In the present specification, description will be made using environmental light detected by the imaging device 10 as an example of the environment, and conditions for determining the exposure of the imaging element as imaging conditions. Specifically, the imaging conditions may include at least one of ISO (International Organization for Standardization) sensitivity, aperture, and shutter speed. The configuration example of the vehicle detection system 1 has been described above.

  Subsequently, a functional configuration example of the imaging apparatus 10 will be described. FIG. 2 is a diagram illustrating a functional configuration example of the imaging device 10 according to the embodiment of the present invention. As illustrated in FIG. 2, the imaging apparatus 10 according to the embodiment of the present invention includes a control unit 110, an imaging unit 120, an operation unit 130, a storage unit 140, and an output unit 150.

  The control unit 110 has a function of controlling the entire operation of the imaging device 10. The imaging unit 120 has a function of acquiring a captured image by imaging a real space, and is configured by, for example, a monocular camera. The operation unit 130 has a function of receiving input of various operations from the user.

  The storage unit 140 can store a program and data for operating the control unit 110. In addition, the storage unit 140 can temporarily store various data necessary for the operation of the control unit 110. The output unit 150 has a function of performing output according to control by the control unit 110. The type of the output unit 150 is not particularly limited, and may be a display device, an audio output device, or a communication device that transmits information to the information processing device 20.

  In the example illustrated in FIG. 2, the imaging unit 120, the operation unit 130, the storage unit 140, and the output unit 150 exist inside the imaging apparatus 10, but the imaging unit 120, the operation unit 130, the storage unit 140, and the output All or part of the unit 150 may be provided outside the imaging apparatus 10. The function configuration example of the imaging device 10 according to the embodiment of the present invention has been described above.

  Subsequently, a functional configuration of the information processing apparatus 20 according to the embodiment of the present invention will be described. FIG. 3 is a diagram illustrating a functional configuration example of the information processing apparatus 20 according to the embodiment of the present invention. As illustrated in FIG. 3, the information processing apparatus 20 according to the embodiment of the present invention includes a control unit 210, a storage unit 280, and an output unit 290.

  The control unit 210 has a function of controlling the entire operation of the information processing apparatus 20. The storage unit 280 can store a program and data for operating the control unit 210. In addition, the storage unit 280 can temporarily store various data necessary in the course of the operation of the control unit 210. The output unit 290 has a function of outputting information (such as vehicle detection results) according to control by the control unit 210. The type of the output unit 290 is not particularly limited, and may be a display device, an audio output device, or a communication device that transmits information to the imaging device 10.

  In the example illustrated in FIG. 3, the storage unit 280 and the output unit 290 exist inside the information processing device 20, but all or part of the storage unit 280 and the output unit 290 are external to the information processing device 20. May be provided. In addition, the control unit 210 includes an image acquisition unit 211, a region setting unit 212, a reference value calculation unit 213, an output control unit 214, a change amount detection unit 215, a parameter selection unit 216, and a vehicle detection unit 217. Is provided. Details of these functional units included in the control unit 210 will be described later. The functional configuration example of the information processing apparatus 20 according to the embodiment of the present invention has been described above.

[Setting area settings]
Next, details of the embodiment of the present invention will be described. FIG. 4 is a diagram illustrating an example of a captured image Img-p captured by the imaging device 10 according to the embodiment of the present invention. As shown in FIG. 4, the captured image Img-p captured by the imaging device 10 shows the vehicle M traveling on the road plane. The captured image Img-p captured by the imaging device 10 is provided from the imaging device 10 to the information processing device 20.

  Next, details of functions of the information processing apparatus 20 will be described. First, the captured image Img-p captured by the imaging device 10 is acquired by the image acquisition unit 211. Then, the region setting unit 212 performs processing for setting the region in which the vehicle M travels in the captured image Img-p as the setting region R. Here, the setting method of the setting region R by the region setting unit 212 is not particularly limited. For example, the region setting unit 212 may set the setting region R based on an optical flow extracted from a captured image group captured in the past or a background difference method applied to the captured image group.

  For example, the region setting unit 212 may set the moving region detected based on the optical flow or the background difference method as the setting region R. In the present specification, an example in which the region setting unit 212 sets the traveling region of the vehicle M as the setting region R will be described. The setting region R may be a predetermined region including a region where the vehicle M travels. That's fine. Specifically, the moving area detected based on the optical flow or the background difference method may be larger than the traveling area of the vehicle M.

  When the setting region R is set by the region setting unit 212, the reference value calculation unit 213 calculates the luminance of the setting region R in a predetermined reference image captured by the imaging device 10, and calculates the overall luminance in the reference image. calculate.

  In this specification, the average luminance of the setting region R in the reference image is used as the luminance of the setting region R in the reference image, and the entire average luminance in the reference image is used as the total luminance of the reference image. . In addition, the reference value calculation unit 213 may use a single captured image captured in the past by the imaging device 10 as a reference image, or average for each corresponding pixel in the captured image group captured in the past by the imaging device 10. The luminance of each pixel of the reference image may be calculated by calculating the luminance.

  Next, the flow of setting operation for the setting region R will be described. FIG. 5 is a flowchart showing the flow of the setting operation for the setting region R. The flowchart shown in FIG. 5 only shows an example of the setting region R setting operation. Therefore, the setting operation of the setting region R is not limited to the operation example shown by the flowchart of FIG.

  First, the image acquisition unit 211 acquires a past captured image group captured by the imaging device 10, and the region setting unit 212 sets a setting region R based on the acquired past captured image group (step S11). ). Subsequently, the reference value calculation unit 213 calculates the average luminance of the setting region R in the reference image (Step S12). Further, the reference value calculation unit 213 calculates the overall average luminance in the reference image (step S13).

  The output control unit 214 may cause the output unit 290 to output various information calculated by the region setting unit 212 and the reference value calculation unit 213. Subsequently, when the setting operation of the setting region R is continued (“Yes” in step S14), the control unit 210 shifts the operation to step S11, but when the setting operation of the setting region R is not continued. (“No” in step S14), the operation is terminated. The flow of the setting region R setting operation has been described above.

[Vehicle detection]
As described above, the setting region R can be set in advance. After that, vehicle detection is performed from the captured image captured by the imaging device 10, but after the reference image is captured, the imaging condition may be changed automatically (or manually), or the ambient light May be changed. Here, the change of the imaging condition and the change of the ambient light can be a factor for changing the luminance of the captured image on the basis of the luminance of the reference image.

  Here, the luminance change due to the change of the imaging condition is different from the luminance change due to the change of the ambient light. In the following, first, a difference between a luminance change due to a change in imaging conditions and a luminance change due to a change in ambient light will be described.

  FIG. 6 is a diagram illustrating an example of a change in luminance of the entire image when the imaging condition is changed. Referring to FIG. 6, when the imaging condition is changed, an example of the overall luminance distribution in each of the reference image and the captured image is shown. The entire captured image in the captured image based on the average average luminance in the reference image is shown. The change amount of the average luminance is shown as the luminance change amount Vt.

  Here, the change amount detection unit 215 detects the luminance change amount Vt of the overall average brightness in the captured image with the overall average brightness in the reference image as a reference, and uses the average brightness of the setting region R in the reference image as a reference. A luminance change amount Vr of the average luminance of the setting region R in the captured image is detected.

  FIG. 7 is a diagram illustrating an example of a change in luminance of the setting region R when the imaging condition is changed. Referring to FIG. 7, when the imaging condition is changed, an example of the luminance distribution of the setting region R in each of the reference image and the captured image is shown, and imaging based on the average luminance of the setting region R in the reference image is shown. The average luminance of the setting region R in the image is shown as the luminance change amount Vr.

  Referring to FIG. 6, when the imaging condition is changed, the luminance change amount Vt of the overall average brightness in the captured image based on the overall average brightness in the reference image does not exceed the specified range A2. On the other hand, referring to FIG. 7, when the imaging condition is changed, the luminance change amount Vr of the average luminance of the setting region R in the captured image with the average luminance of the setting region R in the reference image as a reference is within the specified range A1. Over.

  When the imaging conditions are changed, the shape of the luminance distribution of the road portion that is the setting area is steeper than the entire luminance distribution for the following reason. That is, the change of the shooting condition such as the longer exposure time occurs when the entire shooting environment becomes dark due to sunset or the like. When the entire photographing environment becomes dark, halation occurs due to lighting of a vehicle traveling on the road or lighting of a street lamp, so that the road portion becomes white and the luminance distribution becomes steep at a large value. On the other hand, since the above-mentioned halation does not occur in portions other than the road, the image remains dark even if the exposure time is long, and the luminance distribution does not become steep where the value is large.

  FIG. 8 is a diagram illustrating an example of a change in luminance of the entire image when the ambient light is changed. Referring to FIG. 8, when the ambient light is changed, an example of the overall luminance distribution in each of the reference image and the captured image is shown. The entire captured image in the captured image based on the average average brightness in the reference image is shown. The change amount of the average luminance is shown as the luminance change amount Vt.

  FIG. 9 is a diagram illustrating an example of a change in luminance of the setting region R when the ambient light is changed. Referring to FIG. 9, an example of the luminance distribution of the setting region R in each of the reference image and the picked-up image when the ambient light is changed is shown. The image pickup is based on the average luminance of the setting region R in the reference image. The average luminance of the setting region R in the image is shown as the luminance change amount Vr.

  Referring to FIG. 8, when the ambient light is changed, the luminance change amount Vt of the overall average brightness in the captured image with the overall average brightness in the reference image as a reference exceeds the specified range A2. On the other hand, referring to FIG. 9, when the ambient light is changed, the luminance change amount Vr of the average luminance of the setting region R in the captured image based on the average luminance of the setting region R in the reference image exceeds the specified range A1. Not.

  Therefore, the parameter selection unit 216 sets the luminance range for the vehicle detection unit 217 to detect the vehicle from the captured image based on the overall luminance change amount Vt in the captured image and the luminance change amount Vr of the setting region R in the captured image. It is good to choose.

  Thereby, the parameter selection unit 216 responds to the luminance change amount Vr of the setting region R in the captured image and the overall luminance change amount Vt in the captured image when the imaging condition is automatically (or manually) changed. A luminance range corresponding to the imaging condition can be selected. Therefore, the luminance range for vehicle detection can be selected with higher accuracy.

  FIG. 10 is a diagram illustrating an example of the luminance range D1 selected when the imaging condition is changed. As shown in FIG. 10, the parameter selection unit 216, when the luminance change amount Vr of the setting region R in the captured image exceeds the specified range A1, and when the entire luminance change amount Vt in the captured image falls within the specified range A2. In addition, the luminance range D1 may be selected.

  FIG. 11 is a diagram illustrating an example of the luminance range D2 selected when the ambient light is changed. As illustrated in FIG. 11, the parameter selection unit 216 may select a luminance range D2 different from the luminance range D1 when the entire luminance change amount Vt in the captured image exceeds the specified range A2.

  10 and 11, a luminance range D0 for detecting the vehicle from the reference image is shown, and the luminance change when the imaging condition is changed is larger than the luminance change when the environmental light is changed. It has become. Therefore, as shown in FIGS. 10 and 11, when the average luminance of the captured image rises with reference to the average luminance of the reference image, the lower limit value of the luminance range D1 is based on the lower limit value of the luminance range D0. It is preferable that the value be changed to be larger than the lower limit value of the luminance range D2.

  10 and 11, the luminance distribution when the imaging condition is changed is biased to a narrower range than the luminance distribution when the ambient light is changed. Therefore, the width of the luminance range D1 may be a value that is changed to be larger than the width of the luminance range D2, with reference to the width of the luminance range D0. More specifically, as shown in FIGS. 10 and 11, when the average luminance of the captured image increases with the average luminance of the reference image as a reference, the width of the luminance range D <b> 1 is used as a reference. The width is preferably wider than the width of the luminance range D2.

  The vehicle detection unit 217 detects the vehicle from the captured image based on the luminance range set by the parameter selection unit 216. More specifically, the vehicle detection unit 217 detects a vehicle from an area where the luminance falls within the luminance range set by the parameter selection unit 216 in the captured image. The vehicle detection method is not particularly limited. For example, the vehicle detection unit 217 may detect the vehicle by extracting the vehicle silhouette region from the captured image based on the background difference method, or may detect the vehicle by another method.

  Subsequently, the flow of the vehicle detection operation will be described. FIG. 12 is a flowchart showing the flow of the vehicle detection operation. Note that the flowchart shown in FIG. 12 merely shows an example of the vehicle detection operation. Therefore, the vehicle detection operation is not limited to the operation example shown by the flowchart of FIG.

  First, the change amount detection unit 215 detects the change amount Vt of the overall average brightness in the captured image with the overall average brightness in the reference image as a reference (step S21). Subsequently, when the change amount Vt exceeds the specified range A2 (“Yes” in step S22), the parameter selection unit 216 selects the luminance range D2 for vehicle detection (step S23), and the process proceeds to step S27. Transition operation. On the other hand, when the change amount Vt does not exceed the specified range A2 (“No” in step S22), the parameter selection unit 216 shifts the operation to step S24.

  Subsequently, the change amount detection unit 215 detects the change amount Vr of the average luminance of the setting region R in the captured image with reference to the average luminance of the setting region R in the reference image (step S24). When the change amount Vt exceeds the specified range A1 (“Yes” in step S25), the parameter selection unit 216 selects the luminance range D1 for vehicle detection (step S26), and proceeds to step S27. Let On the other hand, when the change amount Vt does not exceed the specified range A1 (“No” in step S25), the parameter selection unit 216 shifts the operation to step S27.

  Subsequently, the vehicle detection unit 217 detects the vehicle from the captured image based on the luminance range set by the parameter selection unit 216. The output control unit 214 may cause the output unit 290 to output the vehicle detection result detected by the vehicle detection unit 217. Subsequently, when the vehicle detection operation is continued (“Yes” in step S28), the control unit 210 shifts the operation to step S21, but when the vehicle detection operation is not continued (“No” in step S28). )), The operation is terminated. The vehicle detection operation has been described above.

[Description of effects]
As described above, according to the embodiment of the present invention, the captured image based on the entire luminance change amount Vt in the captured image based on the entire predetermined reference image and the predetermined setting region R in the reference image. A change amount detection unit 215 that detects the luminance change amount Vr of the setting region R in the image area, and a parameter selection unit 216 that selects a luminance range for detecting the vehicle from the captured image based on the luminance change amount Vt and the luminance change amount Vr. An information processing apparatus 20 is provided. According to such a configuration, the luminance range for vehicle detection can be selected with higher accuracy.

[Description of modification]
The preferred embodiments of the present invention have been described in detail above with reference to the accompanying drawings, but the present invention is not limited to such examples. It is obvious that a person having ordinary knowledge in the technical field to which the present invention pertains can come up with various changes or modifications within the scope of the technical idea described in the claims. Of course, it is understood that these also belong to the technical scope of the present invention.

  For example, in the above, the parameter selection unit 216 selects the luminance range for detecting the vehicle from the captured image based on the entire luminance change amount Vt in the captured image and the luminance change amount Vr of the setting region R in the captured image. An example is shown. However, the parameter selected by the parameter selection unit 216 is not limited to the luminance range for detecting the vehicle. Therefore, the parameter selected by the parameter selection unit 216 may include a luminance range for detecting the vehicle or may not include a luminance range for detecting the vehicle.

  In the above description, the overall average brightness in the reference image and the overall average brightness in the captured image have been described. However, instead of the overall average brightness in the reference image, the average brightness of a predetermined area in the reference image is used. Instead of the overall average brightness in the captured image, the average brightness of a predetermined area in the captured image may be used. In such a case, the predetermined area may be an area including an area other than the setting area R.

  In the above embodiment, the luminance change amount of the captured image based on the predetermined reference image and the luminance change amount of the setting area in the captured image based on the predetermined setting area in the reference image are selected as parameters. Although used, it is possible to realize a configuration in which the parameter is selected using only the luminance change amount of the predetermined setting area. That is, as described above, when the imaging condition is changed, the luminance range of the luminance change amount of the road portion that is the setting area changes. Therefore, processing such as measuring the change tendency of the luminance range when the shooting condition is changed is performed in advance and registered in the parameter selection unit 216, so that the change of the shooting condition and the change of the ambient light are discriminated. Thus, it is possible to select an optimum parameter.

  Each block configuring the control unit 110 includes, for example, a CPU (Central Processing Unit), a RAM (Random Access Memory), and the like, and a program stored in the storage unit 180 is expanded on the RAM and executed by the CPU. Thus, the function can be realized. Or each block which comprises the control part 110 may be comprised by the hardware for exclusive use, and may be comprised by the combination of several hardware.

  Each block constituting the control unit 210 includes, for example, a CPU (Central Processing Unit), a RAM (Random Access Memory), and the like, and a program stored in the storage unit 280 is expanded into the RAM and executed by the CPU. Thus, the function can be realized. Or each block which comprises the control part 210 may be comprised by the hardware for exclusive use, and may be comprised by the combination of several hardware.

  In this specification, the steps described in the flowcharts are executed in parallel or individually even if they are not necessarily processed in time series, as well as processes performed in time series in the described order. Including processing to be performed. Further, it goes without saying that the order can be appropriately changed even in the steps processed in time series.

DESCRIPTION OF SYMBOLS 1 Vehicle detection system 10 Imaging device 20 Information processing apparatus 110 Control part 120 Imaging part 130 Operation part 140 Storage part 150 Output part 180 Storage part 210 Control part 211 Image acquisition part 212 Area setting part 213 Reference value calculation part 214 Output control part 215 Change detection unit 216 Parameter selection unit 217 Vehicle detection unit 280 Storage unit 290 Output unit M Vehicle R Setting region

10 and 11, the luminance distribution when the imaging condition is changed is biased to a narrower range than the luminance distribution when the ambient light is changed. Therefore, the width of the luminance range D1 may be a value that is changed to be larger than the width of the luminance range D2, with reference to the width of the luminance range D0. More specifically, as shown in FIGS. 10 and 11, when the average luminance of the captured image increases with the average luminance of the reference image as a reference, the width of the luminance range D <b> 1 is used as a reference. The width is preferably narrower than the width of the luminance range D2.

Claims (16)

A change amount detection unit for detecting a luminance change amount of a captured image based on a predetermined reference image and a luminance change amount of the setting region in the captured image based on a predetermined setting region in the reference image;
A parameter selection unit that selects a predetermined parameter for detecting a vehicle from the captured image based on the luminance change amount of the captured image and the luminance change amount of the setting region in the captured image;
An information processing apparatus comprising: A change amount detection unit that detects a luminance change amount of a predetermined setting area in the captured image;
A parameter selection unit that selects a predetermined parameter for detecting a vehicle from the captured image based on a luminance range of the luminance change amount of the setting region in the captured image;
An information processing apparatus comprising: The parameter selection unit is configured such that when the luminance change amount of the setting area in the captured image exceeds a first specified range, and when the luminance change amount of the captured image falls within a second specified range, Select 1 parameter,
The information processing apparatus according to claim 1. The parameter selection unit selects a second parameter different from the first parameter when the luminance change amount of the captured image exceeds the second specified range.
The information processing apparatus according to claim 3. The captured image is captured by an imaging device whose imaging conditions are automatically adjusted,
The parameter selection unit selects the parameter corresponding to the imaging condition according to the luminance change amount of the setting region and the luminance change amount of the captured image in the captured image.
The information processing apparatus according to claim 1. The imaging conditions include at least one of ISO sensitivity, aperture, and shutter speed.
The information processing apparatus according to claim 5. The luminance change amount of the setting area in the captured image is a change amount of the average luminance of the setting area in the captured image with reference to the average luminance of the setting area in the reference image,
The brightness change amount of the captured image is a change amount of the average brightness of the captured image based on the average brightness of the reference image.
The information processing apparatus according to claim 1. The parameter includes at least a luminance range for detecting the vehicle from the captured image.
The information processing apparatus according to claim 4. With reference to the threshold value of the luminance range included in the parameter for detecting the vehicle from the reference image, the threshold value of the luminance range included in the first parameter is the threshold value of the luminance range included in the second parameter. It is a value changed more than the threshold value,
The information processing apparatus according to claim 8. With reference to the width of the luminance range included in the parameter for detecting the vehicle from the reference image, the width of the luminance range included in the first parameter is the width of the luminance range included in the second parameter. The value is changed more than the width,
The information processing apparatus according to claim 8. The information processing apparatus includes an area setting unit that sets a predetermined area including an area where the vehicle travels as the setting area.
The information processing apparatus according to claim 1 or 2. The region setting unit sets the setting region based on an optical flow extracted from a captured image group captured in the past or a background difference method applied to the captured image group.
The information processing apparatus according to claim 11. The information processing apparatus includes a reference value calculation unit that calculates the luminance of the reference image and the luminance of the setting area in the reference image.
The information processing apparatus according to claim 1. The reference value calculation unit calculates the luminance of each pixel of the reference image by calculating an average luminance for each corresponding pixel in a captured image group captured in the past;
The information processing apparatus according to claim 13. Detecting a luminance change amount of a captured image based on a predetermined reference image and a luminance change amount of the setting region in the captured image based on a predetermined setting region in the reference image;
Selecting a predetermined parameter for detecting a vehicle from the captured image based on the luminance change amount of the captured image and the luminance change amount of the setting area in the captured image;
Including an information processing method. Computer
A change amount detection unit for detecting a luminance change amount of a captured image based on a predetermined reference image and a luminance change amount of the setting region in the captured image based on a predetermined setting region in the reference image;
A parameter selection unit that selects a predetermined parameter for detecting a vehicle from the captured image based on the luminance change amount of the captured image and the luminance change amount of the setting region in the captured image;
A program for causing an information processing apparatus to function.

Images