JP2016032255A - Image processor - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide an image processor capable of expanding a situation where one imaging device is shred by a plurality of applications.SOLUTION: An image processor 1 executing a plurality of applications 11-1N on the basis of an image captured by means of a stereoscopic camera 8 includes parameter range acquisition means 5, a parameter determination unit 6, and a camera control unit 7. The parameter range acquisition means 5 acquires the range of imaging parameters related to an image required for execution of each application 11-1N. The parameter determination unit 6 determines whether there is a common range, in respective ranges of imaging parameters acquired in the parameter range acquisition means 5. When a determination is made that there is a common range, the parameter determination unit 6 determines a share imaging time for sharing an image captured by means of the stereoscopic camera 8 among the plurality of applications 11-1N. The camera control unit 7 controls imaging of the stereoscopic camera 8 on the basis of the share imaging time.SELECTED DRAWING: Figure 1

Description

  The present invention relates to an image processing apparatus that shares one imaging device among a plurality of applications.

  Conventionally, as a technique in such a field, for example, there is one described in Patent Document 1. The image processing apparatus described in this document includes an imaging device that acquires an image, a control unit that controls the imaging device from a plurality of applications, and a plurality of applications that capture image data from a single imaging device without overlapping in time. An image capture scheduling unit that determines the timing of the image capture. According to the image processing apparatus having the above-described configuration, one imaging device can be shared with high reliability by a plurality of applications that dynamically change camera parameters.

JP 2008-278515 A

  However, in the above-described image processing apparatus, in order to share one imaging device, it is necessary to use a common function among a plurality of applications. For example, it is possible to share an image captured by the imaging device only between applications that commonly use the lane recognition function, such as a lane departure warning and a lane maintenance driving support. For this reason, the situation where one imaging device can be shared by a plurality of applications has been limited.

  The present invention has been made in view of the above points, and an object of the present invention is to provide an image processing apparatus capable of enlarging a situation in which one imaging device is shared by a plurality of applications.

  An image processing apparatus of the present invention that solves the above-described problems is an image processing apparatus in which a plurality of applications are executed based on an image captured by an imaging device, and sets a range of imaging parameters related to images necessary for execution of each application. Parameter range determination means for determining a shared imaging parameter for sharing an image captured by the imaging device with a plurality of applications based on a parameter range acquisition means to be acquired and a range of each imaging parameter acquired by the parameter range acquisition means And control means for controlling imaging of the imaging device based on the shared imaging parameter determined by the parameter determination means.

  According to the image processing apparatus of the present invention, since the shared imaging parameter for sharing the image captured by the imaging device is determined based on the range of each imaging parameter, for example, a common part or a similar part of each imaging parameter When there is, it becomes possible to share an image captured by the imaging device with a plurality of applications. Therefore, it is possible to expand the aspect in which an image can be shared, as compared to the aspect in which a common function can be shared only when a common function is used as in the past. As a result, the situation where one imaging device is shared by a plurality of applications can be expanded.

1 is a block diagram showing an overall configuration of an image processing apparatus according to a first embodiment. 3 is a flowchart showing a processing procedure of the image processing apparatus according to the first embodiment. The figure which shows the example of an imaging condition definition. The figure which shows the example of a required performance definition. The figure which shows the example of the imaging parameter definition of the application A. The figure which shows the example of the imaging parameter definition of the application B. FIG. The figure which shows the example of the imaging parameter definition of the application A and the application B. FIG. The figure which shows the example of the imaging time in the case of sharing an image by the application A and the application B. 9 is a flowchart showing a processing procedure of an image processing apparatus according to a second embodiment. (A) The figure which shows the example of the imaging time at the time of sharing an image with the application A and the application B, (b) The example of the imaging time in the case of imaging separately the image required for execution of the application A and the application B is shown Figure. (A) The figure which shows the example of the imaging time in the case of sharing an image with the application A and the application B which concern on 3rd Embodiment, (b) The image required for execution of the application A and the application B which concerns on 3rd Embodiment The figure which shows the example of the imaging time in the case of imaging individually, (c) The figure which shows the other example of the imaging time in the case of imaging separately the image required for execution of the application A and the application B which concern on 3rd Embodiment .

  Hereinafter, an embodiment of an image processing apparatus according to the present invention will be described with reference to the drawings. In the description of the drawings, the same elements are denoted by the same reference numerals, and redundant description is omitted.

<First Embodiment>
FIG. 1 is a block diagram showing the overall configuration of the image processing apparatus according to the first embodiment. The image processing device 1 is a device that is mounted on a vehicle and that realizes safe driving of the vehicle by processing images captured by the stereo camera 8 and executing N applications 11 to 1N. Note that imaging according to the present embodiment means capturing an image. As shown in FIG. 1, the image processing apparatus 1 includes a memory 2, a CAN (Controller Area Network) interface unit 3, a parameter range acquisition unit 5, a parameter determination unit 6, and a camera control unit 7.

  The memory 2 stores information related to the operation of the image processing apparatus 1. In the present embodiment, the memory 2 stores a host vehicle situation 21, an external world situation 22, and application information 23. The own vehicle situation 21 and the outside world situation 22 are various situations relating to the current running state of the vehicle, and include data obtained from the processing results of the applications 11 to 1N or other systems in the vehicle.

  Examples of the host vehicle situation 21 include the running speed, acceleration, steering wheel operation, gear operation, and pedal operation of the host vehicle. Examples of the outside world situation 22 include the positions of preceding and oncoming vehicles, the positions of pedestrians around the host vehicle, ambient brightness, weather, and road conditions. The application information 23 includes information necessary for execution of each application, and includes, for example, an imaging condition definition, a required performance definition, an imaging parameter definition, and the like.

  The CAN interface unit 3 is connected to the memory 2 and configured to be able to transfer data to each other. The CAN interface unit 3 can communicate with other systems in the vehicle via the CAN bus 4. For example, when a steering wheel operation is performed on the host vehicle, information regarding the steering wheel operation is input to the memory 2 via the CAN bus 4 and the CAN interface unit 3 and stored in the host vehicle situation 21.

The parameter range acquisition unit 5 is connected to the memory 2, refers to each piece of information stored in the memory 2, and acquires an imaging parameter range related to an image necessary for executing each application.
The imaging parameter is each set value related to imaging of the stereo camera 8, and examples thereof include imaging time, exposure time, resolution, white balance (color tone), image size, gain, and the like. The parameter determination unit 6 is connected to the memory 2 and the parameter range acquisition unit 5, respectively. The parameter determination unit 6 refers to the application information stored in the memory 2 and shares an image captured by the stereo camera 8 with a plurality of applications based on a range of imaging parameters obtained for each application. A shared imaging parameter is determined.

  Here, determining the shared imaging parameter means determining not only the specific name of the shared imaging parameter but also the value or range of the parameter. For example, when the shared imaging parameter is the exposure time, the parameter determination unit 6 determines the exposure time as the shared imaging parameter and also determines a specific value (for example, 30 ms). Therefore, the shared imaging parameter determined by the parameter range acquisition unit 5 includes not only the specific name of the parameter but also its value or range. Then, the parameter determination unit 6 transmits the determined shared imaging parameter to the camera control unit 7.

  The camera control unit 7 is connected to the parameter determination unit 6 and sends a control signal to the stereo camera 8 based on the shared imaging parameter transmitted from the parameter determination unit 6 to control the imaging of the stereo camera 8. Examples of control signals related to the stereo camera 8 include those related to control of exposure, gain, color information, and the like. The camera control unit 7 is connected to each of the applications 11 to 1N, and transmits an image captured by the stereo camera 8 to each application.

  The applications 11 to 1N acquire images captured by the stereo camera 8 via the camera control unit 7, and are executed according to the respective programs based on the images. Examples of applications include vehicle / pedestrian recognition, sign recognition, light distribution control, lane departure warning, interrupted vehicle warning, overtaking vehicle warning, lane maintenance travel support, and the like.

  The stereo camera 8 images the state in front of the vehicle. The stereo camera 8 includes a left camera 81 and a right camera 82 that are attached at a predetermined interval. Each of these cameras 81 and 82 is connected to the camera control unit 7, receives a control signal from the camera control unit 7, performs imaging in accordance with the control command, and transmits the captured data to the camera control unit 7. The cameras 81 and 82 are configured by an image sensor such as a CCD (Charge Coupled Device) or a CMOS (Complementary Metal Oxide Semiconductor), for example.

  Hereinafter, the processing procedure of the image processing apparatus 1 will be described with reference to FIG. FIG. 2 is a flowchart illustrating a processing procedure of the image processing apparatus according to the first embodiment. The image processing apparatus 1 according to the present embodiment normally performs imaging periodically based on a set imaging schedule (that is, the order of capturing images from the stereo camera 8), but the imaging schedule at a predetermined timing. It has been possible to reconfigure. For example, the imaging schedule is reset when the application is started, when the application is stopped, when the state of the vehicle or the outside world changes, or when a predetermined time has elapsed. The resetting of the imaging schedule may be, for example, changing the imaging order or changing the imaging time.

  First, in step S11, the parameter range acquisition unit 5 refers to the required performance definition in the host vehicle situation 21, the external world situation 22, and the application information 23, and obtains the required performance of the application being executed. For example, when applications for vehicle / pedestrian recognition, sign recognition, and light distribution control are executed, the parameter range acquisition unit 5 first stores the own vehicle situation 21, the outside world situation 22 and these applications stored in the memory 2. Information on the required performance definition in the information 23 is acquired. Next, the parameter range acquisition unit 5 determines the required performance of these applications based on the acquired information. Note that the required performance of each application constantly changes depending on the vehicle situation 21 and the outside world situation 22.

  FIG. 3 is a diagram illustrating an example of the imaging condition definition. As shown in FIG. 3, in the case of an application of vehicle / pedestrian recognition, sign recognition, and light distribution control, the image type and the imaging frequency are listed as the imaging conditions. Specifically, in the case of a vehicle / pedestrian recognition application, since parallax information is required, a stereo image is required. On the other hand, in the case of a sign recognition application and a light distribution control application, a monocular image is sufficient. The imaging frequency of the three applications is every 50 ms. In addition to the above-described image type and imaging frequency, the imaging conditions include, for example, image quality and exposure time (shutter speed).

  FIG. 4 is a diagram showing an example of the required performance definition. As shown in FIG. 4, the required performances of the applications of vehicle / pedestrian recognition, sign recognition, and light distribution control are all the detection distance, and are divided depending on whether or not the vehicle speed is less than 50 km / h. When the host vehicle speed is less than 50 km / h, the required performance of the vehicle / pedestrian recognition application and the sign recognition application is a detection distance of 50 m or more, and the required performance of the light distribution control application application is a detection distance of 100 m or more. On the other hand, when the own vehicle speed is 50 km / h or more, the required performance of these applications is both a detection distance of 100 m or more.

  Here, an example in which the vehicle speed is 50 km / h or more will be described. In this case, the parameter range acquisition unit 5 acquires information on the vehicle speed from the host vehicle situation 21, and based on the acquired information, the application of the vehicle / pedestrian recognition, sign recognition, and light distribution control application shown in FIG. Referring to the required performance, the required performance of these applications (that is, the detection distance is 100 m or more) is obtained.

  In step S12, the parameter range acquisition unit 5 acquires the imaging parameter range obtained for each application based on the required performance of each application obtained in step S11. For example, in the case of a sign recognition application (hereinafter referred to as application A) and a light distribution control application (hereinafter referred to as application B), the parameter range acquisition unit 5 assumes that the required performance of these applications is satisfied. With reference to the imaging parameter definition in the information 23, a range of imaging parameters related to an image necessary for execution of each application is acquired.

  FIG. 5 is a diagram illustrating an example of the imaging parameter definition of the application A, and FIG. 6 is a diagram illustrating an example of the imaging parameter definition of the application B. Since the required performance of both the application A and the application B is 100 m or more, in the case of FIG. 5, the range of the imaging parameter (here, the exposure time) of the application A that satisfies the condition is 10 to 40 ms. On the other hand, in the case of FIG. 6, the range of the imaging parameter (here, the exposure time) of the application B that satisfies the condition is 20 to 50 ms.

  In step S13, the parameter range acquisition unit 5 acquires the imaging time range based on the imaging parameter range of each application obtained in step S12. The imaging time is determined by the image size, the exposure time, the gain, etc. In this embodiment, the imaging time is simply set as the exposure time. Therefore, the imaging time range of the application A is 10 to 40 ms, and the imaging time range of the application B is 20 to 50 ms.

  In step S14, the parameter determination unit 6 determines whether there is a common range among the imaging parameter ranges of each application. If there is a common range, the process proceeds to step S15. On the other hand, if there is no common range, the process proceeds to step S16. FIG. 7 is a diagram illustrating an example of imaging parameter definitions of the application A and the application B. In the case of FIG. 7, the imaging parameter of the application A and the application B is the imaging time, and the common range of the imaging time of both is 20 to 40 ms. Therefore, the parameter determination unit 6 determines that the imaging parameter range has a common range. judge.

  In step S15, the parameter determination unit 6 determines a shared imaging parameter for sharing an image captured by the stereo camera 8 with a plurality of applications. Here, since the imaging parameter is the imaging time, the parameter determination unit 6 determines the shared imaging time. As shown in FIG. 7, when the imaging time is 30 ms out of the common imaging time range of 20 to 40 ms for the apps A and B, the graph of the app A and the app B are maintained while maintaining the performance of these applications high. Intersects with the graph. Therefore, from the viewpoint of ensuring high performance of the application A and the application B, it is preferable to determine the imaging time 30 ms as the shared imaging time. FIG. 8 is a diagram illustrating an example of an imaging time when an image is shared between the app A and the app B. As shown in FIG. 8, the shared imaging time for sharing images between the app A and the app B is 30 ms, and the imaging cycle of these applications is 50 ms (that is, the imaging frequency is every 50 ms).

  In step S <b> 16, the camera control unit 7 controls image capture by the stereo camera 8 in accordance with the shared imaging time determined by the parameter determination unit 6. Here, since the images necessary for executing the app A and the app B are both monocular images, the camera control unit 7 performs control so that only the left camera 81 of the stereo camera 8 is imaged, for example. And the camera control part 7 transmits the image imaged with the left camera 81 to the application A and the application B, respectively.

  On the other hand, if it is determined in step S14 that the imaging parameter range does not have a common range, the process proceeds to S16. Here, the camera control unit 7 captures an image necessary for executing each application, for example, as a normal individual. The stereo camera 8 is controlled to perform the imaging method. The camera control unit 7 transmits an image captured by the individual imaging method to each application. As a result, a series of processing is completed.

  In the image processing apparatus 1 having the above configuration, the parameter range acquisition unit 5 acquires the imaging parameter ranges related to the images necessary for executing the applications 11 to 1N, and the parameter determination unit 6 includes the imaging parameter ranges. Then, a shared imaging parameter (shared imaging time) for sharing an image captured by the stereo camera 8 with the plurality of applications 11 to 1N when there is a common range is determined. Therefore, it is possible to expand the aspect in which an image can be shared, as compared to the aspect in which a common function can be shared only when a common function is used as in the past. As a result, the situation where one imaging device is shared by a plurality of applications can be expanded. Further, by expanding the situation in which images captured by the stereo camera 8 can be shared, more applications can be executed within a limited period without increasing the number of cameras, thereby reducing the cost of the image processing apparatus. There is an effect.

Second Embodiment
Hereinafter, the second embodiment will be described with reference to FIGS. 9 and 10. The image processing apparatus according to the present embodiment is different from the first embodiment in the processing procedure, but the configuration and the like of the apparatus are the same as those in the first embodiment, and thus the duplicate description is omitted.

  A characteristic part of this embodiment is that the parameter determination unit 6 further provisionally determines an individual imaging time for individually capturing images necessary for each application in addition to the shared imaging time, and determines the individual imaging time and the shared imaging time. The final imaging time is determined by comparison. Hereinafter, the characteristic part will be mainly described. FIG. 9 is a flowchart illustrating a processing procedure of the image processing apparatus according to the second embodiment. In the present embodiment, application A and application B are executed.

  Processes S21 to S23 are the same as the processes S11 to S13 of the first embodiment. The process following S23 is divided into steps S24 to S25 and steps S26 to S27 that proceed in parallel. In step S24, the parameter determination unit 6 determines whether there is a common range in the imaging parameter range. If there is a common range, the process proceeds to step S25. On the other hand, if there is no common range, the process proceeds to step S28.

  As shown in FIG. 7 described above, since the common range of the imaging time of the app A and the app B is 20 to 40 ms, the parameter determination unit 6 determines that there is a common range in the imaging parameter range. In step S <b> 25, the parameter determination unit 6 determines a shared imaging time for sharing images captured by the stereo camera 8 between the app A and the app B. FIG. 10A is a diagram illustrating an example of an imaging time when an image is shared between the app A and the app B. FIG. As shown in FIG. 10A, here, the parameter determination unit 6 determines the shared imaging time as an imaging time 30 ms that can ensure high performance of both the application A and the application B.

  On the other hand, in step S <b> 26, the parameter determination unit 6 determines whether or not the total value of the imaging time when images necessary for executing the application A and the application B are individually captured is within a predetermined imaging cycle. If it is determined that the total value of the imaging time is within the predetermined imaging cycle, the process proceeds to step S27. If it is determined that the total value of the imaging time is not within the predetermined imaging cycle, the process proceeds to step S28.

  Specifically, the parameter determination unit 6 first refers to the imaging time ranges of the app A and the app B acquired in step S23, and takes the shortest imaging when imaging images necessary for executing these applications. Calculate the total time. Next, the parameter determination unit 6 determines whether or not the total value is within a predetermined imaging cycle.

  In the above example, the shortest imaging time of an image necessary for executing the application A is 10 ms (see FIG. 5), and the shortest imaging time of an image necessary for executing the application B is 20 ms (see FIG. 6). The total value of both is 30 ms. Since the predetermined imaging cycle is 50 ms, the total value of the shortest imaging times of both falls within the predetermined imaging cycle. Therefore, the parameter determination unit 6 determines that the total value of the imaging time is within the predetermined imaging cycle, and the process proceeds to S27.

  In step S27, the parameter determination unit 6 provisionally determines an individual imaging time for individually capturing images necessary for each application. FIG. 10B is a diagram illustrating an example of an imaging time when images necessary for executing the application A and the application B are individually captured. In a simple configuration, if the image capturing time required for executing the application A is determined as 10 ms which is the shortest image capturing time, and the image capturing time required for executing the application B is determined as 20 ms which is the minimum capturing time. Here, the parameter determination unit 6 further adjusts the imaging time within a predetermined imaging cycle (50 ms) to improve the performance of each application.

  In the present embodiment, the parameter determination unit 6 adjusts the image capturing time required for executing the app A to 20 ms and the image capturing time required to execute the app B to 30 ms (FIG. 10B). reference). In this way, the performance of each application can be further improved. That is, in the case of the app A, the detection distance is further increased when the imaging time is 20 ms as compared to the shortest imaging time of 10 ms (see FIG. 5), so that the performance of the app A can be improved. Similarly, in the case of the application B, since the detection distance is further increased when the imaging time is 30 ms as compared with the shortest imaging time of 20 ms, the performance of the application B can be improved.

  It should be noted that the adjustment here does not need to target the imaging times of all applications, and may adjust the imaging times of some of the plurality of applications as necessary. For example, when there is a request for maximizing the performance of the application B among the applications A and B, the imaging time of the application B is increased to an exposure time of 35 ms when the detection distance is the longest. On the other hand, the imaging time of the app A is kept at the shortest imaging time of 10 ms. As described above, since the imaging time can be adjusted as necessary, it is possible to meet various requirements for the apparatus.

  In step S28, the parameter determination unit 6 compares the imaging times determined in steps S24 to S25 and steps S26 to S27, respectively, and determines the final imaging time. Specifically, the parameter determination unit 6 selects a shared imaging time and an individual imaging time to improve the performance of the app A and the app B and sets it as the final imaging time.

  On the other hand, when there is no difference in application performance between the two, the parameter determination unit 6 selects, for example, the one that consumes less power by driving the camera as the final imaging time. Note that which of the shared imaging time and the individual imaging time to select varies depending on the situation, but the parameter determination unit 6 should improve the performance of each application according to the situation at that time. What is necessary is just to determine as the last imaging time. On the other hand, if it is determined in step S24 that there is no common range in the imaging parameter range, the shared imaging time is not determined, so the parameter determination unit 6 determines the individual imaging time as the final imaging time.

  In step S29, the camera control unit 7 controls image capture by the stereo camera 8 according to the final imaging time determined in step S28. Here, since the images necessary for executing the application A and the application B are both monocular images, the camera control unit 7 performs control so that only the left camera 81 of the stereo camera 8 is imaged, for example. And the camera control part 7 transmits the image imaged with the left camera 81 to the application A and the application B, respectively. As a result, a series of processing is completed.

  The image processing apparatus according to the present embodiment can obtain the same effects as those of the first embodiment, compare the shared shooting time with the individual shooting time, and select the method that further improves the performance of each application. By determining as the imaging time, it is possible to achieve high performance of each application.

<Third Embodiment>
The third embodiment will be described below with reference to FIG. A characteristic part of the present embodiment is that, in addition to apps A and B that require a monocular image, app C that requires a stereo image is also executed. Hereinafter, the characteristic part will be mainly described. Since the configuration of the apparatus, the processing procedure, and the like are the same as those in the second embodiment, a duplicate description is omitted.

  FIG. 11A is a diagram illustrating an example of an imaging time when an image is shared between the app A and the app B according to the third embodiment, and FIG. 11B is a diagram of the app A and the app B according to the third embodiment. It is a figure which shows the example of the imaging time in the case of image | photographing separately an image required for execution, (c) is a case where the image required for execution of the application A and the application B which concerns on 3rd Embodiment is imaged separately It is a figure which shows the other example of imaging time.

  In this embodiment, a sign recognition application (application A), a light distribution control application (application B), and a vehicle / pedestrian recognition application (hereinafter referred to as application C) are executed. As shown in FIG. 3, in the case of application C, since disparity information is required, a stereo image is required. On the other hand, for the applications A and B, a monocular image is sufficient. Note that the imaging period of these applications is 50 ms.

  Since execution of the application C requires a stereo image, it is necessary to simultaneously capture images with the left camera 81 and the right camera 82. On the other hand, since an image necessary for execution of the application A and the application B is a monocular image, it is only necessary to take an image using one of the left camera 81 and the right camera 82. In the present embodiment, among the three applications, the priority of the application C is the highest. Accordingly, the application C preferentially uses the stereo camera 8 and captures images necessary for the execution of the application A and the application B during the idle time.

  Regarding the imaging time for the application A and the application B, it is considered that there are three types as shown in FIG. First, as shown in FIG. 11A, there is a common range of imaging parameter ranges related to the application A and the application B, and images necessary for executing these applications are captured in the shared imaging time. The processing in this case is performed by the parameter determination unit 6 in steps S24 to S25 of FIG. 9 described above.

  Next, as shown in FIG. 11B, when the total value of the imaging time when images necessary for executing the application A and the application B are individually taken is within a predetermined imaging cycle, the left camera 81 And an image is imaged in individual imaging time using one of the right cameras 82 (here, the right camera 82). The process in this case is performed by the parameter determination unit 6 in steps S26 to S27 of FIG. 9 described above.

  Furthermore, as shown in FIG. 11C, when the respective imaging times when images necessary for executing the application A and the application B are individually taken are within a predetermined imaging cycle, the left camera 81 and the right camera An image is picked up with an individual image pickup time using both the camera 82. In the present embodiment, the right camera 82 captures an image necessary for executing the application A and the left camera 81 captures an image necessary for executing the application B individually. Further, FIG. 11C shows a case where imaging necessary for executing the application A and the application B is performed at the same time. However, these imaging are not necessarily performed at the same time, and may be performed at different timings. Note that the processing in this case is performed by the parameter determination unit 6 in steps S26 to S27 of FIG. 9 described above.

  Subsequently, the parameter determination unit 6 determines the final imaging time based on the above three imaging times. Here, in addition to the priority order, it is preferable to determine the final imaging time in consideration of, for example, ensuring the performance of the obtained application or reducing power consumption by driving the camera. For example, the imaging time shown in FIG. 11A is the best from the viewpoint of sharing imaging.

  In the case of FIGS. 11 (a) and 11 (b), in order to capture an image necessary for execution of the app A and the app B using one of the left camera 81 and the right camera 82 (here, the right camera 82), Since the other camera (left camera 81) is empty, it is possible to take an image necessary for executing another application. Therefore, there is an advantage that more applications can be executed within a limited period without increasing the number of cameras.

  On the other hand, in the case of FIG. 11C, since two cameras are used, there are disadvantages in that the power consumption is increased by driving the camera and the control circuit is complicated. However, in the case of App B (light distribution control application), in order to realize light distribution control including automatic control of the high beam or low beam of the headlight of the own vehicle, the taillight of the preceding vehicle several hundred meters away or the oncoming vehicle It is necessary to detect the headlight. Therefore, imaging with an exposure time longer than other applications (here, application A) is preferable. Therefore, when the application B is executed, it is preferable to determine the imaging time in the case illustrated in FIG. 11C among the above three imaging times as the final imaging time. In this way, the performance of the light distribution control application can be further improved. Note that which of the three imaging times to select varies depending on the situation, so an optimal imaging time may be selected according to the situation and determined as the final imaging time. .

  The image processing apparatus according to the present embodiment can obtain the same effects as those of the above-described embodiments, and can efficiently use the two cameras of the stereo camera 8 based on the type of image necessary for executing each application. Can do. In addition, since a plurality of imaging times as shown in FIG. 11 can be selected, an optimal imaging time can be selected as necessary to enhance the applicability of the apparatus.

  Although the embodiments of the present invention have been described in detail above, the present invention is not limited to the above-described embodiments, and various designs can be made without departing from the spirit of the present invention described in the claims. It can be changed. For example, in the above-described embodiment, the example of imaging time = exposure time has been described as the imaging parameter. However, the imaging parameter is not limited to the exposure time, and the present invention is also applied to other imaging parameters. As another example of the imaging parameter, resolution (number of images) is also conceivable. In this case, the optimum resolution varies depending on the application. As the resolution is higher, the amount of information increases and it takes time to process it. However, in order to obtain a processing result within a predetermined time with a limited processing capability, it is necessary to set a necessary and sufficient resolution.

  As another example of the imaging parameter, white balance (color tone) is also conceivable. In this case, since the object of interest in the image differs depending on the application, it is necessary to set the color tone. For example, the red color in the image stands out to identify the dale light of the preceding vehicle, or the image is made black and white (achromatic) to shorten the processing time.

  In the first embodiment, the stereo camera 8 has been described. However, when the image required for the application to be executed (for example, the app A and the app B) is only a monocular image, a normal camera is used instead of the stereo camera 8. A monocular camera may be used.

DESCRIPTION OF SYMBOLS 1 Image processing apparatus 2 Memory 3 CAN interface part 4 CAN bus 5 Parameter range acquisition part 6 Parameter determination part 7 Camera control part 8 Stereo camera 11-1N Application 81 Left camera 82 Right camera

Claims (8)

An image processing apparatus in which a plurality of applications are executed based on an image captured by an imaging device,
Parameter range acquisition means for acquiring a range of imaging parameters relating to images necessary for execution of each application;
Parameter determining means for determining a shared imaging parameter for sharing an image captured by the imaging device with a plurality of applications based on the range of each imaging parameter acquired by the parameter range acquisition means;
An image processing apparatus comprising: a control unit that controls imaging of the imaging device based on the shared imaging parameter determined by the parameter determination unit.   The parameter determination means determines whether or not there is a common range among the ranges of the respective imaging parameters, and when there is a common range, determines the shared imaging parameter in a plurality of applications having the common range. The image processing apparatus according to claim 1, wherein: The imaging parameter is an imaging time,
The image processing apparatus according to claim 2, wherein the shared imaging parameter is a shared imaging time for sharing an image captured by the imaging device.   The parameter determining means determines whether to execute these applications when the total value of the imaging time when individually capturing images necessary for executing the plurality of applications having the common range is within a predetermined imaging cycle. 4. The image according to claim 3, wherein an individual imaging time for individually capturing necessary images is provisionally determined, and a final imaging time is determined based on the individual imaging time and the shared imaging time. Processing equipment.   5. The parameter determining unit determines, as the final imaging time, the one that further improves the performance of a plurality of applications having the common range among the individual imaging time and the shared imaging time. The image processing apparatus described. The imaging device is a stereo camera;
The monocular image is individually captured by one or both cameras of the stereo camera when an image necessary for executing the plurality of applications having the common range is a monocular image. An image processing apparatus according to 1.   The parameter determining means compares the total value of the shortest imaging time when individually capturing images necessary for execution of the plurality of applications having the common range with the predetermined imaging cycle, and the shortest imaging When the total value of the time is within the predetermined imaging cycle, at least one imaging time is adjusted among the imaging times when imaging is individually performed within a range within the predetermined imaging cycle, and the individual imaging is performed. The image processing apparatus according to claim 6, wherein the time is provisionally determined.   When an application for controlling the light distribution of the imaging device is executed, the parameter determination unit determines an individual imaging time for individually imaging using both of the stereo cameras as a final imaging time. The image processing apparatus according to claim 7.

Images