Information collection device, server, and information collection method

Abstract

This information collecting device for collecting images and position information that are to be transmitted from a vehicle through a communication network to an external server comprises: an image acquiring unit that acquires an image of the outside of the vehicle captured by an image capture device mounted on the vehicle; a position information acquiring unit that acquires position information indicating the image capture position of the image acquired by the image acquiring unit; a resource condition acquiring unit that acquires resource information indicating the condition of resources related to the load of processing the image; a processing method determining unit that determines a processing method with respect to the image in accordance with the condition of the resources indicated by the resource information acquired by the resource condition acquiring unit; an image processing unit that processes the image according to the processing method determined by the processing method determining unit; and an image analyzing unit that analyzes the image as processed by the image processing unit and that outputs the image in accordance with an analyzing result.

Description

[Technical field]

[0001] The present disclosure relates to an information collection device that collects images of the outside of a vehicle captured from the vehicle for detecting abnormalities in the captured images. [Background technology]

[0002] Among conventional techniques for collecting images for anomaly detection, there is a technique in which images taken from the vehicle outside are transmitted to an external server, etc. via a communication network. Since such images generally have a large data size, they are compressed before transmission to prevent transmission failure. Incidentally, Patent Document 1 discloses an image processing device that divides an image based on the viewpoint of areas that a driver driving a vehicle should pay attention to, and performs different compression processing for each divided area. Specifically, the image processing device sets a higher importance for areas that are likely to be overlooked by the driver of the vehicle or that are likely to contain objects that the driver should be aware of, and simplifies the compression process for images of areas with lower importance. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2019-47401 A Summary of the Invention [Problem to be solved by the invention]

[0004] A problem with the conventional techniques is that when an image is compressed, information that indicates anomalies in objects within the image may be lost. The image processing device of Patent Document 1 performs different compression processing for each area into which an image is divided, based on the viewpoint of an area that a driver operating a vehicle should pay attention to, and does not solve the above-mentioned problem.

[0005] The present disclosure is devised to solve the above-mentioned problems, and aims to provide an information collection device that is less likely to lose information indicating abnormalities in objects in images when collecting images. [Means for solving the problem]

[0006] The information collection device disclosed herein is an information collection device that collects images and location information to be transmitted from a vehicle to an external server via a communication network, and includes an image acquisition unit that acquires an image of the outside of the vehicle by an imaging device mounted on the vehicle, a location information acquisition unit that acquires location information indicating the imaging location of the image acquired by the image acquisition unit, a resource status acquisition unit that acquires resource information indicating the status of resources related to the load of processing the image, and a resource status acquisition unit that acquires information on the resource status indicating the load of processing the image by adjusting the resource status indicating ... 、 For each region in the image Compressed or uncompressed The image processing system includes a processing method determination unit which determines a processing method, an image processing unit which processes the image according to the processing method determined by the processing method determination unit, and an image analysis unit which analyzes the image after processing by the image processing unit and outputs the image according to the analysis result. Effect of the Invention

[0007] According to the present disclosure, with the above-described configuration, it is possible to provide an information collection device that is less likely to lose information indicating an abnormality in an object in an image when collecting the image. [Brief description of the drawings]

[0008] [Figure 1] 1 is a diagram showing a configuration of an anomaly detection system including an information collection device according to a first embodiment. [Diagram 2] 4 is a diagram showing an example of a criterion for determining a processing method in the information collecting device according to the first embodiment. FIG. [Diagram 3] 4 is a flowchart showing a process of the information collection device according to the first embodiment. [Figure 4] FIG. 13 is a diagram illustrating an image of processing performed by an information collection device. [Diagram 5] 1 is a diagram illustrating a first example of a hardware configuration of an anomaly detection system including an information collection device. [Figure 6] FIG. 13 is a diagram illustrating a second example of a hardware configuration of an anomaly detection system including an information collection device. [Figure 7] 11 is a diagram illustrating a configuration of an anomaly detection system including an information collection device and a server according to a second embodiment. [Figure 8] FIG. 11 is a diagram showing a configuration of a server according to the second embodiment. [Figure 9] FIG. 11 is a diagram showing an example of a criterion for determining a processing method in the server according to the second embodiment. [Figure 10] FIG. 13 is a diagram showing a first example of an image of command contents from a server to an information collection device. [Figure 11] FIG. 13 is a diagram showing a second example of an image of command contents from the server to the information collection device. [Figure 12] 11 is a flowchart showing an example of processing performed by an information collection device according to the second embodiment. [Figure 13] 13 is a flowchart showing an example of the process of step ST220 in FIG. 12. [Figure 14] 13 is a flowchart showing an example of the process of step ST230 in FIG. 12. [Figure 15] 11 is a flowchart showing an example of processing in a server according to the second embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0009] In order to describe the present disclosure in more detail, embodiments of the present disclosure will be described below with reference to the accompanying drawings.

[0010] Embodiment 1 FIG. 1 is a diagram showing a configuration of an anomaly detection system 1 including an information collection device 10 according to the first embodiment. The abnormality detection system 1 shown in FIG. 1 is a system that detects whether an object in an image captured from the vehicle of the outside of the vehicle is in an abnormal state. The abnormality detection system 1 is composed of an information collection device 10, a camera 20, and a position sensor 30, which are mounted on each vehicle, and a server 100 provided outside the vehicle. The information collecting device and the server 100 are communicatively connected via a communication network (not shown).

[0011] In the anomaly detection system 1 shown in FIG. 1, when an information collection device 10 detects an abnormality in an object in an image captured by a camera 20 through simple analysis processing, the information collection device 10 transmits the image to a server 100, and the server 100 uses the collected image to perform a more detailed analysis processing of the abnormality in the object. The object of abnormality detection is, for example, a road. In this case, abnormalities in road conditions such as unevenness of the pavement, etc., more specifically, abnormalities such as missing white lines on the road, potholes on the road, and cracks or misalignment of manholes, etc. are detected. Furthermore, objects subject to abnormality detection are, for example, traffic lights and structures provided around roads, such as the walls of tunnels. In this case, for example, abnormalities around the road, such as damaged traffic lights and cracks in the walls of a tunnel, are detected.

[0012] The camera 20 is an example of an imaging device in the abnormality detection system 1, and is mounted on each of a number of different vehicles. The camera 20 continuously captures images of the outside of the vehicle from the vehicle and outputs the captured images. An image is made up of multiple frames captured at different times.

[0013] The position sensor 30 is installed in each of a number of different vehicles. The position sensor 30 measures the position of the vehicle at predetermined time intervals using, for example, GPS technology, and outputs position information indicating the position of the vehicle.

[0014] The information collection device 10 is mounted on each of a plurality of different vehicles, and is communicatively connected to a camera 20 and a position sensor 30 mounted on the vehicles. Furthermore, the information collection device 10 is communicably connected to an external server 100 via a communication network. The information collection device 10 collects images to be transmitted to an external server 100 via a communication network, and location information indicating the location where the images were captured. Specifically, the information collection device 10 acquires an image from the camera 20, and acquires location information from the position sensor 30. The acquired location information indicates the location where the image was captured. The information collection device 10 performs analysis using the image and the position information, and when an abnormality is detected in an object in the image, the information collection device 10 transmits the image and the position information to the server 100 . 1, information collection device 10-1, information collection device 10-2, information collection device 10-3, ..., information collection device 10-N (N is an integer equal to or greater than 1) are shown separately. However, in the description, when there is no particular need to show them separately, they will be simply referred to as information collection device 10. The detailed configuration of the information collection device 10 will be described later.

[0015] The server 100 is communicably connected to a plurality of information collection devices 10 via a communication network. The server 100 collects images from each of the information collection devices 10 for analyzing anomalies in objects in the images. The server 100 also analyzes the collected images to detect abnormal details of objects within the images. Specifically, the server 100 receives images and location information from each of a plurality of different information collection devices 10, and stores the images and location information. Then, for example, from a plurality of images in which the position indicated by the position information is the same, the images are analyzed using the images and the position information, and details of abnormalities in the object captured in the images are detected by analysis processing. The server 100 may be realized by, for example, a cloud server, and thus a physical server is not required. Also, the anomaly detection system 1 can be constructed on an appropriate scale according to the range to be analyzed.

[0016] The detailed configuration of the information collection device 10 will be described. The information collection device 10 includes an image acquisition unit 11, a location information acquisition unit 12, a resource status acquisition unit 13, a processing method determination unit 14, an image processing unit 15, an image analysis unit 16, a communication control unit 17, and a transmission unit 18. The information collecting device 10 also includes a storage unit 102 and a control unit, both of which are not shown.

[0017] The image acquisition unit 11 acquires an image of the outside of the vehicle captured by an imaging device mounted on the vehicle.

[0018] The position information acquisition unit 12 acquires position information indicating the imaging position (imaging point) of the image acquired by the image acquisition unit 11. Specifically, when the image acquisition unit 11 acquires an image from the imaging device, the position information acquisition unit 12 acquires position information from the position sensor 30 .

[0019] The resource status acquisition unit 13 acquires resource information indicating the status of resources related to the load of processing an image. The resource status indicated in the resource information is related to the load of image processing, such as the status of the computational resources performing the processing and the image resolution, for example, at least one of the CPU usage rate of the information collecting device 10 (hereinafter also referred to as "CPU usage rate"), the memory usage rate of the information collecting device 10 (hereinafter also referred to as "memory usage rate"), and the resolution of the camera 20 (hereinafter also referred to simply as "resolution"). The resource state acquisition unit 13 sends the resource information to the processing method determination unit 14 .

[0020] The processing method determination unit 14 determines a processing method for the image depending on the state of the resources indicated in the resource information. The processing method is determined by the number of divisions into which each image is divided and the compression method for each divided region. The compression method may be a plurality of compression methods with different compression ratios, for example, it may simply be uncompressed or compressed. In the following description, an area determined to be uncompressed will be referred to as a "uncompressed area", and an area determined to be compressed will be referred to as a "compressed area". Specifically, the processing method determination unit 14 stores in advance the number of divisions and the compression method for each of the CPU utilization rate, the memory utilization rate, and the resolution, or for each combination thereof. The processing method determination unit 14 determines the number of divisions according to at least one of the CPU usage rate, the memory usage rate, and the resolution. Moreover, the processing method determination unit 14 determines a compression method for each divided region, thereby determining a non-compressed region and a compressed region. The compression method for the non-compressed region is a method in which no compression processing is performed, and the amount of information contained in the image captured by the camera 20 is kept as is, without any information loss. However, the compression method for the uncompressed area may be any compression method that causes less information loss and increases the data size compared to the compression method for the compressed area. A compression method for a compressed region is a compression method that causes more information loss and reduces data size compared to a compression method for a non-compressed region.

[0021] FIG. 2 is a diagram showing an example of a criterion for determining a processing method in the information collecting device 10 according to the first embodiment. FIG. 2 shows an example of a combination of CPU usage rate and memory usage rate, and a criterion for determining the number of divisions and one uncompressed area. In FIG. 2, Mod(rand, (division number)) indicates the remainder when the value of a randomly extracted natural number (rand) is divided by the division number.

[0022] The processing method determination unit 14 refers to the criteria shown in FIG. 2 and determines the number of divisions and the non-compressed regions based on the resource information. For example, if the processing method determination unit 14 determines that the CPU usage rate is less than 40% and the memory usage rate is less than 50%, it determines the number of divisions to be four and calculates and determines an identification number indicating one of the four regions after division. For example, if the processing method determination unit 14 determines that the CPU usage rate is less than 40% and the memory usage rate is 50% or more, it determines the number of divisions to be 9 and calculates and determines an identification number indicating one of the nine regions after division. For example, if the processing method determination unit 14 determines that the CPU usage rate is between 40% and 80% and that the memory usage rate is less than 50%, it determines the number of divisions to be 9 and calculates and determines an identification number indicating one of the nine regions after division. For example, if the processing method determination unit 14 determines that the CPU usage rate is between 40% and 80% and that the memory usage rate is 50% or more, it determines the number of divisions to be 16 and calculates and determines an identification number indicating one of the 16 regions after division. For example, if the processing method determination unit 14 determines that the CPU usage rate exceeds 80% and the memory usage rate is less than 50%, it determines the number of divisions to be 16 and calculates and determines an identification number indicating one of the 16 regions after division. For example, if the processing method determination unit 14 determines that the CPU usage rate exceeds 80% and the memory usage rate is 50% or more, it determines the number of divisions to be 25 and calculates and determines an identification number indicating one of the 25 regions after division.

[0023] The image processing unit 15 processes the image according to the processing method determined by the processing method determination unit 14. Specifically, the image processing unit 15 receives information indicating the number of divisions determined by the processing method determination unit 14 and the compression method for each divided region. The image processing unit 15 divides the image according to the division number, processes the uncompressed area so as not to cause information loss according to information indicating the compression method for each area (uncompressed area or compressed area), and compresses the compressed area so as to reduce the data size. When dividing an image, the image processing unit 15 assigns an identification number to each divided region. For example, the upper left region in the image is assigned an identification number (0), the region to the right of the upper left is assigned an identification number (1), and so on up to the upper right region. Next, an identification number is assigned to the region immediately below the upper left region, and so on up to the region immediately below the upper right region. This is repeated to assign identification numbers to all regions up to the lower right region. When the number of divisions is 9, the identification numbers are (0) to (8), and when the number of divisions is 16 (see FIG. 4 described later), the identification numbers are (0) to (15). In the following description, a region with an identification number (n) is also referred to as region (n).

[0024] The image analysis unit 16 is a first image analysis unit in the abnormality detection system 1. The image analysis unit 16 analyzes the image processed by the image processing unit 15, and outputs the image according to the analysis result. Specifically, the image analysis unit 16 receives the processed image from the image processing unit 15, and performs an analysis process on the image to detect abnormalities in objects within the image. The analysis process itself for detecting anomalies from an image is a known technique, and a detailed description thereof will be omitted. As a result of the analysis process, the image analysis unit 16 generates status information indicating whether or not each region contains an abnormality, and outputs the image of the region containing an abnormality and the status information.

[0025] The communication control unit 17 transmits the image output by the image analysis unit 16 and the position information acquired by the position information acquisition unit 12 to an external server 100 via the transmission unit 18 and the communication network. Specifically, the communication control unit 17 adds information specifying the external server 100 to the image and position information, and outputs the image and position information to the transmission unit 18.

[0026] Upon receiving a command from the communication control unit 17, the transmission unit 18 transmits the image and status information to the server 100 via the communication network. The transmitting unit 18 is, for example, a communication modem.

[0027] A control unit (not shown) controls the information collection device 10 . A storage unit (not shown) temporarily stores images and position information, for example.

[0028] The following describes the processing of the information collecting device 10. In the description, it is assumed that the criteria shown in Fig. 2 are used, and that the CPU utilization rate is 60% and the memory utilization rate is 60%. FIG. 3 is a flowchart showing the process of the information collecting device 10 according to the first embodiment. FIG. 4 is a diagram showing an image of the process of the information collection device 10. As shown in FIG.

[0029] The information collection device 10 starts processing based on startup or a start operation from the user. The information collection device 10 acquires an image and also acquires location information (step ST101). Specifically, the image acquisition unit 11 in the information collection device 10 acquires an image from the camera 20 , and when the image acquisition unit 11 acquires the image, the position information acquisition unit 12 acquires position information from the position sensor 30 . The image acquisition unit 11 outputs the acquired image. The output image is sent to the image processing unit 15. The location information acquisition unit 12 outputs the acquired location information. The output location information is sent to the communication control unit 17.

[0030] The resource state acquisition unit checks the CPU and memory in the information collection device 10, and acquires resource information including the CPU utilization rate and memory utilization rate (step ST102). The resource state acquisition unit outputs the resource information. The output resource information is sent to the processing method determination unit 14.

[0031] The processing method determination unit 14 determines the processing method using the resource information (step ST103). Specifically, the processing method determination unit 14 recognizes that the CPU usage rate is 60% and the memory usage rate is 60% based on the resource information. Next, the processing method determination unit 14 refers to the criteria shown in Fig. 2 and determines the number of divisions to be 16. Next, the processing method determination unit 14 selects one region from the 16 regions and determines it to be a non-compressed region. Here, it is assumed that the region (7) shown in Fig. 4 has been determined. The processing method determination unit 14 outputs processing method information indicating the division number "16" and the non-compressed region "(7)". The outputted processing method information is sent to the image processing unit 15.

[0032] The image processing unit 15 processes the image using the processing method determined by the processing method determination unit 14 (step ST104). Specifically, the image processing unit 15 receives the processing method information, and acquires the division number "16" and the non-compressed area "(7)" based on the processing method information. Next, as shown in Fig. 4, the image processing unit 15 divides the image 1000 received from the image acquisition unit 11 into equal division numbers "16". Next, the image processing unit 15 assigns identification numbers from (0) to (15) to the divided areas, in order, from the upper left area to the lower right area. The identification number of each area is added, for example, to the header of the data in area units. Next, based on the uncompressed area "(7)", the image processing unit 15 processes area (7) as an uncompressed area 1001, as shown in FIG. 4, and compresses areas (0), (1), (2), (3), (4), (5), (6), (8), (9), (10), (11), (12), (13), (14) and (15) as compressed areas 1002. The image processing unit 15 outputs the processed image 1000. The output image 1000 is sent to the image analysis unit 16 . The image analysis unit 16 analyzes the processed image (step ST105). The image analysis unit 16 analyzes whether or not there is an abnormality in the object in the image, and determines whether or not there is an abnormality in the object in the image (step ST106). When it is determined that there is an abnormality (step ST106 “YES”), the image analysis unit 16 sends the image to the communication control unit 17. The communication control unit 17 transmits the image and the position information to the server 100 via the transmission unit 18 (step ST107).

[0033] When it is determined that there is no abnormality (step ST106 "NO"), the image analysis unit 16 stores the image in a storage unit (not shown) (step ST108). The images stored in the storage unit may be discarded after a predetermined time.

[0034] When the process of step ST107 or step ST108 ends, a control unit (not shown) in the information collection device 10 determines whether the vehicle has traveled a predetermined distance (step ST109).

[0035] A control unit (not shown) repeats step ST109 until the vehicle travels a predetermined distance, and when it is determined that the vehicle has traveled the predetermined distance (step ST109 "YES"), controls to repeat the processing from step ST101.

[0036] The hardware configuration of the information collection device 10 will be described. It is assumed that the information collecting device 10 includes a processing circuit for realizing the functions of the above-mentioned components in the information collecting device 10. The processing circuit may be a processing circuit as dedicated hardware, or may be a processor that executes a program stored in a memory. FIG. 5 is a diagram illustrating a first example of a hardware configuration of an information collecting system including the information collecting device 10. As shown in FIG. As shown in FIG. 5, when the processing circuit is a processor 2001, the functions of the above components in the information collecting device 10 are realized by software, firmware, or a combination of software and firmware. The software or firmware is written as a program and stored in the memory 2002. The processor 2001 realizes the functions of the components by reading and executing the program stored in the memory 2002. That is, the information collecting device 10 includes the memory 2002 for storing a program that, when executed by the processor 2001, results in the execution of the steps shown in the flowchart shown in FIG. 3 and the like. It can also be said that the program causes a computer to execute the procedure or method of the above components in the information collecting device 10.

[0037] Here, the processor 2001 refers to a CPU (Central Processing Unit), a processing device, an arithmetic device, a microprocessor, or the like. The memory 2002 may be a non-volatile or volatile semiconductor memory such as a RAM (Random Access Memory), a ROM (Read Only Memory), an EPROM (Erasable Programmable ROM), or a flash memory, or may be a magnetic disk such as a hard disk or a flexible disk, or may be an optical disk such as a CD (Compact Disc) or a DVD (Digital Versatile Disc).

[0038] It should be noted that the functions of the above components in the information collecting device 10 may be partially realized by dedicated hardware and partially realized by software or firmware. In this manner, the above components in the information collecting device 10 can realize the above-mentioned functions by hardware, software, firmware, or a combination of these.

[0039] FIG. 6 is a diagram illustrating a second example of the hardware configuration of the information collecting system including the information collecting device 10. As shown in FIG. 6, when the processing circuit is a dedicated hardware, the processing circuit 2003 may be, for example, a single circuit, a composite circuit, a programmed processor, a parallel programmed processor, an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), a SoC (System-on-a-chip), or a combination thereof. 10 The functions of the above components may be realized by a plurality of processing circuits 2003, or the functions of the components may be realized by a single processing circuit 2003.

[0040] As described above, the information collection device of embodiment 1 is an information collection device that collects images and location information to be transmitted from a vehicle to an external server via a communication network, and is configured to include an image acquisition unit that acquires images of the outside of the vehicle by an imaging device mounted on the vehicle, a location information acquisition unit that acquires location information indicating the imaging location of the image acquired by the image acquisition unit, a resource status acquisition unit that acquires resource information indicating the state of resources related to the load of processing the image, a processing method determination unit that determines a processing method for the image depending on the state of resources indicated in the resource information acquired by the resource status acquisition unit, an image processing unit that processes the image in accordance with the processing method determined by the processing method determination unit, and an image analysis unit that analyzes the image after processing by the image processing unit and outputs the image depending on the analysis result. This has the effect of providing an information collection device that is less likely to lose information indicating an abnormality in an object in an image when collecting an image.

[0041] The information collection device is further configured to include a communication control unit that transmits the image output by the image analysis unit and the location information acquired by the location information acquisition unit to an external server via a communication network. This brings about an effect that it is possible to provide an information collection device that efficiently realizes information collection from the information collection device to the server.

[0042] In addition, in the information collection device, the resource information is configured to include at least one of information indicating the performance of the CPU, memory capacity, and resolution of the imaging device. This provides the effect of providing an information collection device that makes it difficult for information indicating an abnormality in an object in an image to be lost, depending on the processing capacity of the information collection device.

[0043] In the information collecting device, the processing method determining unit is configured to determine the number of divisions of the image and the compression method for each divided region based on the resource information. This has the effect of providing an information collection device that efficiently reduces the data size of an image while making it less likely that information indicating abnormalities in objects in the image will be lost, depending on the processing capacity of the information collection device.

[0044] The information collection method of embodiment 1 is an information collection method by an information collection device that collects images and location information to be transmitted from the vehicle to an external server via a communication network, in which an image acquisition unit acquires an image of the outside of the vehicle captured by an imaging device mounted on the vehicle, a location information acquisition unit acquires location information indicating the location where the image was captured, a resource status acquisition unit acquires resource information indicating the status of resources related to the load of processing the image, a processing method determination unit determines a processing method for the image in accordance with the resource status indicated in the resource information, an image processing unit processes the image using the processing method determined by the processing method determination unit, and an image analysis unit analyzes the image after processing by the image processing unit and outputs the image in accordance with the analysis result. This has the effect of providing an information collecting method and an information collecting device using this method in which information indicating an abnormality in an object in an image is unlikely to be lost when the image is collected.

[0045] Embodiment 2 In the first embodiment, the embodiment has been described in which each information collection device 10 independently determines the image processing method. In the second embodiment, a configuration in which an information collection device 10' and a server 100' cooperate with each other will be described. In addition, among the configurations according to the second embodiment, the configurations similar to those of the first embodiment are denoted by the same reference numerals as those in the drawings used in the first embodiment, and the description thereof will be omitted as appropriate.

[0046] FIG. 7 is a diagram showing a configuration of an anomaly detection system 1' including an information collection device 10' and a server 100' according to the second embodiment. An abnormality detection system 1' shown in FIG. 7 is composed of an information collection device 10', a camera and position sensor 30, which are mounted on each vehicle, and a server 100' provided outside the vehicle. In the anomaly detection system 1', the camera and the position sensor 30 are similar to the camera and the position sensor 30 in the anomaly detection system 1 of the first embodiment, and therefore a description thereof will be omitted.

[0047] The information collection device 10' includes an image acquisition unit 11, a location information acquisition unit 12, a resource state acquisition unit 13', a processing method determination unit 14', an image processing unit 15, an image analysis unit 16, a communication control unit 17', and a transmission unit 18. The image acquisition unit 11, the location information acquisition unit 12, the image processing unit 15, the image analysis unit 16, and the transmission unit 18 are similar to the image acquisition unit 11, the location information acquisition unit 12, the image processing unit 15, the image analysis unit 16, and the transmission unit 18 in the information collection device 10 of embodiment 1, respectively, and therefore their descriptions are omitted.

[0048] The resource state acquisition unit 13' has a function similar to that of the resource state acquisition unit 13 of the first embodiment, and in addition, has a function of sending resource information to a communication control unit 17'.

[0049] The processing method determination unit 14' has the same function as the processing method determination unit 14 of the first embodiment. The processing method determination unit 14' also has a function of determining a processing method according to command information from an external server 100'. Specifically, the processing method determination unit 14' receives command information from the notification control unit' and determines a different processing method depending on the content of the command information.

[0050] The communication control unit 17' has the same functions as the communication control unit 17 of the first embodiment. The communication control unit 17' also has a function of receiving resource information from the resource state acquisition unit 13' and sending it to the server 100' via the transmission unit 18 and the communication network. Further, the communication control unit 17' receives command information from the server 100' via the communication network and the transmission unit 18, and transmits the received command information to the processing method determination unit 14. ´ It has the function of sending to.

[0051] The server 100' has the same functions as the server 100 of the first embodiment. In addition, the server 100' has a function of, when the server 100' is notified of resource information from the information collection device 10', using the resource information to give instructions regarding the image processing method in the information collection device 10'. The configuration of the server 100' will now be described. FIG. 8 is a diagram showing a configuration of a server 100' according to the second embodiment. FIG. 9 is a diagram showing an example of a criterion for determining a processing method in the server 100′ according to the second embodiment. As shown in FIG. 8, the server 100′ includes a communication unit 101, a storage unit 102, a command determination unit 103, and an image analysis unit 106.

[0052] The communication unit 101 receives the image and the position information from the information collection device 10'. Furthermore, the communication unit 101 receives resource information for each information collection device 10' from the information collection device 10'. Furthermore, the communication unit 101 transmits command information indicating the command determined within the server 100' to the information collection device 10'.

[0053] The storage unit 102 stores the image and position information received from the information collection device 10'. The storage unit 102 also stores the criteria for determining the processing method and the collection history. FIG. 9 is a diagram showing an example of a criterion for determining a processing method and a collection history in the server 100′ according to the second embodiment. 9, for example, a first division number, a second division number, a third division number, and collection history information are stored in advance in the storage unit 102 for each piece of location information such as point A, point B, and point C. The first division number is the division number when the processing performance of the information collecting device 10' is determined to be low, the second division number is the division number when the processing performance of the information collecting device 10' is determined to be standard, and the third division number is the division number when the processing performance of the information collecting device 10' is determined to be high.

[0054] The command decision unit 103 decides a command such as "issue a command", "specify all processing methods", or "do not issue a command" according to a preset command format. The command determination unit 103 uses resource information indicating the state of resources related to the load of processing the image in the information collecting device 10' to determine the number of divisions of the image and whether some of the divided areas will be compressed areas or non-compressed areas. Specifically, the command determination unit 103 includes a division method determination unit 104 and a designated area selection unit 105 .

[0055] Upon receiving the location information and resource information from the information collection device 10', the division method determination unit 104 uses the location information and resource information to refer to the criteria stored in the storage unit 102 and determines the number of divisions into which the image is to be divided. Specifically, the division method determination unit 104 identifies an image capturing location using the location information. The division method determination unit 104 determines the processing performance of the information collection device 10' using the resource information. The division method determination unit 104 determines the number of divisions based on the criteria shown in FIG. 9 using the location information and the processing performance. When the division method determination unit 104 has determined the number of divisions into which the image is to be divided, the designated region selection unit 105 selects a compressed region or a non-compressed region using the collection history. Specifically, the designated region selection unit 105 selects, as the compression region, a region that has already been acquired in an image at the same position in the acquisition history. Furthermore, the designated region selection unit 105 may add a predetermined region as a compression region.

[0056] The image analysis unit 106 is an anomaly detection system 1 ´ This is the second image analysis section in the The image analysis unit 106 performs an analysis process to detect abnormalities in objects in the images using the images collected from the multiple information collection devices 10'. The image analysis unit 106 performs a more detailed analysis than the image analysis unit 16 in the information collection device 10'.

[0057] Here, an example of the command contents from the server 100' to the information collection device 10' will be described. The server 100' issues, for example, the following five types of commands (1) to (5).

[0058] (1) Specify only the area to be compressed based on past information collected by the server 100 FIG. 10 is a diagram showing a first example of the image of the command contents from the server 100' to the information collection device 10'. In the server 100', the command determination unit 103 determines a command to designate the areas (1) and (7) as compressed areas when uncompressed images are collected for the areas (7) and (1) at the same location.

[0059] (2) Specify only static compression areas FIG. 11 is a diagram showing a second example of the image of the command contents from the server 100' to the information collection device 10'. In FIG. 11, areas (1), (2), (5), (6), (9), (10), (13), and (14) are areas that have been fixed in advance as compression areas. In the server 100', when the compression area is fixed at a predetermined point, the command decision unit 103 decides a command to designate the fixed area as the compression area. The information collecting device 10' that receives this command can determine that the areas other than the designated compressed area are to be non-compressed areas.

[0060] (3) A combination of (1) and (2) The server 100' issues a command by adding a compression area determined based on information collected from the information collecting device 10' in addition to the statically designated compression area.

[0061] (4) No specification of number of divisions or compression area No specification is made from the server 100'. As a result, in the information collection device 10', the image is processed by the processing method determined according to the resource information.

[0062] (5) Specify the number of divisions and the uncompressed area A command is issued from the server 100' to designate the number of divisions and the non-compressed area. As a result, the information collecting device 10' does not perform the process of determining the number of divisions and the non-compressed regions.

[0063] The process in the information collection device 10' will now be described. FIG. 12 is a flowchart showing an example of processing of the information collection device 10' according to the second embodiment. The information collection device 10' starts processing based on startup or a start operation from the user. The information collection device 10' acquires an image and also acquires location information (step ST101). Specifically, the image acquisition unit 11 in the information collection device 10 ′ acquires an image from a camera, and when the image acquisition unit 11 acquires the image, the position information acquisition unit 12 acquires position information from the position sensor 30 . The image acquisition unit 11 outputs the acquired image. The output image is sent to the image processing unit 15. The location information acquisition unit 12 outputs the acquired location information. The output location information is transmitted to the communication control unit 17. ´ will be sent to.

[0064] Resource status acquisition unit 13´ The CPU and memory in the information collection device 10' are checked, and resource information including the CPU utilization rate and memory utilization rate is acquired (step ST102). Resource status acquisition unit 13´ will print resource information.

[0065] The communication control unit 17' determines whether communication with an external server 100' via a communication network is possible (step ST201). If communication is not possible (step ST201 "NO"), the communication control unit 17' waits to receive command information from the server 100'.

[0066] If communication is possible (step ST201 "YES"), the communication control unit 17' acquires location information from the location information acquisition unit 12 and also acquires the resource status acquisition unit 13´ Obtain resource information from. The communication control unit 17' transmits the location information and resource information to the server 100' via the transmission unit 18 and the communication network (step ST202). After executing the process of step ST202, the communication control section 17' waits to receive command information from the server 100'.

[0067] Upon receiving the command information from the server 100' (step ST203), the communication control unit 17' sends the command information to the processing method determination unit 14'. The machining method determination unit 14' analyzes the command information and determines the command content (step ST204).

[0068] When the processing method determination unit 14' determines that the command content is "no command" or "no area designation", the process proceeds to a first processing method determination process (step ST210). An example of the first processing method determination process will be described later.

[0069] If the command content is "only compressed region is designated", the processing method determination unit 14' proceeds to a second processing method determination process (step ST220). An example of the second processing method determination process will be described later.

[0070] If the command content is "division number and compressed region are specified", the processing method determination unit 14' proceeds to a third processing method determination process (step ST230). An example of the third processing method determination process will be described later.

[0071] In the processing method determination unit 14', the process goes to step ST104 via the process of step ST210, step ST220, or step ST230. Since each process from step ST104 to step ST109 is similar to that in the first embodiment, detailed description thereof will be omitted.

[0072] An example of the first processing method determination process (step ST210) will be described. In step ST210, the processing method determination unit 14' determines a processing method using the resource information, similarly to step ST103 described in the first embodiment. The processing method determination unit 14' outputs processing method information indicating the processing method. Next, the information collection device 10' proceeds to the process of step ST104.

[0073] An example of the second processing method determination process (step ST220) will be described. FIG. 13 is a flowchart showing an example of the process of step ST220 in FIG. First, the processing method determination unit 14' determines a processing method by using the resource information (step ST221). Specifically, the number of divisions is determined according to the resource information, and a non-compressed area is determined from among the divided areas other than the designated compressed area. It is determined whether the selected non-compressed area overlaps with the specified compressed area (step ST222). When it is determined in step ST222 that there is an overlap (step ST222 YES "), and increment the number of overlaps (step ST223). The processing method determination unit 14' judges whether the number of overlaps is the same as the number of divisions in the determined processing method (number of overlaps=number of divisions?) (step ST224). If the number of overlaps is not the same as the number of divisions in the processing method determined in step ST221 ("NO" in step ST224), the process returns to step ST221. If the number of overlaps is the same as the number of divisions in the processing method determined in step ST221 ("YES" in step ST224), the number of divisions is changed (step ST225). Then, the overlap count is reset (step ST226), and the process returns to step ST221. In the information collection device 10', when it is determined that there is no overlap in step ST222 ("NO" in step ST222), the information collection device 10' proceeds to the process of step ST104.

[0074] An example of the third processing method determination process (step ST230) will be described. FIG. 14 is a flowchart showing an example of the process of step ST230 in FIG. The processing method determination unit 14' directive A processing method is determined according to the contents (step ST231). After deciding the processing method, the information collecting device 10' proceeds to the process of step ST104.

[0075] The process in the server 100' will be described. Here, the process will be described using the criteria and collection history shown in FIG. FIG. 15 is a flowchart showing the process in the server 100' according to the second embodiment. The server 100' waits for a notification from the information collection device 10' (step ST301). Upon receiving the location information and resource information from the information collection device 10' (step ST302), the command decision section 103 judges the current setting contents (step ST303).

[0076] If the current setting is "no command", the process returns to step ST301.

[0077] If the current setting is "command", the designated region selection unit determines the compression designated region using the collection history and predetermined region information (step ST304), and then proceeds to the process of step ST310.

[0078] If the current setting is "specify all processing methods", the division method decision unit decides the processing performance of the information collection device 10' based on the resource information (step ST305). If it is judged in step ST305 that the processing performance is "high", the division method decision unit decides on the third division number (step ST306). If the processing performance is judged to be "standard" in step ST305, the division method decision unit decides on the second division number (step ST307). If it is judged in step ST305 that the processing performance is "low", the division method decision unit decides on the first division number (step ST308). Next, the designated region selection unit uses the collection history to determine an uncollected region from among the regions that have not yet been collected, in accordance with the division number (step ST309). Next, the process proceeds to step ST310.

[0079] In step ST310, the communication section 101 receives the command information from the command decision section 103, and transmits the command information to the information collection device 10'.

[0080] Accordingly, in the information collecting device 10', processing based on the command information is performed and an image is transmitted. Then, the server 100' receives the location information and the image from the information collection device 10' (step ST311).

[0081] Next, the current settings are confirmed (step ST312). If the current setting is "reflect in history", the command decision section 103 reflects it in the collection history (step ST313).

[0082] If the current setting is "do not reflect in history", the process returns to step ST301 without changing the collection history.

[0083] The hardware configurations of an information collection device 10' and a server 100' according to the second embodiment are similar to those of the first embodiment, and therefore a description thereof will be omitted.

[0084] The information collection device of the above-described embodiment 2 is further configured in addition to the configuration of embodiment 1 so that the communication control unit transmits the resource information acquired by the resource status acquisition unit to an external server, and after transmission, receives an instruction for the information collection method from the external server, and the processing method determination unit determines the processing method in accordance with the instruction for the information collection method received by the communication control unit. This makes it possible to provide an information collection device that efficiently collects information between the server and the information collection device.

[0085] The server according to the above-mentioned embodiment 2 is a server that collects images and location information from an information collection device mounted on a vehicle via a communication network, and is configured to include a command determination unit that, upon receiving resource information from the information collection device indicating the state of resources related to the load of processing on the images, uses the resource information to determine the number of divisions of the image and whether some of the multiple areas into which the image is divided will be compressed areas or non-compressed areas, and a communication unit that notifies the information collection device of the number of divisions and areas determined by the command determination unit. This has the effect of providing a server in which information indicating an abnormality in an object in an image is unlikely to be lost when the image is collected.

[0086] It should be noted that, within the scope of the disclosure, the embodiments may be freely combined, any component of each embodiment may be modified, or any component of each embodiment may be omitted. [Industrial Applicability]

[0087] An information collection device according to the present disclosure is suitable for use in an abnormality detection system or the like that collects images of the outside of a vehicle from the vehicle. [Explanation of symbols]

[0088] 1,1´ Anomaly detection system, 10,10-1,10-2,10-3,10-N,10´,10´-1,10´-2,10´-3,10´-N Information collection device, 11 Image acquisition unit, 12 Location information acquisition unit, 13,13´ Resource status acquisition unit, 14,14´ Processing method determination unit, 15 Image processing unit, 16 Image analysis unit, 17,17´ Communication control unit, 18 Transmission unit, 20 Camera (imaging device), 30 Position sensor, 100,100´ Server, 101 Communication unit, 102 Memory unit, 103 Command determination unit, 104 Division method determination unit, 105 Designated area selection unit, 106 Image analysis unit, 1000 Image, 1001 Uncompressed area, 1002 Compressed area, 2001 Processor, 2002 Memory, 2003 Processing Circuits.

Claims

1. An information collection device for collecting images and position information to be transmitted from a vehicle to an external server via a communication network, an image acquisition unit that acquires an image of the outside of the vehicle by an imaging device mounted on the vehicle; a position information acquisition unit that acquires position information indicating an imaging position of the image acquired by the image acquisition unit; a resource status acquisition unit that acquires resource information indicating a status of a resource related to a load of processing an image; a processing method determination unit that determines a processing method (compression or non-compression) for each region of the image in accordance with a resource state indicated in the resource information acquired by the resource state acquisition unit so that a non-compressed region is included in a part of the region of the image; an image processing unit that processes an image according to the processing method determined by the processing method determination unit; an image analysis unit that analyzes the image processed by the image processing unit and outputs an image according to the analysis result; An information gathering device comprising:

2. The information collection device according to claim 1 , further comprising a communication control unit that transmits the image output by the image analysis unit and the location information acquired by the location information acquisition unit to an external server via a communication network.

3. 2. The information collection device according to claim 1, wherein the resource information includes at least one of information indicating a CPU usage rate, a memory usage rate, and a resolution of an image capture device.

4. the processing method determination unit determines the number of divisions of the image and a compression method for each divided region based on the resource information; 2. The information collecting device according to claim 1.

5. the communication control unit transmits the resource information acquired by the resource state acquisition unit to an external server, and after the transmission, receives a command for an information collection method from the external server; The processing method determination unit determines a processing method according to the command for the information collection method received by the communication control unit.

3. The information collecting device according to claim 2.

6. A server that collects image and position information from an information collection device mounted on a vehicle via a communication network, a command determination unit that, when receiving resource information indicating a state of a resource related to a load of processing an image from the information collecting device, determines the number of divisions of the image and whether some of the multiple regions into which the image is divided are to be compressed regions or non-compressed regions using the resource information; a communication unit that notifies the information collection device of the division number and the area determined by the command determination unit; A server comprising:

7. 1. An information collection method for an information collection device that collects images and position information to be transmitted from a vehicle to an external server via a communication network, comprising: The image acquisition unit acquires an image of the outside of the vehicle by an imaging device mounted on the vehicle, The position information acquisition unit acquires position information indicating a position where the image was captured, a resource status acquisition unit acquires resource information indicating a status of resources related to a load of processing the image; a processing method determination unit determines a processing method (compression or non-compression) for each region of the image in accordance with a resource state indicated in the resource information so that a non-compressed region is included in a part of the region of the image; an image processing unit processes the image by the processing method determined by the processing method determination unit; An image analysis unit analyzes the image processed by the image processing unit and outputs the image according to the analysis result.

1. An information gathering method comprising:

Images