Video compression device, video compression method, and computer program

Abstract

A video compression method by a video compression device, including: a step for extracting a region of interest that includes one of a plurality of objects of interest from each image constituting a video; a step for determining the image quality of the region of interest on the basis of the priority of the object of interest that is included in the extracted region of interest and the available bandwidth of a transmission path; a step for compressing the video on the basis of the determined image quality of the region of interest; and a step for transmitting the compressed video to the outside of the video compression device via the transmission path.

Description

Video compression method, video compression device, and computer program

[0001] This disclosure relates to a video compression method, a video compression device, and a computer program. This application claims priority to Japanese Patent Application No. 2022-065258, filed April 11, 2022, and incorporates by reference all of the contents of said Japanese application.

[0002] BACKGROUND ART There are an increasing number of opportunities to transmit video images wirelessly or via wires, such as when a video image of the surroundings of a moving object such as an automobile, captured by a camera mounted on the moving object, is transmitted to a server outside the moving object.

[0003] Generally, available bandwidth (the communication bandwidth of the transmission path available for communication) fluctuates in communications. For this reason, if a video data volume that exceeds the available bandwidth is sent to the transmission path, the video cannot be transmitted correctly. This causes block noise and distorted video when the video received on the server is played back. In particular, available bandwidth tends to be insufficient when transmitting video via wireless communications.

[0004] Meanwhile, a technology called smart codec has been developed that compresses a region of interest in a video using a compression method that allows expansion with higher image quality than other regions (see, for example, Non-Patent Document 1).

[0005] JSECURITY, "Smart Encoding", [online], 2019, [Retrieved October 5, 2021], Internet <URL: https: / / jsecurity.jp / new-product / smartencoding / >

[0006] A video compression method according to one aspect of the present disclosure is a video compression method using a video compression device, and includes the steps of extracting a target area including one of a plurality of target objects from each image constituting the video, determining the image quality of the target area based on the priority of the target object included in the extracted target area and the available bandwidth of a transmission path, compressing the video based on the determined image quality of the target area, and transmitting the compressed video to an outside of the video compression device via the transmission path.

[0007] The present disclosure can also be realized as a computer program for causing a computer to execute characteristic steps included in the video compression method. Needless to say, such a computer program can be distributed on a computer-readable non-volatile recording medium such as a CD-ROM (Compact Disc-Read Only Memory) or via a communication network such as the Internet.

[0008] FIG. 1 is a block diagram showing a configuration of a video processing system according to an embodiment of the present disclosure. FIG. 2 is a block diagram showing a configuration of a video compression device according to an embodiment of the present disclosure. FIG. 3 is a diagram showing an example of an image included in video output by a camera. FIG. 4 is a diagram showing the image shown in FIG. 3 divided into a plurality of blocks. FIG. 5 is a diagram showing an example of a target region including a target object. FIG. 6 is a diagram showing another example of a target region including a target object. FIG. 7 is a diagram showing an example of a result of target region extraction by a target region extraction unit. FIG. 8 is a block diagram showing a configuration of a server according to an embodiment of the present disclosure. FIG. 9 is a flowchart showing an example of a processing procedure executed by the video compression device. FIG. 10 is a flowchart showing details of an image quality determination process (step S2 of FIG. 9 ). FIG. 11 is a flowchart showing details of an image quality determination process (step S2 of FIG. 9 ) according to Modification 2. FIG. 12 is a flowchart showing details of an image quality determination process (step S2 of FIG. 9 ) according to Modification 3. FIG. 13 is a flowchart showing details of an image quality determination process (step S2 of FIG. 9 ) according to Modification 4. FIG. 14 is a flowchart showing details of an image quality determination process (step S2 of FIG. 9 ) according to Modification 5. FIG. 15 is a flowchart showing details of the image quality determination process (step S2 in FIG. 9) according to the sixth modification.

[0009] [Problem to be Solved by the Present Disclosure] Even if a conventional smart codec reduces the amount of data by lowering the image quality of areas other than the area of ​​interest, there is a possibility that the amount of compressed video data that exceeds the available bandwidth may be transmitted to the transmission path. As a result, when the compressed video is decompressed and played back on the server side, the video may become distorted.

[0010] The present disclosure has been made in consideration of the above circumstances, and aims to provide a video compression method, a video compression device, and a computer program that can achieve transmission of video including a high-quality region of interest even when the available bandwidth of the transmission path used for communication fluctuates.

[0011] Effect of the Present Disclosure According to the present disclosure, even if the available bandwidth of the transmission path used for communication fluctuates, it is possible to realize transmission of high-quality video including a region of interest.

[0012] [Outline of Embodiments of the Present Disclosure] First, an outline of embodiments of the present disclosure will be listed and described. (1) A video compression method according to one embodiment of the present disclosure is a video compression method performed by a video compression device, and includes the steps of extracting a target region including any one of a plurality of target objects from each image constituting a video, determining image quality of the target region based on a priority of the target object included in the extracted target region and an available bandwidth of a transmission path, compressing the video based on the determined image quality of the target region, and transmitting the compressed video to an external device via the transmission path.

[0013] This configuration allows the image quality of the target region to be adjusted based on the priority of the target object and the available bandwidth of the transmission path. In other words, the image quality of the target region can be determined so that the target region containing a target object with a higher priority is compressed with higher image quality and the compressed video is not transmitted to the transmission path in excess of the available bandwidth. Therefore, even if the available bandwidth of the transmission path used for communication fluctuates, it is possible to transmit video containing a high-quality region of interest.

[0014] (2) In the above (1), the compressed video may be used for at least one of remote monitoring and remote control of a moving object, and the priority may be determined based on the degree of influence of the moving object on the target object.

[0015] For example, the greater the impact on a target object that would be received in the event of a collision with a moving body, the higher the priority is set. Therefore, it becomes possible to remotely monitor or remotely control the moving body so that a collision can be avoided more easily with a target object that is more likely to be affected in the event of a collision. For example, when a moving body approaches a pedestrian who is most likely to be affected in the event of a collision, remote control such as stopping the moving body can be performed.

[0016] (3) In (1) or (2) above, the compressed video may be used for at least one of remote monitoring and remote control of a moving object, and the priority may be determined based on the usefulness of information collected from the target object.

[0017] For example, information obtained from a traffic signal is more useful for remote monitoring or remote control of a mobile object than information obtained from a signboard. Therefore, with this configuration, the image quality of a target area including a traffic signal, which is more useful for remote monitoring or remote control of a mobile object, can be set higher than the image quality of a target area including a roadside signboard, which is less useful for remote monitoring or remote control of a mobile object.

[0018] (4) In any of (1) to (3) above, in the step of compressing the image, the image may be compressed by excluding a background area that is an area other than the target area and the target area that includes the target object with a priority lower than a predetermined priority.

[0019] According to this configuration, by excluding background regions and target regions containing less important objects, the data volume of the compressed video can be reduced. This allows the target regions containing more important objects to be transmitted with high image quality within the available bandwidth. Furthermore, when receiving and processing the compressed video, high-speed processing is possible because less important information has been excluded in advance. Therefore, such compressed video is suitable for real-time processing.

[0020] (5) In any of (1) to (4) above, in the step of determining the image quality, a predetermined lower limit of image quality at which the presence of the target object can be recognized may be determined as the image quality of the target area including the target object having a priority lower than a predetermined priority.

[0021] According to this configuration, target regions containing low-importance target objects are compressed to the lowest possible image quality at which the presence of the target objects can be recognized. Therefore, the video can be compressed while minimizing the amount of data in target regions containing low-importance target objects. While such compressed video is typically subjected to recognition processing only on target regions containing high-importance target objects, if a need arises to re-verify the video, it can be used for verification purposes, such as performing recognition processing on all target regions, including low-importance target objects. Therefore, such compressed video is suitable for storage in a storage device.

[0022] (6) In any one of (1) to (5) above, the step of compressing the video may generate the compressed video to which information on the image quality of the determined target area has been added.

[0023] With this configuration, the device that receives the compressed video adds the image quality information that was attached to the video to the expanded video, so that when a person views the expanded video, they can understand the image quality of each target area quantitatively rather than intuitively.

[0024] (7) In any one of (1) to (6) above, the step of compressing the video may generate the compressed video to which information of the target object included in the target region has been added.

[0025] With this configuration, a device that receives compressed video can efficiently perform processing on the target object (for example, target object recognition processing) based on the information on the target object added to the video.

[0026] (8) In any of (1) to (7) above, in the step of determining the image quality, the image quality of the target region may be determined when there is a change in the available bandwidth of a predetermined value or more, and the image quality of the target region determined when there is a change in the available bandwidth of a predetermined value or more may be set as the image quality of the target region when there is no change in the available bandwidth of a predetermined value or more.

[0027] When the change in available bandwidth is small, there is no need to change the amount of compressed video data. Therefore, by not changing the image quality, it is possible to keep the amount of compressed video data unchanged. This eliminates the need to perform unnecessary image quality determination processing.

[0028] (9) A video compression device according to another embodiment of the present disclosure is a video compression device that compresses video, and includes: a target area extraction unit that extracts a target area including one of multiple target objects from each image that constitutes the video; an image quality determination unit that determines the image quality of the target area based on the priority of the target object included in the extracted target area and the available bandwidth of a transmission path; a video compression unit that compresses the video based on the determined image quality of the target area; and a video transmission unit that transmits the compressed video to an outside of the video compression device via the transmission path.

[0029] This configuration includes processing units corresponding to the characteristic steps in the above-described video compression method, and therefore the video compression device can achieve the same functions and effects as the above-described video compression method.

[0030] (10) A computer program according to another embodiment of the present disclosure is a computer program for causing a computer to function as a video compression device, and causes the computer to function as a target area extraction unit that extracts a target area containing one of multiple target objects from each image that constitutes a video, an image quality determination unit that determines the image quality of the target area based on the priority of the target object contained in the extracted target area and the available bandwidth of a transmission path, a video compression unit that compresses the video based on the determined image quality of the target area, and a video transmission unit that transmits the compressed video to an outside of the video compression device via the transmission path.

[0031] This configuration allows a computer to function as the above-described video compression device, and therefore the computer program can achieve the same functions and effects as the above-described video compression device.

[0032] [Details of the Embodiments of the Present Disclosure] Hereinafter, embodiments of the present disclosure will be described with reference to the drawings. Note that each of the embodiments described below represents a specific example of the present disclosure. The numerical values, shapes, materials, components, component placement and connection configurations, steps, and step order shown in the following embodiments are examples and do not limit the present disclosure. Furthermore, among the components in the following embodiments, components not recited in independent claims are components that can be added arbitrarily. Furthermore, each figure is a schematic diagram and is not necessarily a precise illustration.

[0033] The same components are denoted by the same reference numerals, and their functions and names are also the same, so their explanations will be omitted where appropriate.

[0034] [Overall Configuration of Video Processing System] FIG. 1 is a block diagram showing the configuration of a video processing system according to an embodiment of the present disclosure.

[0035] The video processing system 1 includes a server 2 and a video compressor 3 connected to each other via a network 4 such as the Internet, and a camera 5 connected to the video compressor 3. Although only one video compressor 3 is shown in Fig. 1, a plurality of video compressors 3 may be connected to the server 2. The server 2 and the video compressor 3 are connected to the network 4 wirelessly or by wire.

[0036] The video compression device 3 compresses each image in time series contained in the video captured by the camera 5 and transmits the compressed image sequence (video) to the server 2 .

[0037] The server 2 receives compressed video from the video compression device 3 via the network 4 and decompresses the received video. The server 2 performs video processing on the decompressed video. For example, the server 2 detects the position of a target object included in the video, the circumscribing area of ​​the target object, and the like through video processing.

[0038] 2 is a block diagram showing the configuration of a video compression device according to an embodiment of the present disclosure. The video compression device 3 is connected to a camera 5 and includes a target region extraction unit 32, a bandwidth estimation unit 33, an image quality determination unit 34, a video compression unit 35, a storage device 36, and a video transmission unit 37.

[0039] The video compression device 3 may be configured as a computer system including a processor such as a CPU and a storage device 36 such as a volatile memory or a non-volatile memory. Each of the processing units 32 to 35, 37 performs its function by executing a computer program stored in the storage device 36 on the processor.

[0040] The camera 5 captures an image of a subject and outputs the image of the subject. The image is composed of a plurality of time-series images. The camera 5 may be provided inside the video compression device 3 and may be included as a component of the video compression device 3.

[0041] Fig. 3 is a diagram showing an example of an image included in a video output by the camera 5. The image shown in Fig. 3 shows a dog 11, a bicycle 12, a car 13, and a tree 14. The video is made up of a time-series of images of multiple frames.

[0042] The target area extraction unit 32 extracts a target area including any one of a plurality of target objects from each image that constitutes the video.

[0043] For example, if the unit of an image used to determine whether or not it contains a target object is a block, the target area extraction unit 32 divides the image into a plurality of blocks and determines for each block whether or not it contains a predetermined target object, thereby allowing the video compression unit 35, described below, to extract a target area to be compressed at a higher image quality than a background area, which is an area other than the target area in the image. Compressing an image at a high image quality means compressing the image so that when the image is expanded and restored, the restored image has a high image quality.

[0044] The processing of the target region extraction unit 32 will be described in detail below. Figure 4 is a diagram showing the image shown in Figure 3 divided into a plurality of blocks. Here, an example is shown in which one image is divided into 49 blocks of 7 rows and 7 columns. As shown in Figure 4, block numbers from 1 to 49 are assigned to each block in raster scan order from the top left to the bottom right of the image. However, the size and number of blocks are not limited to those shown in Figure 4.

[0045] The types of target objects that are the determination targets of the target area extraction unit 32 are, for example, four types, and the target objects of types A, B, C, and D are a person, a car, a bicycle, and a dog, respectively. The target objects of types A to D are also referred to as target objects A to D, respectively. Priorities are set for the types of target objects, with types A, B, C, and D having the highest priorities in this order. Note that the types of target objects are not limited to four.

[0046] The target region extraction unit 32 uses a learning model to determine whether each of the blocks numbered 1 to 49 contains one of the target objects A to D. The learning model is, for example, a convolutional neural network (CNN), a recurrent neural network (RNN), an autoencoder, etc. Using images of blocks containing various target objects A (hereinafter referred to as "block images"), block images containing target objects B, block images containing target objects C, and block images containing target objects D as training data, learning of target objects A, B, C, and D is carried out by a machine learning method such as deep learning, and parameters of the learning model are determined.

[0047] Specifically, the target region extraction unit 32 inputs an image composed of 49 block images into the learning model. The learning model determines whether or not each of the target objects A, B, C, and D is included in each block, and outputs the determination result. The target region extraction unit 32 obtains the determination result from the learning model.

[0048] The target region extraction unit 32 determines the region consisting of blocks including the target object A as the target region for compression processing with higher image quality than the background region. The target region extraction unit 32 similarly determines the blocks including each of the target objects B to D as the target region.

[0049] FIG. 5 is a diagram showing an example of a target region including target objects. FIG. 5 shows target regions 41B to 41D including target objects B to D, respectively. Target regions 41B and 41D include blocks within a thick solid frame, and target region 41C includes blocks within a thick dashed frame. Target region 41B is an area including target object B (a car) and includes blocks 12 to 14. Target region 41C is an area including target object C (a bicycle) and includes blocks 9, 11, 15 to 19, 22 to 26, 32, and 33. Target region 41D is an area including target object D (a dog) and includes blocks 16, 17, 22 to 24, 29 to 31, and 36 to 38.

[0050] The target area extraction unit 32 may determine that the target area containing the target object is a rectangular area. In this case, the target area extraction unit 32 determines, for each target object, the circumscribing rectangle of the block containing the target object as the target area based on the result of determining whether the target object is included. FIG. 6 is a diagram showing another example of a target area containing a target object. FIG. 6 shows target areas 41B to 41D containing target objects B to D, respectively. Target areas 41B and 41D include the blocks enclosed in the thick solid frames, and target area 41C includes the block enclosed in the thick dashed frame. Target area 41B is an area containing target object B (a car) and includes blocks 12 to 14. Target area 41C is an area containing target object C (a bicycle) and includes blocks 8 to 12, 15 to 19, 22 to 26, and 29 to 33. The target area 41D is an area including the target object D (dog), and includes blocks 15-17, 22-24, 29-31, and 36-38.

[0051] FIG. 7 is a diagram showing an example of the results of target region extraction by the target region extraction unit 32. The table shown in FIG. 7 indicates, for each block number, whether or not the block contains target objects A to D. That is, a block containing a target object is indicated by "1," and a block containing no target object is indicated by "0." For example, block 1 indicates that none of target objects A to D is contained. Block 13 indicates that target object B is contained, but target objects A, C, and D are not contained. Block 23 indicates that target objects C and D are contained, but target objects A and B are not contained. Block 37 indicates that target object D is contained, but target objects A to C are not contained. Block 49 indicates that none of target objects A to D are contained.

[0052] 2 again, the bandwidth estimation unit 33 estimates the available bandwidth (upper limit of the bandwidth available for communication) on the communication path (transmission path) between the video compression device 3 and the server 2. For example, the bandwidth estimation unit 33 may estimate the available bandwidth by transmitting a test stream to the server 2, receiving the returned test stream, measuring quality information such as the round trip time and packet loss rate, and inputting the quality information into a pre-set analysis model. However, the method for estimating the available bandwidth is not limited to the above. The bandwidth is expressed, for example, as a transmission speed in units of Mbps (Megabits per second).

[0053] For each target area extracted by the target area extraction unit 32, the image quality determination unit 34 determines the image quality of the target area based on the priority of the target object included in the target area and the available bandwidth in the transmission path between the video compression device 3 and the server 2 estimated by the bandwidth estimation unit 33. The determined image quality is the image quality when compression is performed by the video compression unit 35. Specifically, the image quality determination unit 34 determines the image quality that satisfies the following two conditions:

[0054] (Condition 1) A target area including a target object with a relatively high priority is compressed with higher image quality than or the same image quality as a target area including a target object with a relatively low priority. (Condition 2) The video compressed by the video compression unit 35 can be transmitted to the server 2 with a bandwidth equal to or less than the available bandwidth. The image quality determination process by the image quality determination unit 34 will be described in detail later.

[0055] The video compression unit 35 changes the image quality for each target area based on the image quality determined by the image quality determination unit 34, and compresses the video (each image) output from the camera 5.

[0056] Compression methods include, for example, H.264 / MPEG-4 AVC, or H.265 / MPEG-H HEVC. Image quality is expressed by, for example, a quantization parameter QP. The smaller the quantization parameter QP is set when compressing an image (region), the higher the image quality of the expanded image (region), and the larger the quantization parameter QP is set to compress the image (region), the lower the image quality of the expanded image (region).

[0057] The video compression unit 35 adds, to the compressed video, information for identifying the image quality of a target region of each image constituting the compressed video. That is, the video compression unit 35 adds, to the compressed video, information for identifying the image quality of each block of each image constituting the compressed video. For example, the video compression unit 35 adds, to the compressed video, information associating a block number with a quantization parameter QP.

[0058] The video compression unit 35 also adds, to the compressed video, information for identifying a target object included in the target area of ​​each image constituting the compressed video. That is, the video compression unit 35 adds, to the compressed video, information for identifying a target object included in each block of each image constituting the compressed video. For example, the video compression unit 35 may add, to the compressed video, information that associates a block number with name information of the target object included in that block for each block. The video compression unit 35 may also add, to the compressed video, information that associates a block number with a number corresponding to the type of target object included in that block for each block. The video compression unit 35 stores the compressed video with the added information in the storage device 36.

[0059] The video transmission unit 37 acquires the compressed video with the added information from the video compression unit 35 and transmits the acquired compressed video to the server 2 via the network 4 .

[0060] 8 is a block diagram showing the configuration of a server according to an embodiment of the present disclosure. The server 2 includes a video receiving unit 21, a video decompression unit 22, and a video processing unit 23.

[0061] The server 2 may be configured as a computer system including a processor such as a CPU and a storage device such as a volatile memory or a non-volatile memory. Each of the processing units 21 to 23 performs its function by executing a computer program stored in the storage device on the processor.

[0062] The video receiving unit 21 receives compressed video from the video compression device 3 via the network 4 .

[0063] The video decompression unit 22 decompresses the compressed video received by the video receiving unit 21 to restore the original video.

[0064] The video processing unit 23 performs predetermined video processing on the decompressed video. For example, the video processing unit 23 detects a circumscribed rectangular area of ​​an object included in each image constituting the video. The video processing unit 23 may also perform region segmentation processing to extract the area of ​​an object included in an image on a pixel-by-pixel basis. Furthermore, the video processing unit 23 may also perform skeleton estimation processing to estimate the skeleton of an object included in an image. The server 2 may transmit the result of the video processing by the video processing unit 23 to the video compression device 3.

[0065] [Processing Procedure of the Video Compression Device] FIG. 9 is a flowchart showing an example of the processing procedure executed by the video compression device. The target area extraction unit 32 determines whether or not each block in an image output from the camera 5 contains target objects A to D, and extracts a target area containing each of the target objects A to D (step S1). For example, suppose the target area extraction unit 32 determines that the block being determined contains target object C. In this case, the target area extraction unit 32 extracts the block being determined as a target area containing target object C. Also, suppose the target area extraction unit 32 determines that the block being determined contains target objects A and B. In this case, the target area extraction unit 32 extracts the block being determined as a target area containing target object A, which has a high priority. Also, suppose the target area extraction unit 32 determines that the block being determined does not contain a target object. In this case, the target area extraction unit 32 extracts the block being determined as a background area. By performing this target area extraction process, each block is classified as a target area containing one of the target objects A to D or a background area.

[0066] The bandwidth estimation unit 33, the image quality determination unit 34, and the video compression unit 35 determine the image quality of the target region including the target objects A to D and the background region (step S2).

[0067] 10 is a flowchart showing details of the image quality determination process (step S2 in FIG. 9). The bandwidth estimation unit 33 estimates the available bandwidth in the communication path between the video compression device 3 and the server 2 (step S11).

[0068] The image quality determination unit 34 determines the level of the available bandwidth estimated by the bandwidth estimation unit 33 (step S12). The level of the available bandwidth is assumed to be determined in advance. For example, the image quality determination unit 34 determines the available bandwidth to be a high level when it is equal to or greater than a, a medium level when it is less than a and equal to or greater than b, and a low level when it is less than b. Here, a and b are predetermined values, and a>b.

[0069] When the available bandwidth level is high (high in step S12), the image quality determination unit 34 sets a quantization parameter QP of image quality level 1 as the quantization parameter QP for compressing the target region including any of the target objects A to D, and sets a quantization parameter QP of image quality level 4 for the background region (step S13). Here, the image quality levels include image quality level 1, image quality level 2, image quality level 3, and image quality level 4 in descending order of image quality. Each image quality level is associated with a quantization parameter QP, and the quantization parameter QP decreases in the order of image quality level 1, image quality level 2, image quality level 3, and image quality level 4. For example, the quantization parameters QP for image quality level 1, image quality level 2, image quality level 3, and image quality level 4 are 30, 35, 40, and 50, respectively.

[0070] If the available bandwidth level is medium (medium in step S12), the image quality determination unit 34 sets a quantization parameter QP of image quality level 2 for the target region including any of the target objects A to D, and sets a quantization parameter QP of image quality level 4 for the background region (step S14).

[0071] If the available bandwidth level is low (low in step S12), the image quality determination unit 34 sets a quantization parameter QP of image quality level 3 for the target region including any of the target objects A to D, and sets a quantization parameter QP of image quality level 4 for the background region (step S15).

[0072] Based on the quantization parameter QP set in any one of steps S13 to S15, the video compression unit 35 estimates the amount of data to be obtained when the image output from the camera 5 is compressed (step S16). As an example, the video compression unit 35 refers to a data table indicating, for each quantization parameter QP, the average amount of data to be obtained after one block image is quantized and compressed using that quantization parameter QP, and estimates the amount of data to be obtained after compression of all block images, thereby estimating the amount of data to be obtained for one frame of image.

[0073] For example, the number of blocks in the target region including target object A, the target region including target object B, the target region including target object C, the target region including target object D, and the background region are assumed to be NA, NB, NC, ND, and NE, respectively, and all blocks include zero or one target object. Furthermore, the quantization parameters QP used when compressing the target region including target object A, the target region including target object B, the target region including target object C, the target region including target object D, and the background region are assumed to be QPA, QPB, QPC, QPD, and QPE, respectively. Furthermore, the average data volume of one block image after compressing the block image with the quantization parameters QPA, QPB, QPC, QPD, and QPE is assumed to be DA, DB, DC, DD, and DE. In this case, the video compression unit 35 estimates the data volume of one frame image after compression to be (NA x DA + NB x DB + NC x DC + ND x DD + NE x DE).

[0074] The video compression unit 35 estimates the amount of compressed video data per second by multiplying the amount of compressed data for one frame of image by the number of frames contained per second (for example, 30).

[0075] The image quality determination unit 34 compares the available bandwidth estimated in step S11 with the data volume of the compressed video estimated in step S16 to determine whether a bandwidth shortage will occur when transmitting the compressed video to the server 2 (step S17). For example, the image quality determination unit 34 may determine that a bandwidth shortage will occur if the data volume of the compressed video per second exceeds the available bandwidth. Alternatively, the image quality determination unit 34 may determine that a bandwidth shortage will occur if the data volume obtained by adding a predetermined margin (positive value) to the data volume of the compressed video per second exceeds the available bandwidth. In this way, it is possible to determine whether a bandwidth shortage will occur, taking into account cases where the available bandwidth fluctuates.

[0076] If it is determined that a bandwidth shortage will occur (YES in step S17), the image quality determination unit 34 resets the quantization parameters QP by increasing the quantization parameters QP (decreasing image quality) in order from the quantization parameters QP set for the target regions including the target objects with the lowest priority (step S18). Then, the process from step S16 onward is repeated. The amount by which the quantization parameters QP are changed may be a predetermined value (e.g., 2). For example, assume that in step S13, the quantization parameters QP for the target objects A to D are set to 30, corresponding to image quality level 1. The image quality determination unit 34 increases the quantization parameter QP for the target region including the target object D with the lowest priority by 2, changing it to 32.

[0077] If the bandwidth shortage cannot be resolved by simply increasing the quantization parameter QP of the target object D, the image quality determination unit 34 increases the quantization parameter QP for the target objects C, B, and A in that order until the bandwidth shortage is resolved. For example, the image quality determination unit 34 changes the quantization parameter QP for the target regions including each of the target objects C, B, and A to 32 in that order.

[0078] If the bandwidth shortage is still not resolved, the image quality determination unit 34 similarly increases the quantization parameter QP further until the bandwidth shortage is resolved, in the order of the target objects D, C, B, and A. For example, the image quality determination unit 34 changes the target regions including the target objects D, C, B, and A to 34 in order.

[0079] If it is determined that a bandwidth shortage will not occur (NO in step S17), the image quality determination unit 34 reduces the set quantization parameters QP (increasing image quality) by sequentially decreasing the quantization parameters QP set for the target regions including the target objects with the highest priority (step S19). Here, the amount by which the quantization parameters QP are changed may be a predetermined value (e.g., 1). For example, suppose that in step S13, the quantization parameter QP corresponding to image quality level 1 for the target objects A to D is set to 30. The image quality determination unit 34 reduces the quantization parameter QP for the target region including the target object A with the highest priority by 1, changing it to 29.

[0080] Based on the quantization parameter QP set in step S19, the video compression unit 35 estimates the amount of data to be generated when the video output from the camera 5 is compressed (step S20). The process of step S20 is the same as the process of step S16.

[0081] After step S20, the image quality determination unit 34 compares the available bandwidth estimated in step S11 with the data volume of the compressed video estimated in step S20 to determine whether or not a bandwidth shortage will occur when transmitting the compressed video to the server 2 (step S21). The process of step S21 is the same as the process of step S17. If it is determined that a bandwidth shortage will not occur (NO in step S21), the process returns to step S19.

[0082] If it is determined that a bandwidth shortage will occur (YES in step S21), the image quality determination unit 34 returns the value of the quantization parameter QP of the target region including the target object last processed in step S19 to the value before the change (step S22). For example, if the last process performed in step S19 was to change the quantization parameter QP of the target region including the target object A from 30 to 29, the image quality determination unit 34 returns the quantization parameter QP from 29 to 30.

[0083] By the processing of steps S11 to S22 shown in FIG. 10, the quantization parameter QP corresponding to the image quality of the target region including the target objects A to D and the background region is determined.

[0084] 9 again, the video compression unit 35 compresses the video output from the camera 5 based on the set quantization parameter QP (step S3). The video compression unit 35 adds information for identifying the image quality of the target region to the compressed video (step S4).

[0085] The video compression unit 35 adds information for identifying the target object included in the target region to the compressed video (step S5).

[0086] The video compression unit 35 writes the compressed video with this information added to the storage device 36 (step S6).

[0087] The video transmission unit 37 receives the compressed video from the video compression unit 35 and transmits it to the server 2 (step S7). Note that the processing of step S6 and the processing of step S7 may be executed in parallel. The video compression device 3 performs the processing shown in FIG. 9 for each image constituting the video.

[0088] 2 may be, for example, an in-vehicle device installed in a vehicle (mobile object) such as an automobile or motorcycle. For example, the video compression device 3 compresses video of the area ahead of the vehicle captured by a camera 5 and transmits the compressed video to a server 2. The server 2 decompresses the compressed video, detects target objects based on the decompressed video through video processing, and transmits the detection results to the video compression device 3. The in-vehicle device installed in the vehicle performs at least one of remote monitoring and remote control of the vehicle based on the target object detection results obtained by the server 2. In other words, the compressed video is used for at least one of remote monitoring and remote control of the mobile object.

[0089] In this case, the priority of the target object is determined based on the degree of influence of the moving object on other people. In other words, if other people are the target objects, the higher the degree of influence the moving object will have on other people if it collides with them, the higher the priority will be. For example, target object A is a pedestrian, target object B is a passenger car, target object C is a truck, and target object D is a traffic light.

[0090] By setting the priority of the type of target object in this way, the video compression process is executed so that the image quality at the time of decompression is improved for objects (other people) that are more affected by the moving object.

[0091] [Application Example 2 of the Embodiment] As in Application Example 1 of the embodiment, the video compression device 3 may be an in-vehicle device installed in a mobile object such as an automobile. Furthermore, the priority of a target object may be determined based on the degree of impact of a collision between a mobile object and the target object or the usefulness of information collected from the target object. For example, the priority of a target object with a high degree of impact in the event of a collision may be set equal to or higher than the priority of a target object for which the information provided by the target object is highly useful. Furthermore, the higher the degree of impact of a collision, the higher the priority of the target object. Furthermore, the higher the usefulness of the information provided by the target object, the higher the priority of the target object. For example, target object A is a pedestrian, vehicle, or traffic signal, target object B is a road sign, target object C is a barricade or traffic cone, and target object D is a store sign or road surface.

[0092] [Application Example 3 of the Embodiment] The type of a target object may be determined according to the size of the object in the image. For example, target object A may be a small-sized object, target object B may be a medium-sized object, and target object C may be a large-sized object. Each size is assumed to be predetermined. This allows the video compression device 3 to perform video compression processing such that the smaller the object, the better the image quality when decompressed.

[0093] Note that target object A may be a large-sized object, target object B may be a medium-sized object, and target object C may be a small-sized object.

[0094] Effect of the Embodiment As described above, according to the embodiment of the present disclosure, it is possible to adjust the image quality of a target region based on the priority of the target object and the available bandwidth of the transmission path. In other words, the image quality of a target region can be determined so that the target region containing a target object with a higher priority is decompressed with higher image quality and the compressed video is not transmitted to the transmission path in excess of the available bandwidth. Therefore, even if the available bandwidth of the transmission path used for communication fluctuates, it is possible to transmit a video including a high-quality region of interest.

[0095] Furthermore, the target region is extracted by determining whether or not each block that makes up the image contains a target object. This allows for faster extraction of the target region than when extracting the target region from an image that is not divided into blocks.

[0096] The available bandwidth indicates the upper limit of the available bandwidth. Therefore, the image quality of the target area can be determined so that the target area containing the target object with higher priority is decompressed with higher image quality, and the compressed image is not sent to the transmission path exceeding the available bandwidth. This allows the data volume of the compressed image to be maximized.

[0097] Furthermore, when the video compression device 3 is installed on a moving body, a higher priority is set for a target object that will be more affected in the event of a collision with the moving body. This makes it possible to remotely monitor or remotely control the moving body so that a collision can be avoided more easily for a target object that is more likely to be affected in the event of a collision. For example, when a moving body approaches a pedestrian who is most likely to be affected in the event of a collision, remote control can be performed to stop the moving body, etc.

[0098] Furthermore, a higher priority can be set for a target object that is more important for avoiding collisions with a moving object. For example, avoiding collisions with pedestrians is more important than avoiding collisions with billboards. Therefore, the image quality of a target area including pedestrians can be set higher than the image quality of a target area including roadside billboards. This allows for control, such as stopping a moving object, to avoid collisions with pedestrians even when the available bandwidth is small. Furthermore, a higher priority can be set for a target object whose information is more useful for remote monitoring or remote control of a moving object. For example, information obtained from a traffic light is more useful for remote monitoring or remote control of a moving object than information obtained from a billboard. Therefore, the image quality of a target area including a traffic light can be set higher than the image quality of a target area including a roadside billboard.

[0099] Furthermore, the compressed video is provided with information about the image quality of the target area. Therefore, when the server 2 receives the compressed video, it adds the image quality information that was added to the compressed video to the decompressed video, so that when a person views the decompressed video, they can understand the image quality of each target area quantitatively, rather than just intuitively.

[0100] Furthermore, information about the target object included in the target region is added to the compressed video, so that the server 2 that receives the compressed video can efficiently process the target object (for example, recognize the target object) in units of blocks based on the information about the target object added to the video.

[0101] In the above-described embodiment, all block images constituting a video (image) are compressed. In contrast, in Modification 1, the video is compressed by excluding a background region, which is a region other than the target region, and a target region composed of block images containing target objects with a priority lower than a predetermined priority.

[0102] For example, the image quality determination unit 34 of the video compression device 3 determines the image quality by compressing the video while excluding the target region including the object D, which has the lowest priority, and the background region from the compression targets. For example, the image quality determination unit 34 estimates the data volume of the compressed video by assuming that the data volume of the compressed block images of the target region including the object D and the background region is a constant value (e.g., the above-mentioned DD = DE = 0), and determines whether a bandwidth shortage will occur by comparing the estimated data volume with the available bandwidth. As in the first embodiment, the image quality determination unit 34 repeats the above determination process and increases or decreases the image quality of the object A to C. In this way, the best image quality is determined for the target region including the object A to C, such that the data volume of the compressed video is equal to or less than the available bandwidth.

[0103] According to the first modification, the data volume of the compressed video can be reduced by excluding background regions and target regions including less important objects. This allows the target regions including more important objects to be transmitted with high image quality within the available bandwidth. Furthermore, when the compressed video is received and processed, high-speed processing is possible because less important information has been excluded in advance. Therefore, such compressed video is suitable for real-time processing.

[0104] 10, in the above embodiment, all target regions are set to the same image quality level according to the band level. However, it is not necessary to set all target regions to the same image quality level.

[0105] Fig. 11 is a flowchart showing details of the image quality determination process (step S2 in Fig. 9) according to Modification 2. The process shown in Fig. 11 includes steps S31 to S33 instead of steps S13 to S15 shown in Fig. 10. The processes of steps S11 and S16 to S22 are the same as those shown in Fig. 10.

[0106] If the available bandwidth level is high (high in step S12), the image quality determination unit 34 sets a quantization parameter QP of image quality level 1 for the target region including any of the target objects A to D, and sets a quantization parameter QP of image quality level 4 for the background region (step S31).

[0107] If the available bandwidth level is medium (medium in step S12), the image quality determination unit 34 sets a quantization parameter QP of image quality level 1 for the target region including any of the target objects A to B, sets a quantization parameter QP of image quality level 2 for the target region including any of the target objects C to D, and sets a quantization parameter QP of image quality level 4 for the background region (step S32).

[0108] If the available bandwidth level is low (low in step S12), the image quality determination unit 34 sets a quantization parameter QP of image quality level 1 for the target region including target object A, sets a quantization parameter QP of image quality level 2 for the target region including target object B, sets a quantization parameter QP of image quality level 3 for the target region including any of target objects C to D, and sets a quantization parameter QP of image quality level 4 for the background region (step S32).

[0109] According to Modification 2, for example, a target region including a target object A is initially set to a quantization parameter QP of image quality level 1. Therefore, a target region including a target object with a high priority is compressed with higher image quality than in the above-described embodiment.

[0110] <Modification 3> In the above embodiment, when the bandwidth used by the compressed video exceeds the available bandwidth, the image quality is lowered in order from the target region including the target object type with the lowest priority.

[0111] In the third modification, when the bandwidth used by the compressed video exceeds the available bandwidth, the image quality is lowered in order from the target area containing the object of the lowest priority type, as in the above embodiment, except that the image quality of the target area containing the important target object is fixed without being lowered.

[0112] Fig. 12 is a flowchart showing details of the image quality determination process (step S2 in Fig. 9) according to Modification 3. The process shown in Fig. 12 includes step S41 instead of step S18 shown in Fig. 10. The processes of steps S11 to S17 and S19 to S22 are the same as those shown in Fig. 10.

[0113] If it is determined that a bandwidth shortage will occur (YES in step S17), the image quality determination unit 34 increases the set quantization parameters QP (decreases image quality) in order from the quantization parameter QP set for the target region including the target object with the lowest priority, and resets the quantization parameters QP (step S41). At this time, the image quality determination unit 34 changes the quantization parameters QP for the target regions including target objects B to D, but does not change the quantization parameter QP for the target region including target object A. Here, the amount by which the quantization parameters QP are changed is a predetermined value (for example, 2).

[0114] For example, in step S13, assume that the quantization parameter QP corresponding to image quality level 1 is set to 30 for the target objects A to D. The image quality determination unit 34 increases the quantization parameter QP of the target region including the target object D, which has the lowest priority among the target objects B to D, by 2, to change it to 32.

[0115] If the bandwidth shortage cannot be resolved by simply increasing the quantization parameter QP of the target object D, the image quality determination unit 34 increases the quantization parameter QP for the target objects C and B in that order until the bandwidth shortage is resolved. For example, the image quality determination unit 34 changes the quantization parameter QP of the target regions including the target objects C and B to 32 in that order.

[0116] If the bandwidth shortage is still not resolved, the image quality determination unit 34 similarly increases the quantization parameter QP further until the bandwidth shortage is resolved, in the order of the target objects D, C, and B. For example, the image quality determination unit 34 changes the target regions including the target objects D, C, and B to 34 in order.

[0117] According to variant example 3, for at least the target area including the target object A with the highest priority, compressed video can be transmitted to server 2 while maintaining a constant image quality regardless of changes in communication bandwidth.

[0118] <Modification 4> In the above embodiment, the image quality is determined for each frame of an image that constitutes a video. However, it is also possible to determine an image quality that is common to a plurality of frames of images in a time series.

[0119] Fig. 13 is a flowchart showing details of the image quality determination process (step S2 in Fig. 9) according to Modification 4. The flowchart shown in Fig. 13 is the flowchart shown in Fig. 10 with steps S51 and S52 added.

[0120] Here, a common image quality is determined for multiple images included in a GOP (Group of Pictures), which is a unit of compression in a compression method such as H.264 / MPEG-4 AVC or H.265 / MPEG-H HEVC.

[0121] The image quality determination unit 34 determines whether the image to be compressed is the first picture (I-picture) of a GOP (step S51). If the image to be compressed is the first picture (YES in step S51), the processing of steps S11 to S22 is performed to determine the image quality of each target region and background region included in the first picture. The processing of steps S11 to S22 is the same as that shown in FIG. 10.

[0122] If the image to be compressed is not the first picture (NO in step S51), the image quality determination unit 34 sets the image quality of each region included in the first picture as the image quality of each region included in the image to be compressed (step S52). According to the fourth modification, the same image quality is maintained for the same region within the same GOP.

[0123] It should be noted that the image quality may be determined not for each GOP but for each predetermined time period (for example, one minute). In other words, the image quality may be determined for the first frame image of the predetermined time period, and the image quality determined for the first frame image may be maintained for the remaining frame images.

[0124] <Modification 5> In the above embodiment, the image quality is determined for each frame of an image that constitutes a video, but it is also possible to determine the image quality only when there is a change in the available bandwidth.

[0125] Fig. 14 is a flowchart showing details of the image quality determination process (step S2 in Fig. 9) according to Modification 5. The flowchart shown in Fig. 14 is the flowchart shown in Fig. 10 with steps S61 and S62 added.

[0126] The image quality determination unit 34 determines whether the available bandwidth estimated by the bandwidth estimation unit 33 has changed (step S61). For example, the image quality determination unit 34 determines that the available bandwidth has changed if the available bandwidth has changed by a predetermined value or more from the available bandwidth referenced when the image quality was last determined, and otherwise determines that the available bandwidth has not changed. Note that when compressing the first frame of video, the image quality determination unit 34 determines that the available bandwidth has changed.

[0127] If it is determined that the available bandwidth has changed (YES in step S61), the process of steps S11 to S22 is executed to determine the image quality of each region included in the image to be compressed. The process of steps S11 to S22 is the same as that shown in FIG.

[0128] If it is determined that the available bandwidth has not changed (NO in step S61), the image quality determination unit 34 sets the image quality of each region included in the image to be compressed to the image quality of each region determined the last time it was determined that the available bandwidth had changed (step S62).

[0129] According to Variation 5, if there is little change in the available bandwidth, there is no need to change the amount of data of the compressed video. Therefore, by not changing the image quality, it is possible to keep the amount of data of the compressed video unchanged. This eliminates the need to perform unnecessary image quality determination processing.

[0130] <Variation 6> In Variation 6, the image quality of a target region including a target object with a priority lower than a predetermined priority is set to a minimum image quality (hereinafter referred to as "limit image quality") at which the presence of a predetermined target object can be recognized. For example, the value of the quantization parameter QP indicating the limit image quality is 50. Here, the maximum value of the quantization parameter QP is 51.

[0131] Fig. 15 is a flowchart showing details of the image quality determination process (step S2 in Fig. 9) according to Modification 6. The flowchart shown in Fig. 15 is similar to the flowchart shown in Fig. 10, except that step S71 is added, steps S72, S73, and S74 are used instead of steps S13, S14, and S15, and steps S75 and S76 are used instead of steps S18 and S19. The processes in steps S11, S12, S16, S17, and S20 to S22 are the same as those shown in Fig. 10.

[0132] The image quality determination unit 34 sets the image quality limit to the image quality of the target region including the target object with a priority lower than that of the type C target object (that is, target object D) (step S71).

[0133] If the available bandwidth level is high (high in step S12), the image quality determination unit 34 sets the quantization parameter QP of image quality level 1 as the quantization parameter QP when compressing the target area including any of the target objects A to C (step S72).

[0134] If the available bandwidth level is medium (medium in step S12), the image quality determination unit 34 sets the quantization parameter QP of image quality level 2 to the target region including any of the target objects A to C (step S73).

[0135] If the available bandwidth level is low (low in step S12), the image quality determination unit 34 sets the quantization parameter QP of image quality level 3 for the target region including any of the target objects A to C (step S74).

[0136] If it is determined that a bandwidth shortage will occur (YES in step S17), the image quality determination unit 34 resets the quantization parameters QP by increasing (decreasing image quality) the quantization parameters QP set for the target regions including the target objects A to C in order starting from the quantization parameters QP set for the target regions including the target objects with the lowest priority (step S75). This process is the same as the process in step S41 in FIG. 12.

[0137] If it is determined that a bandwidth shortage will not occur (NO in step S17), the image quality determination unit 34 lowers (increases image quality) the quantization parameters QP set for the target regions including the target objects A to C in order from the quantization parameter QP set for the target region including the target object with the highest priority, and resets the quantization parameters QP (step S76). Here, the amount by which the quantization parameters QP are changed is a predetermined value (for example, 1).

[0138] According to this modification, a target region including a target object D of low importance is compressed to the lowest possible image quality at which the presence of the target object D can be recognized. This allows the video to be compressed while keeping the amount of data for the target region including the target object D of low importance as low as possible. For example, while recognition processing is normally performed only on the target region including the target objects A to C of high importance, such compressed video can be used for verification purposes, such as performing recognition processing on the target region including all of the target objects, including the target object D of low importance, if re-verification of the video becomes necessary. This type of compressed video is therefore suitable for storage in a storage device.

[0139] [Additional Notes] Some or all of the components constituting each of the above devices may be made up of semiconductors such as one or more system LSIs.

[0140] The above-described computer program may be recorded on a computer-readable non-volatile recording medium, such as a HDD, a CD-ROM, or a semiconductor memory, and distributed. The computer program may also be transmitted and distributed via a telecommunications line, a wireless or wired communication line, a network such as the Internet, or data broadcasting. Each of the above-described devices may be realized by multiple computers or multiple processors.

[0141] In addition, some or all of the functions of each of the above-described devices may be provided by cloud computing. That is, some or all of the functions of each device may be realized by a cloud server. Furthermore, at least some of the above-described embodiments and modifications may be combined in any manner.

[0142] The embodiments disclosed herein should be considered to be illustrative and not restrictive in all respects. The scope of the present disclosure is defined by the claims, not by the above meaning, and is intended to include all modifications within the meaning and scope equivalent to the claims.

[0143] REFERENCE SIGNS LIST 1 Video processing system 2 Server 3 Video compression device 4 Network 5 Camera 11 Dog 12 Bicycle 13 Car 14 Tree 21 Video receiving unit 22 Video decompression unit 23 Video processing unit 32 Target area extraction unit 33 Bandwidth estimation unit 34 Image quality determination unit 35 Video compression unit 36 ​​Storage device 37 Video transmission unit 41B Target area 41C Target area 41D Target area

Claims

1. A video compression method by a video compression device, comprising: extracting a target region including any one of a plurality of target objects from each image constituting the video; determining an image quality of the extracted target region based on a priority of the target object included in the extracted target region and an available bandwidth of a transmission path; compressing the video based on the determined image quality of the region of interest; transmitting the compressed video used for at least one of remote monitoring and remote control of a mobile object to an outside of the video compression device via the transmission path; A video compression method, wherein the priority is determined based on the degree of influence that the moving body will have on the target object when the moving body collides with the target object.

2. A video compression method using a video compression device, comprising: extracting a target region including any one of a plurality of target objects from each image constituting the video; determining an image quality of the extracted target region based on a priority of the target object included in the extracted target region and an available bandwidth of a transmission path; compressing the video based on the determined image quality of the region of interest; transmitting the compressed video used for at least one of remote monitoring and remote control of a mobile object to an outside of the video compression device via the transmission path; A video compression method, wherein the priority is determined based on the usefulness of information collected from the target object for the remote monitoring or remote control.

3. 3. The video compression method according to claim 1, wherein in the step of compressing the video, the video is compressed by excluding a background region that is a region other than the target region and the target region that includes the target object having a priority lower than a predetermined priority.

4. A video compression method using a video compression device, comprising: extracting a target region including any one of a plurality of target objects from each image constituting the video; determining an image quality of the extracted target region based on a priority of the target object included in the extracted target region and an available bandwidth of a transmission path; compressing the video based on the determined image quality of the region of interest; transmitting the compressed video to an outside of the video compression device via the transmission path; In the step of determining the image quality, a predetermined lower limit of image quality at which the presence of the target object can be recognized is determined as the image quality of the target region containing the target object having a priority lower than a predetermined priority.

5. 3. The video compression method according to claim 1, wherein the step of compressing the video generates the compressed video to which information about the image quality of the determined target region is added.

6. 3. The video compression method according to claim 1, wherein the step of compressing the video generates the compressed video to which information about the target object included in the target region is added.

7. 3. The video compression method of claim 1, wherein in the step of determining the image quality, the image quality of the target region is determined when there is a change in the available bandwidth of a predetermined value or more, and the image quality of the target region determined when there is a change in the available bandwidth of a predetermined value or more is set as the image quality of the target region when there is no change in the available bandwidth of a predetermined value or more.

8. A video compression device that compresses video, a target region extraction unit that extracts a target region including any one of a plurality of target objects from each image that constitutes the video; an image quality determination unit that determines image quality of the extracted target area based on the priority of the target object included in the extracted target area and an available bandwidth of a transmission path; a video compression unit that compresses the video based on the determined image quality of the target region; a video transmission unit that transmits the compressed video used for at least one of remote monitoring and remote control of a mobile object to an outside of the video compression device via the transmission path; A video compression device, wherein the priority is determined based on the degree of influence that the moving body will have on the target object when the moving body collides with the target object.

9. A video compression device for compressing video, comprising: a target region extraction unit that extracts a target region including any one of a plurality of target objects from each image that constitutes the video; an image quality determination unit that determines image quality of the extracted target area based on the priority of the target object included in the extracted target area and an available bandwidth of a transmission path; a video compression unit that compresses the video based on the determined image quality of the target region; a video transmission unit that transmits the compressed video used for at least one of remote monitoring and remote control of a mobile object to an outside of the video compression device via the transmission path; A video compression device, wherein the priority is determined based on the usefulness of information collected from the target object for the remote monitoring or the remote control.

10. A video compression device for compressing video, comprising: a target region extraction unit that extracts a target region including any one of a plurality of target objects from each image that constitutes the video; an image quality determination unit that determines image quality of the extracted target area based on the priority of the target object included in the extracted target area and an available bandwidth of a transmission path; a video compression unit that compresses the video based on the determined image quality of the target region; a video transmission unit that transmits the compressed video used for at least one of remote monitoring and remote control of a mobile object to an outside of the video compression device via the transmission path; The image quality determination unit determines a predetermined lower limit of image quality at which the presence of the target object can be recognized as the image quality of the target region including the target object having a priority lower than a predetermined priority.

11. A computer program for causing a computer to function as a video compression device, The computer a target region extraction unit that extracts a target region including any one of a plurality of target objects from each image that constitutes the video; an image quality determination unit that determines image quality of the extracted target area based on the priority of the target object included in the extracted target area and an available bandwidth of a transmission path; a video compression unit that compresses the video based on the determined image quality of the target region; and a computer program for causing the video compression device to function as a video transmission unit that transmits the compressed video used for at least one of remote monitoring and remote control of a mobile object to an outside of the video compression device via the transmission path, the computer program comprising: The priority is determined based on the degree of influence that the moving body will have on the target object when the moving body collides with the target object.

12. A computer program for causing a computer to function as a video compression device, comprising: The computer a target region extraction unit that extracts a target region including any one of a plurality of target objects from each image that constitutes the video; an image quality determination unit that determines image quality of the extracted target area based on the priority of the target object included in the extracted target area and an available bandwidth of a transmission path; a video compression unit that compresses the video based on the determined image quality of the target region; and a computer program for causing a computer to function as a video transmission unit that transmits the compressed video used for at least one of remote monitoring and remote control of a mobile object to an outside of the video compression device via the transmission path, the computer program comprising: A computer program, wherein the priority is determined based on the usefulness of information collected from the target object for the remote monitoring or remote control.

13. A computer program for causing a computer to function as a video compression device, comprising: The computer a target region extraction unit that extracts a target region including any one of a plurality of target objects from each image that constitutes the video; an image quality determination unit that determines image quality of the extracted target area based on the priority of the target object included in the extracted target area and an available bandwidth of a transmission path; a video compression unit that compresses the video based on the determined image quality of the target region; and a computer program for causing a computer to function as a video transmission unit that transmits the compressed video used for at least one of remote monitoring and remote control of a mobile object to an outside of the video compression device via the transmission path, the computer program comprising: The image quality determination unit determines a predetermined lower limit of image quality at which the presence of the target object can be recognized as the image quality of the target region including the target object having a priority lower than a predetermined priority.