Method for evaluating the amount of video information and corresponding network management system

Abstract

The present application provides a method for evaluating the amount of video information and a corresponding network management system, wherein the method comprises: obtaining a video; identifying one or more objects in the video; for each of the one or more objects: determining a probability of the object appearing in the video; and determining an information entropy of the object based on the probability of the object appearing in the video; and summing the information entropy of each object to indicate the amount of information of the video.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of video networking, and more particularly, to a method and system for analyzing information quantity in a video. BACKGROUND

[0002] For security purposes, more and more places are installed with surveillance cameras, and the coverage is also wider and wider. Nowadays, with the development of artificial intelligence technology, the image field target detection algorithm has been relatively mature, and it is possible to detect and analyze various targets appearing in the video. Many surveillance cameras have the ability of target detection, face recognition, license plate recognition, etc. However, the cost of such cameras is high, and if all the cameras are upgraded to such intelligent cameras, the cost will increase significantly. Therefore, where to install the camera, at what angle to install the camera, and which specification of camera to choose are all difficult problems faced in the camera installation layout. At present, the installation layout of the camera basically relies on the experience of technical personnel, which may lead to some cameras not meeting the expected monitoring effect after installation, and some cameras causing resource waste due to over-performance.

[0003] Therefore, it is hoped to provide a mechanism that can objectively and quantitatively evaluate whether the camera installation position is appropriate, and thereby scientifically conduct the installation layout of the surveillance camera. SUMMARY

[0004] This summary is provided to introduce some concepts in a simplified form that are further described below in the detailed description. This summary is not intended to identify key or essential features of the claimed subject matter, nor is it intended to be used to determine the scope of the claimed subject matter.

[0005] To solve the above problems, the present application provides a method and system for defining the effective information entropy size of a surveillance video, which can be used for quantitative analysis of the information quantity size of the surveillance video, for example, for solving the objective evaluation and analysis problem of the camera installation position, and the planning problem related to the camera-related network and the allocation of computing resources.

[0006] According to one aspect of the present application, a method for evaluating video information quantity is provided, comprising: obtaining a video;

[0007] identifying one or more objects in the video;

[0008] for each of the one or more objects:

[0009] determining the probability of the object appearing in the video; and

[0010] determining an information entropy of the object based on a probability of the object appearing in the video; and

[0011] summing the information entropy of each object to indicate an amount of information of the video.

[0012] According to another embodiment of the present disclosure, determining the probability of the object appearing in the video further comprises:

[0013] recording a first time of the object appearing in the video;

[0014] recording a second time of the object leaving the video;

[0015] determining a duration of the object existing in the video based on the first time and the second time; and

[0016] taking a ratio of the duration of the object existing in the video to a total duration of the video as the probability of the object appearing in the video.

[0017] According to yet another embodiment of the present disclosure, the one or more objects are identified by performing an object detection algorithm on the video.

[0018] According to a further embodiment of the present disclosure, determining the information entropy of the object based on the probability of the object appearing in the video further comprises calculating the information entropy of the object according to the following formula:

[0019]

[0020] where a is an object identified in the video, H(a) is the information entropy of object a, Pr a is an object detection confidence rate for object a, t a is a duration of object a existing in the video, and T is a total duration of the video.

[0021] According to a further embodiment of the present disclosure, further comprising:

[0022] determining a respective plurality of object detection confidence rates of the object at a plurality of times within the video; and

[0023] taking a maximum value of the plurality of object detection confidence rates as the object detection confidence rate of the object.

[0024] According to another aspect of the present disclosure, there is provided a method for planning installation positions of surveillance cameras, comprising:

[0025] obtaining captured videos of surveillance cameras installed at different positions;

[0026] evaluate a video information amount of videos captured by the monitoring cameras at the different locations through a method as recited in any of the aspects of the present application; and

[0027] determine an installation scheme of the cameras based on the video information amounts of the different locations.

[0028] According to yet another aspect of the present application, a method for allocating resources among a network of monitoring cameras is provided, comprising:

[0029] obtaining captured videos of a plurality of monitoring cameras of the network of monitoring cameras;

[0030] evaluating a video information amount of videos captured by each of the plurality of monitoring cameras through a method as recited in any of the aspects of the present application; and

[0031] determining a resource allocation among the network of monitoring cameras based on the video information amount of videos captured by each of the monitoring cameras.

[0032] According to further embodiments of the present application, the resources comprise at least one of:

[0033] network resources, computing power resources, and device hardware resources.

[0034] According to yet another aspect of the present application, a network management system of monitoring cameras is provided, comprising:

[0035] a communication unit configured to obtain captured videos of a plurality of monitoring cameras of the network of monitoring cameras installed at different locations;

[0036] a storage unit configured to store the captured videos and computer executable instructions; and

[0037] a processing unit, wherein the computer executable instructions, when executed by the processing unit, cause the processing unit to perform a method as recited in any of the aspects of the present application to evaluate a video information amount of videos captured by each of the plurality of monitoring cameras.

[0038] According to further embodiments of the present application, the computer executable instructions, when executed by the processing unit, cause the processing unit to:

[0039] determine an installation scheme of the cameras based on the video information amounts of the different locations; or

[0040] determine a resource allocation among the network of monitoring cameras based on the video information amount of videos captured by each of the monitoring cameras.

[0041] These and other features and advantages will be apparent from a reading of the following detailed description taken in conjunction with the associated drawings. It is understood that both the foregoing summary of the application and the following detailed description are merely illustrative and are intended to provide additional description both as to its structure and its methodology than the title and abstract. The above summary of the application not intended to be limiting, but rather to generally provide an understanding of the aspects of the application. BRIEF DESCRIPTION OF DRAWINGS

[0042] So that the manner in which the above recited features of the present application can be understood in detail, a brief description of the drawings is followed, followed by a detailed description of the application, illustrated by way of example with reference to the accompanying drawings. It is to be noted, however, that the appended drawings illustrate only typical aspects of this application and are therefore not to be considered limiting of its scope, for the description can admit to other equally effective aspects.

[0043] Figure 1 is a flowchart of a method for evaluating video information volume according to an embodiment of the application.

[0044] Figure 2 is a flowchart of a method for planning surveillance camera installation locations according to an embodiment of the application.

[0045] Figure 3 is a flowchart of a method for allocating resources among a network of surveillance cameras according to an embodiment of the application.

[0046] Figure 4 is a schematic diagram of a surveillance camera network management system according to an embodiment of the application.

[0047] Figures 5A-5D is a schematic diagram of key frame pictures of surveillance video according to an embodiment of the application.

[0048] Figure 6 is a flowchart of a method for evaluating video information volume according to an embodiment of the application.

[0049] In the drawings, the drawings are not drawn to scale. DETAILED DESCRIPTION

[0050] The application is herein described, by way of example only, with reference to the accompanying drawings, wherein:

[0051] In the description of the present application, it should be noted that, unless otherwise specified, the meaning of "a plurality of" is more than two; the orientation or positional relationship indicated by the terms "upper", "lower", "left", "right", "inner", "outer" and the like only indicates or implies the device or element referred to must have a particular orientation, be constructed and operated in a particular orientation, and therefore cannot be understood as a limitation on the present application. In addition, the terms "first", "second", "third" and the like are only for descriptive purposes and cannot be understood as indicating or implying relative importance. "Vertical" is not strictly vertical, but within the allowable range of error. "Parallel" is not strictly parallel, but within the allowable range of error.

[0052] The orientation words appearing in the following description are the directions shown in the drawings, and are not a limitation on the specific structure of the present application. In the description of the present application, it should be noted that, unless otherwise specified and limited, the terms "mounting", "connecting", "connecting" should be understood broadly, for example, it can be fixedly connected, or it can be detachably connected, or integrally connected; it can be directly connected, or indirectly connected through an intermediate medium. For those skilled in the art, the specific meaning of the above terms in the present application can be understood according to the specific circumstances.

[0053] In this paper, the term "embodiment" means that the specific features, structures or characteristics described in conjunction with the embodiment can be included in at least one embodiment of the present application. The phrase appears at various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment to other embodiments. Those skilled in the art explicitly and implicitly understand that the embodiments described herein can be combined with other embodiments.

[0054] In the description of the embodiments of the present application, the term "and / or" is only a description of the association relationship between the associated objects, which means that there can be three relationships, for example, A and / or B, which can represent the three cases of A alone, A and B together, and B alone. In addition, the character " / " in this paper generally represents a "or" relationship between the associated objects before and after it.

[0055] For solving the related problems of the scene using the camera, the size of the information amount can be used to decide some matters. For example, in the case of installing a limited number of cameras in a certain space, how to decide where to install these cameras, the existing solution is actually that the installer subjectively formulates the position according to experience, and the introduction of the size of the information amount can actually objectively evaluate whether the camera installed at a certain position is a better solution.

[0056] Information entropy is a basic concept of information theory, which describes the uncertainty of the occurrence of each possible event of an information source. According to the relevant research of Shannon's mathematical theory of communication, information entropy can reflect the size of information quantity. Therefore, the concept of information entropy is introduced into the field of monitoring video to evaluate the size of the information quantity of the monitoring video.

[0057] In addition, for multiple camera terminals in a specific area, the pictures taken by each camera at different time periods in a specific position are different. For the ability resources (for example, network bandwidth, storage, computing power, etc.) required to ensure the functions of the camera, the resource allocation can be decided by the information quantity of the current time period, thereby improving the resource utilization rate and making the related functions and service quality of the camera better.

[0058] Figure 1 is a flowchart of a method 100 for evaluating the information quantity of a video according to an embodiment of the present application. As shown in Figure 1 For example, the video can be obtained by a camera, such as a segment of the video captured by the camera can be randomly or according to actual needs. Then, in step 104, one or more objects in the video are identified. Specifically, one or more objects contained therein can be identified, for example, by performing a target detection algorithm on the selected segment of the video. As a non-limiting embodiment, the Yolo related algorithm, R-CNN related algorithm, etc. currently mature in academic and commercial application fields can be used to identify one or more objects contained in the video.

[0059] Next, in step 106, the probability of the occurrence of each of the identified one or more objects in the segment of the video is determined, and the information entropy of the object is determined based on the probability of the occurrence of the object in the segment of the video.

[0060] Specifically, in an embodiment, the probability of the occurrence of the object in the video can be determined by the following method: recording the first time when the object appears in the video, and recording the second time when the object leaves the video, then determining the duration of the existence of the object in the video based on the first time and the second time, for example, the difference between the first time (i.e. the time when the object appears in the video) and the second time (i.e. the time when the object leaves the video) can be taken as the duration of the existence of the object in the video. Then, the ratio of the duration of the existence of the object in the video to the total duration of the video can be taken as the probability of the occurrence of the object in the video.

[0061] In yet another embodiment, assuming that the identified object is a, the information entropy of the object can be calculated according to the following formula:

[0062]

[0063] where a is an object identified in the video, H(a) is the information entropy of the object a, Pr a is the target detection confidence rate for the object a, t a is the time length of the object a existing in the video, and T is the total time length of the video.

[0064] In a further embodiment, the target detection confidence rate Pr a of the object can be determined by, for example, determining a respective plurality of target detection confidence rates of the object at a plurality of times within the video, and then taking the maximum value of the plurality of target detection confidence rates as the target detection confidence rate of the object.

[0065] Finally, in step 108, the information entropies of each object are summed to indicate the information amount of the video. For example, the information entropies of the objects identified in the video can be determined by the method described in step 106, and then the information entropies of the objects are summed to obtain the information amount of the video.

[0066] Figure 2 is a flow chart of a method 200 for planning the installation positions of surveillance cameras according to an embodiment of the present application. As shown in Figure 2 , the method 200 starts in step 202 by obtaining the captured videos of surveillance cameras installed at different positions. Then, in step 204, the video information amounts of the videos captured by the surveillance cameras at different positions can be evaluated by, for example, the method described in Figure 1 .

[0067] In a specific embodiment, for a video captured at a position, one or more objects can be identified in the video. Then, for each of the one or more identified objects, the probability of the object appearing in the video is determined, and the information entropy of the object is determined based on the probability of the object appearing in the video. Finally, the information entropies of each of the objects identified in the video are summed to indicate the information amount of the video.

[0068] The video information amounts of the videos captured by the surveillance cameras at different positions can be determined by the above method. Finally, in step 206, the installation scheme of the cameras can be determined based on the video information amounts at different positions.

[0069] In a non-limiting embodiment, when determining how to arrange the surveillance cameras of a site, a number of surveillance cameras can be installed at different positions of the site, and then the videos captured by each camera at a certain time period can be randomly or on-demand extracted. Then, the video information amounts of the videos captured by the cameras at different positions can be evaluated by, for example, the method described in Figure 1The method for evaluating the video information quantity described in the detailed description can be used to determine the information quantity size of each video. Finally, based on the size of the information quantity, the installation scheme of the camera can be arranged according to the actual needs. For example, in the case where it is expected that the camera can capture more objects, a certain threshold value can be set, and in the case where the information quantity is greater than or equal to the threshold value, the monitoring camera at the corresponding position is retained, and in the case where the information quantity is less than the threshold value, the monitoring camera at the corresponding position is removed or turned off. The videos of all positions can also be sorted, and the cameras at positions with larger information quantities are retained, and the monitoring cameras at positions with smaller information quantities are removed or turned off, and the like. Of course, according to actual needs, a camera can also be installed at a position with a smaller information quantity.

[0070] It can be appreciated that the above method can also be applied in the case where there is only one camera. For example, the camera can be installed at different positions of a place in sequence, and then videos at different positions can be obtained respectively. In order to facilitate comparison, videos of a suitable time period can be selected for analysis, for example, videos of the same time period on different dates can be selected. Then the information quantities of the videos are analyzed, and finally, for example, the position with the largest, smallest or satisfying a certain condition information quantity can be selected to install the camera.

[0071] Figure 3 is a flowchart of a method 300 for allocating resources among a network of monitoring cameras according to an embodiment of the present application. As shown in Figure 3 The method 300 starts at step 302, and videos captured by a plurality of monitoring cameras of a network of monitoring cameras can be obtained. Then, at step 304, the video information quantities of the videos captured by the monitoring cameras at different positions can be evaluated by a method as described with reference to Figure 1 The video information quantity of the video captured by the monitoring camera at a certain position can be evaluated by a method as described with reference to

[0072] In one specific embodiment, for a video captured at a certain position, one or more objects can be identified in the video. Then, for each of the one or more identified objects, the probability of the object appearing in the video is determined, and the information entropy of the object is determined based on the probability of the object appearing in the video. Finally, the information entropies of each of the one or more identified objects in the video are summed to indicate the information quantity size of the video.

[0073] The video information quantity of the video captured by the monitoring camera at a certain position can be evaluated by a method as described with reference to

[0074] In one embodiment, the resources to be allocated can include at least one of: network resources, computing power resources, and device hardware resources. For example, for a video with a large amount of information, more resources can be allocated to a surveillance camera at the location. Conversely, for a video with a small amount of information, fewer resources can be allocated to a surveillance camera at the location, and so on.

[0075] Figure 4 is a schematic diagram of a surveillance camera network management system 400 according to an embodiment of the present application. As shown in Figure 4 , the surveillance camera network management system 400 can include a communication unit 402, a storage unit 404, and a processing unit 406.

[0076] The communication unit 402 can be configured to obtain captured videos of a plurality of surveillance cameras in a surveillance camera network. The storage unit 404 can be configured to store the captured videos and computer executable instructions. The processing unit 406 can be configured to, when executing the stored computer executable instructions, perform evaluation of video information amount of a video captured by each of the plurality of surveillance cameras as described in the method for evaluating video information amount with reference to Figure 1 .

[0077] In one specific embodiment, the processing unit 406 can be configured to, for a certain captured video, first identify one or more objects in the video. Then, for each of the identified one or more objects, determine a probability of the object appearing in the video segment, and determine an information entropy of the object based on the probability of the object appearing in the video segment. Finally, sum the information entropy of each of the identified objects in the video to indicate the information amount of the video.

[0078] In further embodiments, the processing unit 406 can be configured to determine a camera installation scheme based on the video information amount of different locations (as described in the method with reference to Figure 2 ), or determine resource allocation among the surveillance camera network based on the video information amount of the video captured by each of the surveillance cameras (as described in the method with reference to Figure 3 .

[0079] Figures 5A-5D is a schematic diagram of a key frame picture of a surveillance video according to an embodiment of the present application. For ease of understanding, as a non-limiting embodiment, reference is made to Figures 5A-5D , the information entropy of a single object in a surveillance video is calculated, and the derivation of the overall information amount of the surveillance video will be given below based on this.

[0080] Figures 5A-5DThe four pictures in the figure are key frame pictures extracted from a monitoring video with a total time length T, and a woman circled in the pictures is taken as an object a for analysis.

[0081] Through video statistical analysis, it is found that the object a appears in the video picture for and disappears from the video picture for Therefore, the time length of the object a in the video is

[0082] Through artificial intelligence object detection related algorithm, the video is labeled, and the object a appears in the video for a with different confidence probabilities Pr in the time period. For example, the confidence rate of the object a at is 0.71 (not shown), the confidence rate of the object a at is 0.62 (not shown), and the confidence probabilities of the object a at the two middle time points are 0.89 and 0.90 (as shown in Figure 5B and Figure 5C ).

[0083] The maximum confidence probability (i.e., target detection confidence rate) of the object a in the time period t a is calculated as follows:

[0084]

[0085] The information entropy calculation formula given by Shannon is as follows:

[0086]

[0087] where p(x i ) is the probability of a random event X being x i .

[0088] The object detected in the monitoring video can be considered as a random event, and the ratio of the time length of the object appearing in the video to the total time length of the whole video can be defined as the probability of the object event appearing. In addition, as described above, the maximum confidence rate (i.e., target detection confidence rate) of the object has been obtained in the object detection link, and the target detection confidence rate can be used as the weight of the single object information entropy to weight the information entropy of the object.

[0089] Therefore, the single target information entropy of the object a in the monitoring video is as follows:

[0090]

[0091] Specifically, in this embodiment, we assume that the total duration T of a surveillance video is 5 min = 300 s. Taking the circled woman in the image as object a, and assuming she appears between 00:00:00 and 00:00:10, we obtain the duration t of object a's presence in the video. a The time interval is 10 seconds. Generally, object detection algorithms can be used to determine the probability (confidence rate) of an object within each frame over those 10 seconds. Alternatively, the probability (confidence rate) can be determined at predetermined time intervals, such as 1-second intervals. This would result in 11 probability values ​​(confidence rates) within the timeframe of the woman's appearance, for example: (0s: 0.71, 1s: 0.88, 2s: 0.96, ..., 10s: 0.55). The maximum confidence rate (object detection confidence rate) is calculated to be 0.96. Then, according to the single-object information entropy formula above, we can obtain:

[0092]

[0093] Figure 6 This is a flowchart of a method 600 for evaluating video information content according to an embodiment of the present invention.

[0094] In step 602, surveillance video files for a specific space and time period can be obtained. For example, the obtained video file is X, and the total duration of the corresponding surveillance video is T.

[0095] In step 604, an artificial intelligence object detection algorithm can be used to detect the video file, thereby identifying the various targets (i.e., the objects mentioned above) appearing in the video file. For example, the target set is obtained as A = {a1, a2, a3, ..., a...} n}

[0096] In step 606, the targets in the target set A (e.g., a1, a2, a3, ..., a...) can be counted. n The appearance and disappearance times of each target in the video are used to calculate the set of durations each target exists in the video. Specifically, for example, for target a... i The times it appeared and disappeared in the video were respectively and Then target a i The duration of the video is Accordingly, the set of durations corresponding to the target set A in this video is:

[0097] In step 608, analyze each target in the target set A (e.g., a1, a2, a3, ..., a...). n In the corresponding duration set T AThe confidence rate set within the target set is used to statistically calculate the maximum confidence rate set (i.e., the target detection confidence rate set) for each target in the target set. Specifically, for example, for target a... i Its duration is (Right now The set of confidence rates measured between ) is:

[0098]

[0099] Then target a i exist The maximum confidence rate (i.e., the target detection confidence rate) within the time period is:

[0100]

[0101] Accordingly, the set of maximum confidence rates (i.e., the set of target detection confidence rates) corresponding to target set A is:

[0102]

[0103] In step 610, the total duration T of the monitored video and the duration set corresponding to the target set A in the video are defined as T. A The corresponding target detection confidence rate set Pr A This allows us to determine the amount of information contained in the surveillance video. Specifically, for example, for target a... i Its information entropy is:

[0104]

[0105] Therefore, the amount of information in this surveillance video is:

[0106]

[0107] In one specific embodiment, for example, refer to Figures 5A-5D The woman drawing the circle is just one object in the video. It can be understood that there are other objects in the video that may appear at any time, such as people A, B, C, D, cats A, B, C, D, cars 1, 2, 3, 4, etc. These can all be targets or objects in the target set A.

[0108] The above describes the method and system for calculating the amount of information in surveillance video according to the present invention. This amount of information can serve as an important evaluation indicator for subsequent iterations and research on cameras, etc. The amount of information in the video is calculated based on the surveillance video recorded by the camera in a specific time period and a specific space. This can solve problems such as quantitatively evaluating the merits of camera installation locations and determining how to allocate network resources, computing power resources, etc. among multiple cameras.

[0109] Compared with the prior art, the present application has at least the following advantages: the information entropy of an image and a video is mainly used to represent the image gray scale distribution aggregation characteristics and spatial characteristics of the image or the video, and is an important parameter of image-related academic research. The present application uses the information entropy as an objective evaluation index of the information amount of a monitoring video, uses the time sequence distribution of each object appearing in a monitoring scene and the object detection probability distribution as important basis for calculating the index, detects the objects appearing continuously in the monitoring video file, uses the ratio of the object appearing time length to the total video time length to replace the probability of independent event occurrence in the information amount formula, and uses the maximum confidence rate of the object as the weight to weight the information amount size of the object, so that the information amount size of the monitoring video can be quantitatively calculated.

[0110] What has been described above includes examples of aspects of the claimed subject matter. Of course, those of ordinary skill in the art will recognize that many modifications can be made to the described examples and that such modifications fall within the scope of the disclosed subject matter. Accordingly, the disclosed subject matter is intended to embrace all such alterations, modifications, and variations which fall within the spirit and scope of the appended claims.

Claims

1. A method for evaluating video information quantity, comprising: obtaining a video; identifying one or more objects in the video; for each of the one or more objects: determining a probability of occurrence of the object in the video; and determining an information entropy of the object based on the probability of occurrence of the object in the video; and summing the information entropy of each of the one or more objects to indicate a size of the video information quantity, wherein determining the probability of occurrence of the object in the video further comprises: recording a first time of occurrence of the object in the video; recording a second time of exit of the object from the video; determining a duration of presence of the object in the video based on the first time and the second time; and taking a ratio of the duration of presence of the object in the video to a total duration of the video as the probability of occurrence of the object in the video. The one or more objects are identified by performing an object detection algorithm on the video. Determining the information entropy of the object based on the probability of occurrence of the object in the video further comprises calculating the information entropy of the object according to the following formula:

2. The method of claim 1, wherein, The method further comprises:

3. The method of claim 2, wherein, determining a respective plurality of object detection confidence rates of the object at a plurality of times within the video; and where a is an object identified in the video, H(a) is the information entropy of object a, Pr a is the target detection confidence rate for object a, t a is the length of time object a is present in the video, and T is the total length of the video.

4. The method of claim 3, wherein, taking a maximum value of the plurality of object detection confidence rates as the object detection confidence rate of the object.

5. A method for planning installation locations of surveillance cameras, comprising: obtaining captured videos of surveillance cameras installed at different locations; evaluating video information quantities of the videos captured by the surveillance cameras at the different locations by the method of any one of claims 1-4; and determining an installation scheme of the surveillance cameras based on the video information quantities of the videos at the different locations.

6. A method for allocating resources among a network of surveillance cameras, comprising: obtaining captured videos of a plurality of surveillance cameras of the network of surveillance cameras; evaluating video information quantities of the videos captured by each of the plurality of surveillance cameras by the method of any one of claims 1-4; and determining a resource allocation among the network of surveillance cameras based on the video information quantities of the videos captured by each of the plurality of surveillance cameras. The resources comprise at least one of: network resources, computing power resources, and device hardware resources.

8. A network management system of surveillance cameras, comprising: a communication unit configured to obtain captured videos of a plurality of surveillance cameras of the network of surveillance cameras installed at different locations; 7. The method of claim 6, wherein, a storage unit configured to store the captured videos and computer executable instructions; and a processing unit, wherein the computer executable instructions, when executed by the processing unit, cause the processing unit to perform the method of any one of claims 1-4 to evaluate video information quantities of the videos captured by each of the plurality of surveillance cameras. The computer executable instructions, when executed by the processing unit, cause the processing unit to: ​ ​ ​ ​ 9. The surveillance camera network management system of claim 8, wherein, ​ determine a camera installation scheme based on the video information amount of the different positions; or determine resource allocation among the network of monitoring cameras based on the video information amount of video captured by each monitoring camera.

Images