Intelligent network color image tracking monitoring method, system, terminal and storage medium

Abstract

The present application relates to an intelligent network color image tracking monitoring method, system, terminal and storage medium, and relates to the field of construction safety monitoring technology. The method includes obtaining construction monitoring information, which includes continuous multiple frames of construction image information; calling a preset color identification database, which includes color information and shape information of multiple target individuals; determining the number and position of target individuals in each frame of the construction image information according to each color in the color identification database and the construction image information; judging whether an abnormal event occurs according to the geometric shape and control area of ​​each target individual, as well as the motion state in the continuous multiple frames of the construction image information. The present application realizes real-time monitoring and analysis of the construction site, and can promptly discover abnormal events existing in the current construction site.

Description

Technical Field

[0001] The present application relates to the field of construction safety monitoring technology, and in particular to an intelligent network color image tracking monitoring method, system, terminal and storage medium. Background Art

[0002] The construction safety monitoring system is a management system that detects the overall process of construction. It can provide guarantees for the safety of construction workers, and provide real-time monitoring, data analysis, alarm push and other functions to effectively improve the safety of the construction site, management efficiency and the reliability of maintenance plans. However, due to the complexity of the geographical environment and construction personnel involved in the construction site, the diversity of on-site construction seasons and safety requirements, and the variability of materials and construction equipment as the construction progresses, it is necessary to conduct real-time safety monitoring and early warning of the construction site. Summary of the invention

[0003] In order to conduct real-time safety monitoring and early warning of construction sites, the present application proposes an intelligent network color image tracking monitoring method, system, terminal and storage medium.

[0004] In a first aspect of the present application, an intelligent network color image tracking and monitoring method is provided, the method comprising:

[0005] Acquiring construction monitoring information, wherein the construction monitoring information includes continuous multiple frames of construction image information;

[0006] Retrieving a preset color identification database, wherein the color identification database includes color information and shape information of multiple target individuals;

[0007] Determine the number and position of target individuals in each frame of the construction image information according to the color identification database and each color in the construction image information;

[0008] Whether an abnormal event occurs is determined based on the geometric shape of each target individual, the control area in which it is located, and the movement state in multiple consecutive frames of the construction image information.

[0009] By adopting the above technical solution, construction monitoring information can be obtained, and each frame of construction image information in the construction monitoring information can be analyzed to determine the position of each target individual in the construction image information. Then, based on the geometric shape of the target individual and the control area where it is located, as well as the movement state in continuous multiple frames of construction image information, it is further determined whether an abnormal event has occurred, thereby realizing real-time monitoring and analysis of the construction site, and being able to promptly discover abnormal events existing at the current construction site.

[0010] In a possible implementation manner: determining the number and position of target individuals in each frame of the construction image information according to the color identification database and each color in the construction image information includes:

[0011] Dividing a frame of the construction image information into a plurality of color blocks;

[0012] Determine, according to the color identification database, a color block whose color information is consistent with the color information of the target individual, and cluster the color blocks of the same color;

[0013] The number and location of target individuals are determined according to the color identification database and the cluster shape.

[0014] By adopting the above technical solution, it is possible to accurately determine whether there is a target individual in each frame of construction image information based on the color information and cluster shape of the color block, thereby facilitating the analysis of abnormal events at the construction site.

[0015] In a possible implementation, the color identification database further includes the color difference range and the corresponding hue of each target individual, and the color block whose color information is consistent with the color information of the target individual according to the color identification database includes:

[0016] Selecting color blocks one by one from the construction image information;

[0017] Determining a hue level according to color information of the color block;

[0018] Selecting a target individual whose hue is the same as the hue level from the color identification database and recording it as a reference target individual;

[0019] Calculating a color difference value between the color block and each of the reference target individuals according to the color information of the color block and the color information of the reference target individuals;

[0020] Determining whether the color information of the color block is consistent with the color information of the target individual according to a matching result of the color difference value between the color block and each of the reference target individuals and the color difference range of each target individual in the color identification database;

[0021] A color block whose color information is consistent with the color information of the target individual is selected.

[0022] By adopting the above technical solution, the influence of the color difference of the color information of the target individual under different natural light on the accuracy of identifying the target individual can be eliminated.

[0023] In a possible implementation manner, the calculating the color difference value between the color block and each of the reference target individuals according to the color information of the color block and the color information of the reference target individual includes:

[0024] Retrieve the preset color conversion model;

[0025] Converting the color information of the color block and the color information of the reference target individual into tristimulus values ​​respectively according to the color conversion model;

[0026] Determine the L value, A value and B value according to the tristimulus values ​​of the color block, and determine the L value, A value and B value according to the tristimulus values ​​of the reference target individual;

[0027] The color difference value is calculated according to the L value, A value and B value of the color block, the L value, A value and B value of the reference target individual and a color difference formula.

[0028] In a possible implementation, the method for establishing the color conversion model includes:

[0029] Get the RGB image of the standard color card;

[0030] Establishing a training sample set according to the RGB image of the standard color card and CIEXYZ data;

[0031] The color conversion model is established according to the training sample set based on the least square method or the Wiener estimation method.

[0032] In a possible implementation, determining whether the color information of the color block is consistent with the color information of the target individual according to the matching result of the color difference value between the color block and each of the reference target individuals and the color difference range of each target individual in the color identification database includes:

[0033] If the color difference between the color block and one of the reference target individuals is within the color difference range of the reference target individual, the matching result is a successful match, and the color information of the color block is consistent with the color information of the target individual;

[0034] If the color difference value between the color block and any of the reference target individuals does not conform to the color difference range of the corresponding reference target individual, the matching result is a matching failure, and the color information of the color block is inconsistent with the color information of the target individual.

[0035] In a possible implementation manner, determining the number and location of target individuals according to the color identification database and the cluster shape includes:

[0036] Determine whether the cluster shape of each cluster color block conforms to the shape information of the target individual in the color identification database;

[0037] If the cluster shape matches the shape information of the target individual in the color identification database, the cluster color block is determined as a target individual;

[0038] Count the number of clustered color blocks that meet the conditions and record them as the number of target individuals;

[0039] The color block number occupied by the qualified clustered color block is recorded as the position of the target individual.

[0040] By adopting the above technical solution, clustered color blocks that are not target individuals in clustered color blocks of the same color can be excluded, thereby improving the accuracy of identifying the target individual.

[0041] In a second aspect of the present application, an intelligent network color image tracking and monitoring system is provided, the system comprising:

[0042] An acquisition module, used to acquire construction monitoring information, wherein the construction monitoring information includes continuous multiple frames of construction image information;

[0043] A calling module, used to call a preset color identification database, wherein the color identification database includes color information and shape information of multiple target individuals;

[0044] a determination module, configured to determine the number and position of target individuals in each frame of the construction image information according to the color identification database and each color in the construction image information; and

[0045] The judgment module is used to judge whether an abnormal event occurs based on the geometric shape and the controlled area of ​​each target individual and the movement state in multiple consecutive frames of the construction image information.

[0046] In a third aspect of the present application, a smart terminal is provided. The smart terminal includes a memory and a processor. The memory stores a computer program that can be loaded by the processor and execute the above-mentioned smart network color image tracking and monitoring method.

[0047] In a fourth aspect of the present application, a computer-readable storage medium is provided, storing a computer program that can be loaded by a processor and execute any of the above-mentioned intelligent network color image tracking and monitoring methods.

[0048] In summary, the present application includes at least one of the following beneficial technical effects:

[0049] In the present application, construction monitoring information can be obtained, and each frame of construction image information in the construction monitoring information can be analyzed to determine the position of each target individual in the construction image information. Then, based on the geometric shape of the target individual and the controlled area where it is located, as well as the movement state in continuous multiple frames of construction image information, it is further determined whether an abnormal event has occurred, thereby realizing real-time monitoring and analysis of the construction site, and being able to promptly discover abnormal events existing at the current construction site. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 It is a flowchart of an intelligent network color image tracking and monitoring method according to one embodiment of the present application.

[0051] Figure 2 It is a system schematic diagram of an intelligent network color image tracking and monitoring system according to one embodiment of the present application.

[0052] Figure 3 It is a schematic diagram of the structure of a smart terminal according to one embodiment of the present application.

[0053] In the figure, 21, acquisition module; 22, call module; 23, determination module; 24, judgment module; 301, CPU; 302, ROM; 303, RAM; 304, bus; 305, I / O interface; 306, input part; 307, output part; 308, storage part; 309, communication part; 310, drive; 311, removable medium. DETAILED DESCRIPTION

[0054] The present application is further described in detail below in conjunction with the accompanying drawings.

[0055] This specific embodiment is merely an explanation of the present application and is not a limitation of the present application. After reading this specification, those skilled in the art may make modifications to the present embodiment without any creative contribution as needed, but such modifications are protected by the patent law as long as they are within the scope of the claims of the present application.

[0056] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0057] In addition, the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article, unless otherwise specified, generally means that the associated objects before and after are in an "or" relationship.

[0058] The embodiment of the present application provides an intelligent network color image tracking and monitoring method, which is applied to a construction site. It can monitor the construction site in real time and analyze the monitoring video to determine whether any abnormal events have occurred at the construction site, thereby promptly discovering abnormal events at the current construction site.

[0059] In order to achieve real-time monitoring of the construction site, multiple surveillance cameras need to be deployed at the construction site. These surveillance cameras can be connected to the video controller via the Internet or WIFI to upload video image data. In order to facilitate uploading video image data, these surveillance cameras can also be equipped with 5G modules. The video controller is connected to a terminal device with processing functions such as a computer or server. The terminal device with processing functions is used to process the video image data and display it through the control display screen.

[0060] It can be understood that in order to implement the intelligent network color image tracking monitoring method provided by this application, there are certain requirements for hardware equipment. Specifically, the monitoring camera needs to use a 1080P, 1 / 2.7 sensor, the sRGB standard of the International Electrotechnical Commission IEC, a 2.7mm to 13.5mm continuous zoom, a minimum on-site target illumination of 0.005Lux for color and 0.0005Lux for black and white, an image signal-to-noise ratio that meets the detection and recognition requirements, and Smart265 video encoding, which is conducive to the continuous and rapid transmission of video images, and is also conducive to the storage of video images. A 12V external power supply or a POE network cable is used for power supply to realize the integration of power supply, control, and data transmission of the imaging device.

[0061] Among them, the intelligent network color image tracking and monitoring method provided by the present application is executed by a terminal device with processing functions such as a computer, a server, etc.

[0062] The embodiments of the present application are further described in detail below in conjunction with the drawings in the specification.

[0063] The main process of the intelligent network color image tracking and monitoring method provided in the embodiment of the present application is described as follows.

[0064] like Figure 1 As shown:

[0065] Step S100: Acquire construction monitoring information.

[0066] The construction monitoring information is the video information of the construction site obtained by the monitoring camera, which includes continuous multi-frame construction image information. The construction image information can reflect the state of the construction site at a certain moment. By splitting the construction monitoring information, the construction image information can be obtained.

[0067] Step S200: Retrieve a preset color identification database.

[0068] Specifically, the color identification database includes color information, shape information, color difference range, hue and abnormal behavior of multiple target individuals. Among them, the target individual can be personnel, building materials or equipment. Since the abnormal events that may occur at the construction site are various, they may be abnormal events caused by personnel, or they may be abnormal events caused by building materials or equipment, so the objects that need to be identified in the construction monitoring information are also various. Usually, personnel are distinguished by the type of work, and personnel of different types of work need to wear helmets of different colors. Therefore, in the color identification database, the color information of the personnel is the color information of the helmet. For building materials and equipment, as the construction progress changes, the required building materials and equipment also need to change. When the building materials and equipment arrive at the construction site, the model of the building materials and equipment, as well as the color information, shape information, color difference range, hue and abnormal behavior are then entered into the color identification database. In the embodiment of the present application, the color identification database adopts a custom database format.

[0069] The color information of the above-mentioned target individual is presented in the form of RGB values. The color information of the target individual can be obtained by taking a photo under the D65 standard light source. The shape information is a set of shapes of the target individual at different angles, which can be obtained by taking a photo. The color difference range is the color difference range allowed for the standard color, which is the color presented by the standard color under different natural light. It can be obtained by taking a photo of the color presented by the standard color under different natural light and identifying the corresponding color information, and then calculating the color difference with the standard color. That is, when the color difference value between a color and the standard color belongs to the color difference range, the color is considered to be the same color as the standard color. The hue is the hue of the color of the target individual, which can be determined by some color classification methods. Abnormal behavior is used to determine whether an abnormal event occurs to the target individual, and abnormal behavior can be obtained based on common sense and experience.

[0070] Step S300: determining the number and position of target individuals in each frame of the construction image information according to the color identification database and each color in the construction image information.

[0071] In order to identify the target individual in the construction monitoring information, it is necessary to split the construction monitoring information into construction image information by frame, and then analyze each frame of construction image information to accurately identify the target individual. The process of analyzing each frame of construction image information is as follows:

[0072] Optionally, step S300 includes the following steps: (step S310 to step S330)

[0073] Step S310: Divide a frame of the construction image information into a plurality of color blocks.

[0074] It is understandable that when dividing a frame of construction image information, a suitable density should be selected so that each color block is a single color. When dividing a frame of construction image information, each color block can also be numbered.

[0075] Step S320: determining color blocks whose color information is consistent with the color information of the target individual according to the color identification database, and clustering color blocks of the same color.

[0076] It is worth noting that, since the construction image information presents the state of the construction site under natural light, the color information of each color block in the construction image information is also the result of the interaction between the standard color and natural light. Therefore, the color block whose color information is consistent with the color information of the target individual in this step actually refers to the color block whose color information is consistent with the color information of the target individual after eliminating the interference of natural light.

[0077] Specifically, first, color blocks need to be selected one by one from the construction image information.

[0078] In some specific embodiments, each color block may be selected according to a preset numbering sequence. Of course, the color blocks may also be selected according to other sequences.

[0079] Secondly, the hue level is determined according to the color information of the color block.

[0080] It is understandable that, since the surveillance camera used can output images in RGB color format, the color information of the color block can be determined by identifying the color of each color block. When determining the hue level according to the color information of the color block, a color classification method can be used. Specifically, the R value, G value and B value of the color included in each hue level have corresponding ranges, and the R value, G value and B value range of each hue level can be matched according to the R value, G value and B value in the color information of the color block. When the R value, G value and B value in the color information of the color block are just within the R value, G value and B value range of a certain hue level, the match is successful, and the hue level is the hue level to which the color block belongs.

[0081] In other embodiments, other methods may be used to determine the hue level of the color block.

[0082] Then, a target individual with the same hue and hue level is selected from the color identification database and recorded as a reference target individual. By matching the hue level with the hue of each target individual in the color identification database, a large number of target individuals can be screened, thereby reducing the number of target individuals that need to be compared with the color block, thereby reducing the amount of calculation and saving the computing power resources of the terminal device. After the target individuals are screened in the above manner, the color block only needs to be compared with the color information and color difference range of the reference target individual in the color identification database.

[0083] Furthermore, the color difference value between the color block and each reference target individual is calculated according to the color information of the color block and the color information of the reference target individual.

[0084] Take the calculation of the color difference between the color information of a color block and the color information of a reference target individual as an example. Specifically, the calculation method is:

[0085] Retrieve the preset color conversion model. The color conversion model is used to convert the RGB color space into the CIEXYZ color space to obtain the tristimulus values. The tristimulus values ​​are specifically X value, Y value and Z value. Among them, the X value represents the sensitivity of the human eye to red and green light, that is, the relative brightness of red light and green light. The Y value represents the sensitivity of the human eye to yellow and blue light, that is, the relative brightness of yellow light and blue light. The Z value represents the sensitivity of the human eye to purple and orange light, that is, the relative brightness of purple light and orange light.

[0086] According to the color conversion model, the color information of the color block and the color information of the reference target individual are converted into tristimulus values, that is, the color information is input into the color conversion model to obtain tristimulus values.

[0087] The L value, A value, and B value are determined based on the tristimulus values ​​of the color block, and the L value, A value, and B value are determined based on the tristimulus values ​​of the reference target individual. Among them, the L value represents the brightness of the color, and the value range is [0,100], which means from pure black to pure white; the A value represents the red-green color, and the value range is [127,-128], which means from red to green; the B value represents the yellow-blue color, and the value range is [127,-128], which means from yellow to blue. Specifically, the L value, A value, and B value can be calculated according to CIE1976LAB.

[0088] The color difference value is calculated based on the L value, A value and B value of the color block and the L value, A value and B value of the reference target individual and the color difference formula. Specifically, the difference △L between the L value of the color block and the L value of the reference target individual is calculated, the difference △A between the A value of the color block and the A value of the reference target individual is calculated, and the difference △B between the B value of the color block and the B value of the reference target individual is calculated. Then, △L, △A and △B are substituted into the color difference formula to calculate the color difference value △E. The smaller the △E value, the smaller the difference between the color of the color block and the color of the reference target individual; conversely, the larger the △E value, the greater the difference between the color of the color block and the color of the reference target individual.

[0089] Repeat the above steps to calculate the color difference between the color block and each reference target individual.

[0090] It is worth noting that the above color conversion model can be a deep learning model, and its establishment process is as follows:

[0091] First, an RGB image of a standard color card is obtained. The RGB image of a standard color card can be obtained by placing the standard color card under a D65 standard light source and photographing the standard color card using a color camera.

[0092] Then, a training sample set is established based on the RGB image of the standard color block and CIEXYZ data. CIEXYZ data is the RGB value converted by the CIE1931XYZ system.

[0093] Finally, based on the least squares method or the Wiener estimation method, a nonlinear color conversion model between RGB and XYZ is established according to the training sample set.

[0094] Whether the color information of the color block is consistent with the color information of the target individual is determined based on the matching result of the color difference value between the color block and each reference target individual and the color difference range of each target individual in the color identification database. There are two matching results of the color difference value between the color block and each reference target individual and the color difference range of each target individual in the color identification database, namely, successful matching and failed matching. When the color difference value between the color block and a certain reference target individual meets the color difference range of the reference target individual, the matching result is a successful matching. At this time, the color information of the color block is consistent with the color information of the target individual. When the color difference value between the color block and any reference target individual does not meet the color difference range of the corresponding reference target individual, the matching result is a failed matching, and at this time, the color information of the color block is inconsistent with the color information of the target individual.

[0095] Through the above method, it can be determined whether the color information of each color block is consistent with the color information of the target individual, so that it is convenient to select the color block whose color information is consistent with the color information of the target individual.

[0096] Of course, when matching the target individual whose color information is consistent with the color information of the color block from the color identification database, it is also possible to directly match the color information of all target individuals according to the color information of the color block.

[0097] When the color blocks whose color information is consistent with the color information of the target individual are determined among all the color blocks, the color blocks with the same color information are clustered.

[0098] Step S330: Determine the number and location of target individuals according to the color identification database and cluster shape.

[0099] It is understandable that a color block selected from a large number of color blocks whose color information is consistent with the color information of the target individual is not necessarily the target individual, and may also be an interference color block. Therefore, further judgment needs to be made based on the shape of the clustered color blocks.

[0100] Specifically, determine whether the cluster shape of each cluster color block conforms to the shape information of the target individual in the color identification database. Since the target individual corresponding to the color information of each cluster color block has been determined, the cluster shape of the cluster color block can be directly compared with the shape information of the target individual in the color identification database. Considering the influence of the shooting angle of the surveillance camera, when identifying the cluster shape of the cluster color block, the cluster shape may deviate from the shape of the target individual. The shape information of the target individual is a collection of the shapes of the target individual at various angles. If the cluster shape matches the shape of any angle in the shape information, the cluster color block can be considered to be the target individual. On the contrary, if the cluster shape does not match the shapes of all angles in the shape information, it is considered that the cluster color block is not the target individual.

[0101] Of course, in other embodiments, other approximate algorithms may also be used to determine whether the cluster shape of the clustered color blocks is consistent with the shape of the target individual.

[0102] According to the above method, all target individuals in each frame of construction image information can be counted to determine the number of target individuals. Since each color block in the construction image information is numbered, the position of the target individual can be determined according to the number of each color block in the clustered color blocks determined as the target individual.

[0103] It is understandable that since the monitoring area of ​​each surveillance camera is limited, when a target individual is found, the target individual can be reflected by information in three dimensions: the monitoring area of ​​the surveillance camera that captured the target individual, the color block number of each color block in the clustered color block, and the color information of the target individual.

[0104] It should be noted that in some other embodiments, the order of executing the above steps can be adjusted according to actual needs. For example, color blocks of the same color can be clustered first, and then the color information of the clustered color blocks is matched with the color identification database.

[0105] Step S400: Determine whether an abnormal event occurs based on the geometric shape of each target individual, the control area in which it is located, and the movement state in multiple consecutive frames of the construction image information.

[0106] The control area is the area that needs to be monitored at the construction site, which can be divided into safe areas and unsafe areas. The safe areas and unsafe areas can be set in advance. For abnormal events, abnormal events may occur in both unsafe areas and safe areas, so it is necessary to monitor both safe areas and unsafe areas at the same time.

[0107] Since the color identification database records the abnormal behavior of each target individual, it is possible to determine whether the abnormal behavior of the target individual is consistent with the target individual's geometric shape and the control area where it is located, as well as the motion state of the continuous multi-frame construction image information. If consistent, it means that an abnormal event has occurred. Conversely, if inconsistent, it means that no abnormal event has occurred.

[0108] In a specific example, a "green hard hat" was found in multiple consecutive frames of construction image information. It should be noted that at construction sites, the types of work are usually distinguished by the color of the hard hat. For example, hard hats are divided into blue, yellow, orange, red, green and other colors. If the control area where the construction image information where the "green hard hat" appears is located is a safe area, it is not determined to be an abnormal event. On the contrary, if the control area where the construction image information where the "green hard hat" appears is located is a non-safe area, it is determined to be an abnormal event.

[0109] When an abnormal event is determined to have occurred at the construction site through analysis of the construction monitoring information, a voice alarm or an audible and visual alarm can be issued.

[0110] It should also be noted that in order to facilitate the identification of target individuals, when selecting surveillance cameras, high-definition network cameras can be used to intelligently lock and track set color wavelengths, thereby achieving target tracking and locking within the lens.

[0111] Figure 2 An intelligent network color image tracking and monitoring system is provided in accordance with an embodiment of the present application.

[0112] The intelligent network color image tracking and monitoring method provided in the embodiment of the present application can be well applied to the above-mentioned scenarios, and can realize real-time monitoring and analysis of the construction site, and can promptly discover abnormal events existing in the current construction site.

[0113] like Figure 2 The intelligent network color image tracking and monitoring system shown includes an acquisition module 21, a call module 22, a determination module 23 and a judgment module 24, wherein:

[0114] The acquisition module 21 is used to acquire construction monitoring information, wherein the construction monitoring information includes continuous multiple frames of construction image information.

[0115] The retrieval module 22 is used to retrieve a preset color identification database, wherein the color identification database includes color information and shape information of multiple target individuals.

[0116] The determination module 23 is used to determine the number and position of target individuals in each frame of the construction image information according to the color identification database and each color in the construction image information.

[0117] The judgment module 24 is used to judge whether an abnormal event occurs according to the geometric shape and the controlled area of ​​each target individual and the movement state in the continuous multiple frames of the construction image information.

[0118] This embodiment is only one possible implementation method and does not limit other possible implementation methods.

[0119] Figure 3 A schematic diagram of the structure of an intelligent terminal suitable for implementing the embodiments of the present application is shown.

[0120] like Figure 3 As shown, the intelligent terminal includes a central processing unit (CPU) 301, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 302 or the program loaded from the storage part to the random access memory (RAM) 303. In the RAM 303, various programs and data required for system operation are also stored. The CPU 301, ROM 302 and RAM 303 are connected to each other through a bus 304. An input / output (I / O) interface 305 is also connected to the bus 304.

[0121] The following components are connected to the I / O interface 305: an input section 306 including a keyboard, a mouse, etc.; an output section 307 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 308 including a hard disk, etc.; and a communication section 309 including a network interface card such as a LAN card, a modem, etc. The communication section 309 performs communication processing via a network such as the Internet. A drive 310 is also connected to the I / O interface 305 as needed. A removable medium 311, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 310 as needed, so that a computer program read therefrom is installed into the storage section 308 as needed.

[0122] In particular, according to an embodiment of the present application, the above reference flow chart Figure 1 The described process can be implemented as a computer software program. For example, an embodiment of the present application includes a computer program product, which includes a computer program carried on a machine-readable medium, and the computer program contains program code for executing the method shown in the flow chart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 309, and / or installed from the removable medium 311. When the computer program is executed by the central processing unit (CPU) 301, the above-mentioned functions defined in the system of the present application are executed.

[0123] It should be noted that the computer-readable medium shown in the present application may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In the present application, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, in which a computer-readable program code is carried. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, optical cable, RF, etc., or any suitable combination of the above.

[0124] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the aforementioned module, a program segment or a part of a code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0125] The units or modules involved in the embodiments described in the present application may be implemented by software or hardware. The units or modules described may also be set in a processor. For example, they may be described as: a processor includes: an acquisition module 21, a retrieval module 22, a determination module 23, and a judgment module 24. The names of these units or modules do not, in some cases, constitute limitations on the units or modules themselves. For example, the acquisition module 21 may also be described as a "module for acquiring construction monitoring information."

[0126] As another aspect, the present application further provides a computer-readable storage medium, which may be included in the intelligent terminal described in the above embodiment; or may exist independently and not be assembled into the intelligent terminal. The above computer-readable storage medium stores one or more programs, and when the above programs are used by one or more processors to execute the intelligent network color image tracking and monitoring method described in the present application.

[0127] The above description is only a preferred embodiment of the present application and an explanation of the technical principles used. Those skilled in the art should understand that the scope of application involved in the present application is not limited to the technical solution formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the aforementioned application concept. For example, the above features are replaced with (but not limited to) technical features with similar functions applied in the present application.

Claims

1. An intelligent network color image tracking and monitoring method, characterized in that: The method comprises: Acquiring construction monitoring information, wherein the construction monitoring information includes continuous multiple frames of construction image information; Retrieving a preset color identification database, the color identification database includes color information, shape information, color difference range, color tone and abnormal behavior of multiple target individuals; wherein the target individual may be a person, building material or equipment; in the color identification database, the color information of the person is the color information of the helmet; when the building material and the equipment arrive at the construction site, the model of the building material and the equipment, as well as the color information, the shape information, the color difference range, the color tone and the abnormal behavior are entered into the color identification database; Determine the number and position of target individuals in each frame of the construction image information according to the color identification database and each color in the construction image information; Determine the number and position of target individuals in each frame of the construction image information according to the color identification database and each color in the construction image information includes: dividing a frame of the construction image information into a plurality of color blocks; determine the color blocks whose color information is consistent with the color information of the target individuals according to the color identification database, and cluster the color blocks of the same color; Determine the number and position of target individuals according to the color identification database and cluster shape; Determine the number and position of target individuals according to the color identification database and cluster shape includes: determine whether the cluster shape of each cluster color block conforms to the shape information of the target individual in the color identification database; if the cluster shape conforms to the shape information of the target individual in the color identification database, determine the cluster color block as a target individual; count the number of cluster color blocks that meet the conditions, and record it as the number of target individuals; record the color block number occupied by the cluster color blocks that meet the conditions as the position of the target individual; The color identification database also includes the color difference range and the hue of each target individual. The color block whose color information is consistent with the color information of the target individual according to the color identification database includes: selecting color blocks one by one from the construction image information; determining the hue level according to the color information of the color block; selecting a target individual whose hue is the same as the hue level from the color identification database, and recording it as a reference target individual; calculating the color difference value between the color block and each of the reference target individuals according to the color information of the color block and the color information of the reference target individual; determining whether the color information of the color block is consistent with the color information of the target individual according to the matching result of the color difference value between the color block and each of the reference target individuals and the color difference range of each target individual in the color identification database; selecting the color block whose color information is consistent with the color information of the target individual; calculating the color difference value between the color block and each of the reference target individuals according to the color information of the color block and the color information of the reference target individual includes: Retrieving a preset color conversion model, wherein the color conversion model is a deep learning model; converting the color information of the color block and the color information of the reference target individual into tristimulus values ​​according to the color conversion model; determining the L value, A value, and B value according to the tristimulus values ​​of the color block, and determining the L value, A value, and B value according to the tristimulus values ​​of the reference target individual; calculating the color difference value according to the L value, A value, and B value of the color block, the L value, A value, and B value of the reference target individual, and a color difference formula; Determine whether an abnormal event occurs according to the geometric shape of each target individual and the control area where it is located, as well as the motion state in multiple consecutive frames of the construction image information; The color identification database records the abnormal behavior of each target individual. Based on the geometric shape of the target individual, the controlled area where it is located, and the motion state of multiple frames of continuous construction image information, it is judged whether it is consistent with the abnormal behavior of the target individual; if it is consistent, the abnormal event has occurred; if it is inconsistent, the abnormal event has not occurred.

2. The intelligent network color image tracking and monitoring method according to claim 1, characterized in that: The method for establishing the color conversion model comprises: Get the RGB image of the standard color card; Establishing a training sample set according to the RGB image of the standard color card and CIEXYZ data; The color conversion model is established according to the training sample set based on the least square method or the Wiener estimation method.

3. The intelligent network color image tracking and monitoring method according to claim 1, characterized in that: The determining whether the color information of the color block is consistent with the color information of the target individual according to the matching result of the color difference value between the color block and each of the reference target individuals and the color difference range of each target individual in the color identification database comprises: If the color difference between the color block and one of the reference target individuals is within the color difference range of the reference target individual, the matching result is a successful match, and the color information of the color block is consistent with the color information of the target individual; If the color difference value between the color block and any of the reference target individuals does not conform to the color difference range of the corresponding reference target individual, the matching result is a matching failure, and the color information of the color block is inconsistent with the color information of the target individual.

4. An intelligent network color image tracking and monitoring system, characterized in that: include, An acquisition module (21) is used to acquire construction monitoring information, wherein the construction monitoring information includes continuous multiple frames of construction image information; A retrieval module (22) is used to retrieve a preset color identification database, wherein the color identification database includes color information, shape information, color difference range, color tone and abnormal behavior of multiple target individuals; wherein the target individual may be a person, a building material or equipment; in the color identification database, the color information of the person is the color information of a safety helmet; when the building material and the equipment arrive at the construction site, the model of the building material and the equipment, as well as the color information, the shape information, the color difference range, the color tone and the abnormal behavior are entered into the color identification database; A determination module (23) is used to determine the number and position of target individuals in each frame of the construction image information according to the color identification database and each color in the construction image information; and the determination of the number and position of target individuals in each frame of the construction image information according to the color identification database and each color in the construction image information comprises: dividing a frame of the construction image information into a plurality of color blocks; determining a color block whose color information is consistent with the color information of the target individual according to the color identification database, and clustering the color blocks of the same color; Determine the number and position of target individuals according to the color identification database and cluster shape; Determine the number and position of target individuals according to the color identification database and cluster shape includes: determine whether the cluster shape of each cluster color block conforms to the shape information of the target individual in the color identification database; if the cluster shape conforms to the shape information of the target individual in the color identification database, determine the cluster color block as a target individual; count the number of cluster color blocks that meet the conditions, and record it as the number of target individuals; record the color block number occupied by the cluster color blocks that meet the conditions as the position of the target individual; The color identification database also includes the color difference range and the hue of each target individual. The color block whose color information is consistent with the color information of the target individual according to the color identification database includes: selecting color blocks one by one from the construction image information; determining the hue level according to the color information of the color block; selecting a target individual whose hue is the same as the hue level from the color identification database, and recording it as a reference target individual; calculating the color difference value between the color block and each of the reference target individuals according to the color information of the color block and the color information of the reference target individual; determining whether the color information of the color block is consistent with the color information of the target individual according to the matching result of the color difference value between the color block and each of the reference target individuals and the color difference range of each target individual in the color identification database; selecting the color block whose color information is consistent with the color information of the target individual; calculating the color difference value between the color block and each of the reference target individuals according to the color information of the color block and the color information of the reference target individual includes: Retrieving a preset color conversion model, wherein the color conversion model is a deep learning model; converting the color information of the color block and the color information of the reference target individual into tristimulus values ​​according to the color conversion model; determining the L value, A value, and B value according to the tristimulus values ​​of the color block, and determining the L value, A value, and B value according to the tristimulus values ​​of the reference target individual; calculating the color difference value according to the L value, A value, and B value of the color block, the L value, A value, and B value of the reference target individual, and a color difference formula; A judgment module (24) is used to judge whether an abnormal event has occurred based on the geometric shape and the control area where each target individual is located, as well as the movement state in the continuous multiple frames of the construction image information; the color identification database records the abnormal behavior of each target individual, and judges whether it is consistent with the abnormal behavior of the target individual based on the geometric shape and the control area where the target individual is located, as well as the movement state in the continuous multiple frames of construction image information; if it is consistent, the abnormal event has occurred; if it is inconsistent, the abnormal event has not occurred.

5. An intelligent terminal, characterized in that: It comprises a memory and a processor, wherein the memory stores a computer program that can be loaded by the processor and execute the intelligent network color image tracking and monitoring method as claimed in any one of claims 1 to 3.

6. A computer-readable storage medium, characterized in that: A computer program is stored which can be loaded by a processor and execute the intelligent network color image tracking and monitoring method as claimed in any one of claims 1 to 3.

Images