Object identification method, device, equipment and medium

Abstract

The present invention discloses an object recognition method, device, equipment and medium. The method comprises: sequentially acquiring two adjacent frames of original images corresponding to a target area; converting the two frames of original images into two corresponding frames of target binary images according to pre-configured target color features; and determining the movement of objects in the target area based on the actual attribute information of the two frames of target binary images. The present invention solves the problem of increased hardware cost due to high amount of computational data in the prior art, thereby reducing the amount of computational data without increasing the hardware cost; and, by using target color features to convert the original images into corresponding target binary images, the situation of misjudgment caused by the influence of light on the optical flow method is reduced, thereby improving the recognition accuracy of the object.

Description

Technical Field

[0001] The present invention relates to the field of image recognition technology, and in particular to an object recognition method, device, equipment and medium. Background Art

[0002] The key to a good recorded course is whether the director's screen can truly restore the classroom itself. Among them, the teacher asking students to answer questions is a very classic and frequently occurring classroom scene. The teacher randomly selects a student from the classroom, and the student stands up (at this time, the student camera needs to identify where the student is standing from the screen, that is, focus the student's close-up screen on the position of the student to highlight the student's standing behavior). After the student finishes answering the question, the student sits down and the teacher continues to lecture.

[0003] In the prior art, the most commonly used method is the optical flow method based on image motion target detection to obtain the motion vector; then determine whether it is the vertical motion of the image. If it is upward motion, it is determined that the student is standing. Once it is determined that the student is standing, the close-up image is directly locked as a "small image with the student standing as the center", focusing on this position and zooming in (equivalent to giving a close-up shot).

[0004] However, the optical flow method requires a large amount of calculation data and is not efficient. Accordingly, a recording and broadcasting camera with higher computing power is required, which adds additional hardware and R&D costs. At the same time, the optical flow method is easily affected by light and other factors during actual operation, which leads to errors in the calculation results (i.e., motion vectors), and further misjudgment of students standing. Summary of the invention

[0005] The present invention provides an object recognition method, device, equipment and medium to solve the problems of high hardware cost and misjudgment of students standing in the prior art.

[0006] According to one aspect of the present invention, there is provided an object recognition method, comprising:

[0007] Sequentially obtain two adjacent frames of original images corresponding to the target area;

[0008] Converting the two frames of original images into two corresponding frames of target binary images respectively according to pre-configured target color features;

[0009] The movement of the object in the target area is determined based on the actual attribute information of the two frames of target binary images.

[0010] According to another aspect of the present invention, there is provided an object recognition device, comprising:

[0011] The first acquisition module is used to sequentially acquire two adjacent frames of original images corresponding to the target area;

[0012] A conversion module, used for converting the two frames of original images into two corresponding frames of target binary images according to pre-configured target color features;

[0013] The first determination module is used to determine the movement of the object in the target area based on the actual attribute information of the two frames of target binary images.

[0014] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0015] at least one processor; and

[0016] a memory communicatively connected to the at least one processor; wherein,

[0017] The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can perform the object recognition method described in any embodiment of the present invention.

[0018] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the object recognition method described in any embodiment of the present invention when executed.

[0019] The technical solution of the embodiment of the present invention obtains two adjacent frames of original images corresponding to the target area, and then converts the two frames of original images into two frames of target binary images according to the target color features, and directly determines the movement of objects in the target area based on the actual attribute information of the target binary images, thereby solving the problem of increased hardware costs due to the high amount of calculation data in the prior art, thereby reducing the amount of calculation data without additionally increasing the hardware cost; and, by using the target color features to convert the original images into the corresponding target binary images, the situation of misjudgment caused by the influence of light on the optical flow method is reduced, thereby improving the recognition accuracy of the object.

[0020] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0022] Figure 1 It is a hardware deployment diagram of a recording and broadcasting scenario provided by an embodiment of the present invention;

[0023] Figure 2 is a flow chart of an object recognition method provided by an embodiment of the present invention;

[0024] Figure 3 is a flow chart of another object recognition method provided by an embodiment of the present invention;

[0025] Figure 4 is a flowchart of another object recognition method provided by an embodiment of the present invention;

[0026] Figure 5 It is a schematic diagram of a change of an object seat diagram provided by an embodiment of the present invention;

[0027] Figure 6 is a display schematic diagram of object movement provided by an embodiment of the present invention;

[0028] Figure 7 is a schematic diagram of the structure of an object recognition device provided by an embodiment of the present invention;

[0029] Figure 8 It is a structural block diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0030] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0031] It should be noted that the terms "first", "second", "original", "target", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0032] Figure 1 FIG. 1 is a schematic diagram of hardware deployment for a recording and broadcasting scenario provided by an embodiment of the present invention. Figure 1 As shown in the figure, in the same classroom, three cameras (teacher camera, student camera and PTZ camera), touch recording and broadcasting host, interactive display screen, sound field transformation unit, directional pickup microphone, integrated active speaker and smart blackboard need to be deployed. Generally speaking, there are 7 pictures in the same classroom (teacher panoramic view / teacher close-up / student panoramic view / student close-up / computer picture / blackboard picture / director picture), which are transmitted to the recording and broadcasting host in different ways and further processed by the recording and broadcasting host.

[0033] Among them, the teacher camera is used to shoot the situation in the teacher area, that is, it can output the teacher's panoramic view or teacher's close-up picture at the same time; the student camera is used to shoot the situation in the student area, that is, it can output the student's panoramic view or student's close-up picture at the same time; the smart blackboard can be input to the recording and broadcasting host through the High Definition Multimedia Interface (HDMI) IN method to form a computer screen; the blackboard can be input to the recording and broadcasting host through the HDMI IN method to form a blackboard screen; the director screen: refers to a composite screen in which one or more screens are selected from the multiple screens collected as the screen source.

[0034] In one embodiment, Figure 2 This is a flow chart of an object recognition method provided by an embodiment of the present invention. This embodiment is applicable to the case of fast fuzzy recognition of an object standing. The method can be executed by an object recognition device, which can be implemented in the form of hardware and / or software, and can be configured in an electronic device. Fuzzy recognition does not pursue 100% individual accuracy, but tends to calculate whether there is an object within a region that undergoes recognition action. Figure 2 As shown, the method includes:

[0035] S110 , sequentially acquiring two adjacent frames of original images corresponding to the target area.

[0036] The target area refers to the student area to be photographed. The student area includes multiple objects (i.e., students). The original image refers to the unprocessed original picture. In actual operation, two frames of unprocessed original pictures taken continuously by the student camera can be used as two adjacent frames of original images corresponding to the target area. The original image can be an RGB image.

[0037] In actual operation, the target area can be photographed by a student camera to obtain all frames of original images corresponding to the target area; then two adjacent frames of original images are intercepted from all frames of original images.

[0038] S120 , converting the two frames of original images into two corresponding frames of target binary images respectively according to pre-configured target color features.

[0039] Among them, the target color feature refers to the color feature that matches the target area. Generally speaking, the target area refers to one of the classrooms in a school. In the school, the school uniform color of each object is generally based on a single color. Of course, different schools can be equipped with school uniforms of different colors. In an embodiment, the target scene corresponding to the target area can be used to determine the corresponding school according to a classroom, and then the target color feature that matches it can be found. For example, the target color feature can be blue. In an embodiment, the original image can be converted into a corresponding binary image according to the color threshold range corresponding to the target color feature, and two frames of target binary images can be obtained. It can be understood that when the colors corresponding to the target color features are different, the corresponding color threshold ranges are also different.

[0040] In an embodiment, for the case where the binary image is an HSV binary image and the original image is an RGB image, when the original image is an RGB image, the RGB image can be converted into an HSV image, and then the HSV image can be converted into an HSV binary image according to the color threshold range corresponding to the target color feature.

[0041] S130 , determining the movement of the object in the target area based on the actual attribute information of the two frames of target binary images.

[0042] The object movement status is used to characterize whether each object in the target area is standing. If one of the objects in the target area is standing, the object movement status of the target area is moving; if no object in the target area is standing, the object movement status of the target area is not moving.

[0043] The actual attribute information is used to characterize the information of the target binary image's own attributes. In one embodiment, the actual attribute information may include, but is not limited to: the actual total pixel value and the pixel point position. The actual total pixel value refers to the total pixel value of a row in the target binary image; the pixel point position refers to the pixel point position of a row in the target binary image.

[0044] In an embodiment, it can be determined whether an object in the target area moves according to the actual total pixel value of a row in the target binary image or the change of the pixel position.

[0045] The technical solution of this embodiment obtains two adjacent frames of original images corresponding to the target area, and then converts the two frames of original images into two frames of target binary images according to the target color features, and directly determines the movement of objects in the target area based on the actual attribute information of the target binary images, thereby solving the problem of increased hardware costs due to the high amount of calculation data in the prior art, thereby reducing the amount of calculation data without additionally increasing the hardware cost; and, by using the target color features to convert the original images into corresponding target binary images, the situation of misjudgment caused by the influence of light on the optical flow method is reduced, thereby improving the recognition accuracy of the object.

[0046] In one embodiment, there are two ways to determine the target color features: first, actively searching for the corresponding target color features according to the target scene corresponding to the target area; second, receiving the target color features corresponding to the target area sent by other devices.

[0047] In one embodiment, for the first determination method of the target color feature: the object recognition method also includes: obtaining the target scene corresponding to the target area; searching for the target color feature corresponding to the target scene according to a pre-configured scene feature mapping table; using the target color feature corresponding to the target scene as the target color feature of the target area. In the embodiment, the mapping relationship between each target scene and the target color feature is pre-configured to generate a corresponding scene feature mapping table; then after obtaining the target scene corresponding to the target area, the corresponding target color feature is directly searched in the scene feature mapping table through the target scene; finally, the target color feature corresponding to the target scene is used as the target color feature of the target area.

[0048] In one embodiment, the first determination method for the target color feature: the object recognition method further includes: receiving the target color feature corresponding to the target area sent by the recording and broadcasting device. The recording and broadcasting device refers to a touch-controlled recording and broadcasting host. In the embodiment, the target area can be sent to the recording and broadcasting device, and then the recording and broadcasting device finds the target color feature corresponding to the target area based on the correspondence between the target area and the color feature, and sends the target color feature to the student camera through the recording and broadcasting device.

[0049] In one embodiment, Figure 3 FIG. 1 is a flow chart of another object recognition method provided by an embodiment of the present invention. Based on the above embodiment, this embodiment further illustrates the process of determining the movement of an object. Figure 3 As shown, the method includes:

[0050] S210 , sequentially acquiring two adjacent frames of original images corresponding to the target area.

[0051] S220 , converting the two frames of original images into two corresponding frames of target binary images respectively according to the pre-configured target color features.

[0052] S230, identifying and extracting all target pixel points that meet a preset pixel threshold in each frame of the target binary image.

[0053] The preset pixel threshold is used as a threshold value for classifying each pixel in the target binary image. It can be understood that the pixel points in the target binary image that meet the preset pixel threshold are used as corresponding target pixels; at the same time, the pixel points in the target binary image that do not meet the preset pixel threshold are filtered.

[0054] S240, generating an object seat map corresponding to the corresponding frame target binary image based on the target pixel points.

[0055] The target pixel is used to characterize the object in the target area. The object seat map is used to characterize the current position of each object in the target area. Of course, in the embodiment, the object seat map corresponding to the corresponding frame target binary image is generated according to the position of the target pixel.

[0056] S250. When the actual attribute information includes the actual total pixel value, the actual total pixel value of the target row in the two frames of target binary images is determined respectively to obtain the corresponding first actual total pixel value and second actual total pixel value; wherein the target row is one of the rows in the object seat map.

[0057] In an embodiment, the same row in two frames of target binary images is extracted as the target row, and then the pixel value of each pixel in the target row is obtained, and the pixel values ​​of all pixels are added to obtain the actual total pixel value of the target row as the corresponding first actual total pixel value and second actual total pixel value.

[0058] S260: Determine the movement of the object in the target area based on the total pixel difference between the first actual pixel total value and the second actual pixel total value.

[0059] In an embodiment, the first actual pixel total value and the second actual pixel total value are subtracted to obtain a corresponding pixel total difference value; then, based on the pixel total difference value, it is determined whether an object in the target area moves.

[0060] S270. When the actual attribute information includes pixel positions, obtain the pixel positions of target pixels contained in the target rows in the two frames of target binary images; wherein the target row is one of the rows in the object seat map.

[0061] In an embodiment, pixel positions of target pixels contained in a target row in each frame of the target binary image are identified and extracted.

[0062] S280: Determine the movement of the object in the target area based on the actual change of the pixel position.

[0063] In an embodiment, whether there is an object moving in the target area can be determined based on whether the position of the pixel point actually changes.

[0064] In one embodiment, determining the movement of an object in a target area based on the actual change of the pixel position includes: determining a change comparison result between the actual change of the target pixel included in the target row and a preset change threshold value; and determining the movement of the object in the target area based on the change comparison result. In an embodiment, when the actual change of the target pixel is a change, the actual change is compared with the preset change threshold value to avoid misjudgment of the object change. When the actual change reaches the preset change threshold value, it can be determined that the object in the target area has moved.

[0065] The technical solution of this embodiment, based on the above-mentioned embodiment, determines the movement of the object in the target area based on the actual total pixel value or pixel position of the target row in the target binary image, thereby constructing the relationship between the pixel change area and the object standing or sitting, thereby avoiding the high performance requirements of conventional visual algorithms and the research and development costs of high algorithm accuracy, and improving the recognition accuracy of objects standing or sitting without increasing the hardware cost.

[0066] In one embodiment, Figure 4 is a flowchart of another object recognition method provided by an embodiment of the present invention. For example, the target area is a classroom A in a school A. Of course, different grades in a school may use the same color uniforms or different colors. In this embodiment, the process of acquiring the target color features is described by taking the case that all grades in the same school use the same color uniforms, the original image is an RGB image, the target binary image is an HSV binary image, and the object is a student as an example. Figure 4 As shown, the process of acquiring the target color feature in this embodiment includes the following steps:

[0067] S310. Receive, on the recording and broadcasting platform, target color features of the target area input by a school administrator.

[0068] S320, the recording and broadcasting platform sends the target color feature to the touch-controlled recording and broadcasting host through the network.

[0069] S330, the touch-controlled recording and broadcasting host transmits the target color feature to the student camera in the target area through the network.

[0070] S340, the student camera obtains the target color feature.

[0071] S350 , converting two adjacent frames of collected RGB images into two corresponding frames of HSV binary images according to the target color features.

[0072] S360, counting the actual total pixel values ​​of the target rows in the two frames of HSV binary images.

[0073] S370, determining the student movement in the target area based on the total pixel difference of the two actual pixel total values.

[0074] It should be noted that before receiving the target color features of the target area input by the school administrator on the recording and broadcasting platform, the following can be deployed in the target scene where the target area is located: Figure 1 The hardware equipment in the recording and broadcasting scenario is shown.

[0075] In an embodiment, after converting the RGB image to the corresponding HSV binary image, the HSV binary images of the previous and next two frames can be extracted, and the actual total pixel values ​​of the target rows in the HSV binary image can be compared to determine whether the students in the target area have moved. By converting the RGB image to an HSV binary image and counting the actual total pixel values ​​of the target rows in the HSV binary image, the required hardware computing performance is greatly reduced, and more memory bandwidth of the hardware can be released for the calculation of other data. At the same time, by using a unified school uniform color, the analysis can be performed within a fixed color gamut range, reducing the influence of light on the optical flow method and causing misjudgment, thereby improving the recognition accuracy of students standing.

[0076] In one embodiment, Figure 5 1 is a schematic diagram of a change in an object seat diagram provided by an embodiment of the present invention. Figure 5 As shown in Figure 1, it is assumed that there are 12 students in a target area, and a small square is used to represent the size of the area occupied by a student in the target area. At time T1, the object seat map corresponding to the target area is as follows: Figure 5 As shown in the left figure in , at the next moment of T1 (i.e., moment T2), the object seat map corresponding to the target area is as follows Figure 5 As shown in the right figure. Figure 5 As shown, block 22 has changed, which can be understood as the student corresponding to block 22 standing up.

[0077] It should be noted that each small square can represent one student or two students. For example, if two students sit close to each other, the small squares corresponding to the two students are the same. If the small squares change, it means that the students in the target area are standing.

[0078] In one embodiment, Figure 6 FIG. 1 is a schematic diagram showing the movement of an object provided by an embodiment of the present invention. Figure 6As shown, block 1 is used to represent the situation where student A is not standing; block 2 is used to represent the situation where student A is standing. When block 1 moves to block 2, it indicates that student A is standing. When block 1 moves vertically to block 2, or when block 1 moves toward the upper left direction to obtain block 2 (i.e., 50% of the small block swings to the left), or when block 1 moves toward the upper right direction to obtain block 2 (i.e., 50% of the small block swings to the right), it can be considered that student A corresponding to block 1 has moved.

[0079] In one embodiment, Figure 7 Schematic diagram of the structure of an object recognition device provided by an embodiment of the present invention. Figure 7 As shown, the device includes: a first acquisition module 410, a conversion module 420 and a first determination module 430.

[0080] The first acquisition module 410 is used to sequentially acquire two adjacent frames of original images corresponding to the target area;

[0081] A conversion module 420, configured to convert the two frames of original images into two corresponding frames of target binary images according to pre-configured target color features;

[0082] The first determination module 430 is configured to determine the movement of the object in the target area based on the actual attribute information of the two frames of target binary images.

[0083] In one embodiment, the object recognition device further includes:

[0084] A second acquisition module is used to acquire a target scene corresponding to the target area;

[0085] A search module, used to search for a target color feature corresponding to the target scene according to a pre-configured scene feature mapping table;

[0086] The second determining module is used to use the target color feature corresponding to the target scene as the target color feature of the target area.

[0087] In one embodiment, the object recognition device further includes:

[0088] The receiving module is used to receive the target color feature corresponding to the target area sent by the recording and broadcasting device.

[0089] In one embodiment, the object recognition device further includes:

[0090] An identification and extraction module, used to identify and extract all target pixel points that meet a preset pixel threshold in each frame of the target binary image;

[0091] A generation module is used to generate an object seat map corresponding to the corresponding frame target binary image based on the target pixel points.

[0092] In one embodiment, the actual attribute information includes an actual total pixel value; the first determination module 430 includes:

[0093] A first determining unit is used to respectively determine the actual total pixel value of the target row in the two frames of the target binary image, and obtain a corresponding first actual total pixel value and a second actual total pixel value; wherein the target row is one of the rows in the object seat map;

[0094] The second determining unit is configured to determine the movement of the object in the target area based on the total pixel difference between the first actual pixel total value and the second actual pixel total value.

[0095] In one embodiment, the actual attribute information includes pixel locations; the first determination module 430 includes:

[0096] An acquisition unit, used for acquiring pixel positions of target pixels contained in a target row in two frames of the target binary images; wherein the target row is one of the rows in the object seat map;

[0097] The third determining unit is used to determine the movement of the object in the target area based on the actual change of the pixel position.

[0098] In one embodiment, the third determining unit includes:

[0099] A first determining subunit is used to determine a change comparison result between an actual change condition of a target pixel point included in the target row and a preset change threshold value;

[0100] The second determining subunit is used to determine the movement of the object in the target area based on the change comparison result.

[0101] The object recognition device provided in the embodiment of the present invention can execute the object recognition method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0102] In one embodiment, Figure 8 is a structural block diagram of an electronic device provided by an embodiment of the present invention, such as Figure 8As shown, a schematic diagram of the structure of an electronic device 10 that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workbenches, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0103] like Figure 8 As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0104] A number of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0105] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 performs the various methods and processes described above, such as an object recognition method.

[0106] In some embodiments, the object recognition method may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the object recognition method described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to perform the object recognition method in any other appropriate manner (e.g., by means of firmware).

[0107] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0108] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0109] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, 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 foregoing.

[0110] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0111] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0112] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0113] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0114] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. An object recognition method, characterized in that: include: Sequentially obtain two adjacent frames of original images corresponding to the target area; Converting the two frames of original images into two corresponding frames of target binary images respectively according to pre-configured target color features; Determine the movement of the object in the target area based on the actual attribute information of the two frames of target binary images; The method further comprises: Acquire a target scene corresponding to the target area; Searching for a target color feature corresponding to the target scene according to a pre-configured scene feature mapping table; wherein the target color feature refers to a color feature that matches the target area; Using the target color feature corresponding to the target scene as the target color feature of the target area; or receiving a target color feature corresponding to the target area sent by a recording and broadcasting device; Identify and extract all target pixel points that meet a preset pixel threshold in each frame of the target binary image; An object seat map corresponding to the corresponding frame target binary image is generated based on the target pixel points; wherein the object seat map is the current position of each object in the target area.

2. The method according to claim 1, characterized in that The actual attribute information includes an actual pixel total value; and determining the object movement in the target area based on the actual attribute information of the two frames of target binary images includes: Determine respectively the actual total pixel values ​​of the target rows in the two frames of the target binary images, and obtain the corresponding first actual total pixel value and second actual total pixel value; wherein the target row is one of the rows in the object seat map; The movement of the object in the target area is determined based on the pixel total difference between the first actual pixel total value and the second actual pixel total value.

3. The method according to claim 1, characterized in that The actual attribute information includes pixel positions; and determining the movement of the object in the target area based on the actual attribute information of the two frames of target binary images includes: Obtaining the pixel positions of target pixels contained in a target row in two frames of the target binary images; wherein the target row is one of the rows in the object seat map; The movement of the object in the target area is determined based on the actual change of the pixel position.

4. The method according to claim 3, characterized in that The determining the movement of the object in the target area based on the actual change of the pixel position includes: Determine a change comparison result between an actual change condition of the target pixel point included in the target row and a preset change threshold value; The movement of the object in the target area is determined based on the change comparison result.

5. An object recognition device, characterized in that: include: The first acquisition module is used to sequentially acquire two adjacent frames of original images corresponding to the target area; A conversion module, used for converting the two frames of original images into two corresponding frames of target binary images according to pre-configured target color features; A first determination module is used to determine the movement of the object in the target area based on the actual attribute information of the two frames of target binary images; The object recognition device further comprises: A second acquisition module is used to acquire a target scene corresponding to the target area; A search module, used to search for a target color feature corresponding to the target scene according to a pre-configured scene feature mapping table; wherein the target color feature refers to a color feature that matches the target area; A second determination module is used to use the target color feature corresponding to the target scene as the target color feature of the target area; or a receiving module, used for receiving a target color feature corresponding to the target area sent by a recording and broadcasting device; The object recognition device further comprises: An identification and extraction module, used to identify and extract all target pixel points that meet a preset pixel threshold in each frame of the target binary image; A generation module is used to generate an object seat map corresponding to the corresponding frame target binary image based on the target pixel points; wherein the object seat map is the current position of each object in the target area.

6. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can perform the object recognition method according to any one of claims 1 to 4.

7. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the object recognition method according to any one of claims 1 to 4 when executed.

Images