Image recognition method and device

Abstract

The invention provides an image recognition method and device, and belongs to the field of image recognition, and the method comprises the steps: obtaining feature body first information and target first information in a first image; target second information is obtained based on the feature body first information and target first information, the feature body first information is information of the feature body in the first image, the target first information is information of the target in the first image, and the target second information is actual information of the target; and updating the GIS electronic picture based on the target second information. According to the image recognition method and device provided by the invention, the accuracy and reliability of image recognition can be improved.

Description

Technical Field

[0001] The present disclosure belongs to the field of image recognition, and more specifically, to an image recognition method and device. Background Art

[0002] With the continuous growth of port business, the throughput of port cargo has also increased exponentially. The storage and transportation of cargo are very frequent, and it is very important to update the distribution information of cargo in a timely manner. Nowadays, the use of GIS electronic pictures can quickly understand the storage and vacant land of cargo, but the update of GIS electronic pictures is not accurate enough, and the size and outline of cargo are prone to deviation, leading to misjudgment.

[0003] It can be seen that an accurate image recognition method is urgently needed. Summary of the invention

[0004] The purpose of the present disclosure is to provide an image recognition method and device to improve the accuracy and reliability of image recognition.

[0005] According to a first aspect of the embodiments of the present disclosure, there is provided an image recognition method, comprising: Acquire first feature body information and first target information in the first image; Obtaining target second information based on the feature first information and the target first information, wherein the feature first information is information of the feature in the first image, the target first information is information of the target in the first image, and the target second information is actual information of the target; The GIS electronic map is updated based on the target second information.

[0006] According to a second aspect of the embodiments of the present disclosure, there is provided an image recognition device, including: An information acquisition module, used for acquiring first information of a feature body and first information of a target in a first image; An image processing module, configured to obtain target second information based on the feature first information and the target first information, wherein the feature first information is information of the feature in the first image, the target first information is information of the target in the first image, and the target second information is actual information of the target; An image updating module is used to update the GIS electronic map based on the target second information.

[0007] According to a third aspect of an embodiment of the present disclosure, an electronic device is provided, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor implements the steps of the above-mentioned image recognition method when executing the computer program.

[0008] According to a fourth aspect of the embodiments of the present disclosure, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the above-mentioned image recognition method are implemented.

[0009] The image recognition method and device provided by the embodiments of the present disclosure have the following beneficial effects: The present disclosure uses a feature body of known size and position as a reference object to accurately calculate the actual size and position of the target. The above-mentioned scale-based calculation method effectively reduces the measurement errors caused by factors such as different shooting heights and different ground heights, and improves the accuracy of the data. The present disclosure can timely update the GIS electronic map through the acquired image and target information, ensure the timeliness and accuracy of the GIS electronic map information, help the warehousing department save human resources, better plan the storage location of goods, and improve the accuracy and reliability of image recognition. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0011] Figure 1 A flowchart of an image recognition method provided by an embodiment of the present disclosure; Figure 2 A structural block diagram of an image recognition device provided by an embodiment of the present disclosure; Figure 3 A schematic block diagram of an electronic device provided by an embodiment of the present disclosure. DETAILED DESCRIPTION

[0012] In the following description, specific details such as specific system structures and technologies are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present disclosure. However, it should be clear to those skilled in the art that the present disclosure may be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid obstructing the description of the present disclosure with unnecessary details.

[0013] In order to make the purpose, technical solutions and advantages of the present disclosure more clear, specific embodiments will be described below in conjunction with the accompanying drawings.

[0014] Please refer to Figure 1 , Figure 1 A flowchart of an image recognition method provided by an embodiment of the present disclosure is provided, and the method includes: S101: Acquire first feature body information and first target information in a first image.

[0015] In this embodiment, the first image can be acquired through a drone or monitoring, and the first image is an image within a target area, and the target area can be a port warehouse.

[0016] The feature body can be set in advance, for example, the feature body is red in color, 2m in length, 1m in width (no height limit), and the coordinates in the first coordinate system are (200, 300). The first coordinate system can be a coordinate system established based on any point in the target area. The positive direction of the X axis of the coordinate system can be due east, and the positive direction of the Y axis can be due north. It should be noted that when selecting and setting the feature body, the principle is that it should not be blocked by the cargo stack and should be fixed. The feature body can be an object in the port warehouse itself, such as a fixed manhole cover, or it can be artificially set, such as a square flag with a length of 2m and a width of 1m.

[0017] The first information of the feature body and the first information of the target in the first image can be obtained through the neural network model and image segmentation trained by the first data set and the second data set. The first data set is a data set formed by pictures of multiple feature bodies, and the second data set is a data set formed by pictures of multiple cargo stacks or containers and other goods stored in port warehouses.

[0018] The first feature information may be the length of the feature in the first image, the width of the feature in the first image, and the color of the feature in the first image.

[0019] The target may be a cargo stack or a container in a port yard. The first target information may be the length of the cargo stack in the first image, the width of the cargo stack in the first image, the color of the target in the first image, and the distance between the target and the feature body in the first image.

[0020] For example, the first image is acquired by a drone, and the feature body and the target in the first image can be identified based on a neural network model that has been trained with a large number of feature body images and a large number of target images to obtain first feature body information and second target information. Specifically, it is identified that the color of the feature body P is blue, and the diameter of the feature body P in the first image is 0.03m. Based on the fact that the color of the feature body is blue, the pre-stored information is retrieved to obtain the coordinates of the center point of the blue feature body (feature body P) as (500, 600). It is identified that the length of the cargo stack Q in the first image is 0.2m, and the width is 0.1m. The color of the cargo stack Q is black and white. The distance between the cargo stack Q and the feature body P in the first image is that the cargo stack Q is 0.05m south of the feature body P.

[0021] S102: Obtaining target second information based on feature body first information and target first information, wherein the feature body first information is information of the feature body in the first image, the target first information is information of the target in the first image, and the target second information is actual information of the target.

[0022] In this embodiment, the first information of the feature body may be the length of the feature body in the first image, the width of the feature body in the first image, and the color of the feature body in the first image. The target first information may be the length of the cargo stack in the first image, the width of the cargo stack in the first image, the color of the cargo stack in the first image, and the distance between the cargo stack and the feature body. The target second information may be the actual length, actual width, actual color, and actual position of the cargo stack.

[0023] The length of the feature body in the first image may be compared with the length of the actual feature body to obtain a first ratio; determining an actual length of the object based on the first ratio and a length of the object in the first image; determining an actual width of the object based on the first ratio and a width of the object in the first image; An actual distance between the target and the feature is determined based on the first ratio and the distance between the target and the feature in the first image.

[0024] Before comparing the length of the feature body in the first image with the length of the actual feature body to obtain a first ratio, the method further includes: Establish a coordinate system based on a point in the target area; Determine the coordinates of the feature body; The coordinates of the feature body in the first image are obtained based on matching the color of the feature body in the first image with the preset color of the feature body.

[0025] Through the above process, the coordinates of the feature body, the actual length and width of the target and the actual distance between the target (stack) and the feature body can be obtained. The actual color of the target is consistent with the color of the target in the first image.

[0026] For example, if the target area is a port warehouse, the first coordinate system can be established based on the port warehouse gate as the origin, with the positive direction of the X-axis being due east and the positive direction of the Y-axis being due north.

[0027] The length of the feature in the first image is 0.01m, and the actual length of the feature is 5m, so the first ratio is 1:500. The length of the target in the first image is 0.1m, so the actual length of the target is 50m; the width of the target in the first image is 0.05m, so the actual length of the target is 25m; the center point of the target in the first image is 0.03m due south of the center point of the feature, so the actual center point of the target is 15m due south of the center point of the feature. The color of the feature is yellow, and the coordinates of the yellow feature in the pre-set information are (500, 700), so the coordinates of the above target are (500, 675). The color of the target in the first image is the actual target color.

[0028] S103: Update the GIS electronic map based on the target second information.

[0029] In this embodiment, the target may be a container, and the second target information may be the actual length, actual width, actual color, and actual location of the container. GIS electronic map is a form of electronic map used by geographic information systems in specific application scenarios, which reflects the image information within the target area.

[0030] Determine the second ratio between the target area and the GIS electronic map, the target area may be a port warehouse; The location and size of the object on the GIS are determined based on the second scale, the actual length of the object, the actual width of the object, the color of the object and the actual location of the object. The object may be a container.

[0031] The actual position of the target is displayed in the form of coordinates. The actual position of the target can be obtained based on the distance between the target and the feature body in the first image and the coordinates of the feature body. The coordinates of the feature body are known. The distance between the target and the feature body can be obtained based on image segmentation and feature extraction. The coordinates of the feature body can be the coordinates of the center of the feature body. The distance between the target and the feature body can be the distance between the center point of the target and the center point of the feature body. The above distance not only represents a number, but also contains a direction. When establishing a GIS electronic map, the points in the GIS electronic map should correspond to the coordinate positions one by one.

[0032] For example, the second ratio is 200:1, that is, 1m in the GIS electronic image is equal to the actual distance of 200m, the actual length of container A is 6m, the actual width is 2.5m, and the actual position is the coordinate (1, 1). Then, the length of container A displayed in the electronic image is 0.03m, the width is 0.0125m, and the center point of container A is at the coordinate (1, 1).

[0033] It can be concluded from the above that the present disclosure can accurately calculate the actual size and position of the target by using a feature body of known size and position as a reference object. The above-mentioned scale-based calculation method effectively reduces the measurement errors caused by factors such as different shooting heights and different ground heights, and improves the accuracy of the data. The present disclosure can timely update the GIS electronic map through the acquired image and target information, ensure the timeliness and accuracy of the GIS electronic map information, help the warehousing department save human resources, better plan the storage location of goods, and improve the accuracy and reliability of image recognition.

[0034] In one embodiment of the present disclosure, before acquiring the feature body information and the target first information in the first image, the method further includes: Establishing a first coordinate system based on a first origin, wherein the first origin is a point in the target area; The second information of the feature body is determined, wherein the second information of the feature body is actual information of the feature body.

[0035] In one embodiment of the present disclosure, the second information of the feature body includes: coordinates of a center point of the feature body in the first coordinate system, a color of the feature body, and second contour information of the feature body.

[0036] In one embodiment of the present disclosure, obtaining target second information based on feature body first information and target first information includes: Determine the coordinates of the center point of the feature body based on the color of the feature body; Acquire the first contour information of the feature body and the first contour information of the target based on image segmentation; Obtaining target second contour information based on the feature body first contour information and the target first contour information; The target position information is determined based on the coordinates of the center point of the feature body and a first distance between the center point of the feature body and the target.

[0037] In this embodiment, the first origin is any point in the target area, and the target area may be a port storage yard. For example, the first origin is the farthest point in the southwest direction of the port storage yard. Based on this point, a two-dimensional coordinate system is established with due east as the positive direction of the X-axis and due north as the positive direction of the Y-axis, which is the first coordinate system.

[0038] The second feature information is the actual information of the feature, including the coordinates of the center point of the feature in the first coordinate system, the color of the feature and the second contour information of the feature, and the contour information of the feature includes the length of the feature, the width of the feature and / or the diameter of the feature. The feature can be a rectangle or a circle.

[0039] The first device may be a drone or a monitoring device. When strong winds or rain or snow occurs and it is difficult for the drone to complete its flight mission, the first image may be acquired based on the monitoring device.

[0040] The first information of the feature may be the length of the feature in the first image, the width of the feature in the first image, and the color of the feature in the first image.

[0041] When pre-setting the feature body, each feature body in the warehouse can be set to a different color. Based on the color of the feature body in the image, it can be determined which pre-set feature body the feature body in the image is, and the actual length, actual width and actual coordinate position of the feature body can be obtained through the pre-stored feature body information. The above-mentioned actual coordinate position can be the coordinate of the center point of the feature body in the first coordinate system.

[0042] In this embodiment, the first contour information of the feature body and the first contour information of the target can be extracted based on image segmentation, and the first ratio can be determined based on the first contour information of the feature body and the preset second contour information of the feature body. The first contour information of the feature body can be the length of the feature body in the first image, the width of the feature body and / or the diameter of the feature body, and the first ratio can be a length ratio, a width ratio or an area ratio. It should be noted that the area ratio is the square of the length ratio or the width ratio.

[0043] The second contour information of the target can be obtained based on the first ratio and the first contour information of the target. The first contour information of the target can be the length of the target, the width of the target and / or the diameter of the target in the first image. The second contour information of the target can be the length of the target, the width of the target and / or the diameter of the target.

[0044] The coordinate position of the center point of the target can be determined based on the coordinates of the center point of the feature body and the distance between the feature body and the target. The color of the target in the first image is the actual color of the target.

[0045] For example, based on the first image obtained by the drone, based on image segmentation, the length of the feature body B in the first image is 0.02m, the width is 0.01m, and the color is green. The distance between the center point of the target and the center point of the feature body in the first image is 0.02m in the east direction. Through the pre-stored information, the actual length of the green feature body is 2m, the actual width is 1m, and the coordinates of the center point in the first coordinate system are (100, 200), that is, the first ratio is the length ratio, and the value is 1:100, that is, 1m in the first image is equivalent to an actual distance of 100m.

[0046] Based on image segmentation, the length of target C in the first image is 0.1m and the width is 0.04m. According to the first ratio and the distance between the center point of the target and the center point of the feature body in the first image is 0.02m in the east direction, the coordinates of the center point of the target are calculated to be (102, 200), that is, the coordinates of the center point of the target in the first coordinate system are (102, 200), the actual length is 10m, and the actual width is 4m. The color of target C in the first image is red, so the actual color of target C is red.

[0047] It can be concluded from the above that the present disclosure provides a unified reference frame for the positioning of the feature body and the target by establishing a first coordinate system based on the first origin in the target area. This helps to reduce the positioning error caused by different reference points or reference systems, thereby enhancing the accuracy of positioning. The present disclosure provides a rich data basis for subsequent image analysis and processing by determining the actual information of the feature body (i.e., the second information of the feature body), including its center point coordinates, color and contour information, which helps to identify the feature body and can also be used to further infer and calculate the relevant information of the target, thereby improving the accuracy and reliability of the image recognition method.

[0048] In one embodiment of the present disclosure, obtaining target second contour information based on feature body first information and target first information includes: Acquire the first contour information of the feature body and the first contour information of the target based on image segmentation; Obtaining a first ratio based on the first contour information of the feature body and the second contour information of the feature body; The second contour information of the target is obtained based on the first ratio and the first contour information of the target.

[0049] In one embodiment of the present disclosure, determining target position information based on the coordinates of the center point of the feature body and the first distance between the center point of the feature body and the target includes: Determine a second distance between the center point of the feature body and the target based on the first distance between the center point of the feature body and the target and the first ratio; The target position information is determined based on the coordinates of the feature body center point and the second distance.

[0050] In this embodiment, image segmentation is a basic process in digital image processing, which can decompose an image into several non-overlapping, meaningful regions with the same properties. The purpose of image segmentation is to separate the target in the image from the background to facilitate subsequent analysis and processing.

[0051] The first contour information of the feature body may be the length, width and / or diameter of the feature body in the first image; the first contour information of the object may be the length, width and / or diameter of the object in the first image.

[0052] The second contour information of the feature body may be the actual length of the feature body, the actual width of the feature body and / or the actual diameter of the feature body; the second contour information of the target may be the actual length of the target, the actual width of the target and / or the actual diameter of the target.

[0053] The first contour information of the feature body and the first contour information of the target can be obtained based on image segmentation and feature extraction, the second contour information of the feature body is pre-set, and the second contour information of the target is calculated based on the first contour information of the feature body, the second contour information of the feature body and the first contour information of the target.

[0054] The first distance between the center point of the feature body and the target is the distance between the center point of the feature body and the center point of the target in the first image; the second distance between the center point of the feature body and the target is the actual distance between the center point of the feature body and the center point of the target. The first distance between the center point of the feature body and the center point of the target can be obtained based on image segmentation and feature extraction, and the above distance is not only a numerical value, but also a direction.

[0055] The second distance can be obtained based on the first ratio and the first distance, that is, the actual distance between the center point of the feature body and the center point of the target can be obtained based on the first ratio and the distance between the center point of the feature body and the center point of the target in the first image, thereby obtaining the coordinates of the target in the first coordinate system. The first coordinate system is a coordinate system established with any point in the target area as the origin. The positive direction of the X-axis of the first coordinate system can be the due east direction, and the positive direction of the Y-axis can be the due north direction.

[0056] For example, the first ratio may be a length ratio, a width ratio or an area ratio. Specifically, the length of the feature body D in the first image is 0.03 m, and the width is 0.02 m, that is, the area is 0.0006 square meters. The actual length of the feature body D is 3 m, and the width is 2 m, that is, the area is 6 square meters. When the first ratio is a length ratio or a width ratio, the first ratio is 1:100. When the first ratio is an area ratio, the first ratio is 1:10000.

[0057] Based on image segmentation and feature extraction, the first contour information of feature body E is: the length in the first image is 0.04m, and the width is 0.03m; based on feature extraction, the color of feature body D in the first image is black, and the second contour information of feature body E is obtained through pre-set information: the actual length is 4m, the width is 3m, and the coordinates of the center point of feature body E in the first coordinate system are (1000, 1120). The first ratio is the area ratio, and the value is 1:10000.

[0058] The target first contour information of stack F is: the length of stack F in the first image is 0.16m, and the width of stack F is 0.12m. At this time, since the area ratio is the square of the length ratio or the width ratio, the length ratio is 1:100, so the target second contour information of stack F is: the actual length of stack F is 16m, and the actual width is 12m.

[0059] Based on image segmentation and feature extraction, the distance between the center point of the feature body E and the center point of the stack F in the first image is 0.1m (first distance) due north of the feature body E. Through the first ratio and the first distance calculation, it is obtained that the actual distance between the center point of the stack F and the center point of the feature body E is 10m, so the coordinates of the center point of the stack F are (1000, 1130).

[0060] It can be concluded from the above that the present disclosure obtains the first contour information of the feature body and the target through image segmentation technology, and can more accurately identify the boundary of the target object and the feature body, thereby reducing the error caused by boundary blur or noise interference. The present disclosure compares the second contour information (i.e., the actual size) of the feature body with the first contour information (i.e., the size in the image) to calculate the first ratio, which reflects the relationship between the pixel size and the actual size in the image, and can convert the size information in the image into the actual size, thereby realizing the standardization of the contour information and improving the reliability and accuracy of image recognition.

[0061] In one embodiment of the present disclosure, updating the GIS electronic map based on the target second information includes: determining a second ratio; The GIS electronic map is updated based on the second scale and the target second information.

[0062] In one embodiment of the present disclosure, the image recognition method further includes: Determine the importance of each coordinate point in the first coordinate system; The update frequency is determined based on the importance of each coordinate point.

[0063] In this embodiment, the second ratio is the mapping ratio between the target area and the GIS electronic map, that is, the second ratio, which is preset and can be manually set based on actual conditions and needs. Before establishing the GIS electronic map, the first coordinate system should be determined first, and the coordinate points in the first coordinate system should correspond one-to-one with each point in the GIS electronic map.

[0064] The importance of each area in the target area can be defined through historical records or manually. The target area can be a port warehouse, and the update frequency of GIS can be determined according to the importance of each area.

[0065] For example, the origin is determined based on the midpoint of the north-south direction and the midpoint of the east-west direction in the port warehouse, and a coordinate system is established with the origin. The positive direction of the X-axis can be the due east direction, and the positive direction of the Y-axis can be the due north direction. In the historical records, if the goods in the area composed of coordinates (1000, 1000), (1100, 1000), (1000, 1200) and (1100, 1200) are not updated for a long time, then the importance of the coordinates in the X-axis coordinate range of 1000~1100 and the Y-axis coordinate range of 1000~1200 can be defined as 1.

[0066] In the area consisting of coordinates (500, 700), (650, 700), (500, 800) and (650, 800), the goods are updated more frequently. Therefore, the importance of the coordinates in the X-axis range of 500-650 and the Y-axis range of 700-800 can be defined as 2.

[0067] Different importance levels correspond to different update frequencies. For example, an area with an importance level of 1 corresponds to an update frequency of 24 hours / time; an area with an importance level of 2 corresponds to an update frequency of 6 hours / time; and an area with an importance level of 1 corresponds to an update frequency of 2 hours / time. The update frequencies corresponding to different importance levels can be set manually.

[0068] The first image is acquired by the drone, the position information of the center point of the feature body is identified and determined according to the preset information, the position information of the target is obtained according to the image segmentation and feature extraction, the importance of the area where the position information is located is judged, and the update frequency of the area is determined according to the importance.

[0069] It can be concluded from the above that the present disclosure can ensure that the GIS electronic map is consistent with the actual situation by determining the second ratio and updating the GIS electronic map based on the ratio, which helps to reduce decision-making errors caused by information lag, improve the accuracy and practicality of the GIS electronic map, and improve the accuracy and reliability of image recognition; the present disclosure can more reasonably allocate and manage resources by determining the importance of each coordinate point in the first coordinate system and setting different update frequencies according to the importance. For areas with higher importance, increasing the update frequency can ensure timely acquisition of the latest information; for areas with lower importance, the update frequency can be appropriately reduced to reduce unnecessary waste of resources.

[0070] Corresponding to the image recognition method of the above embodiment, Figure 2 This is a structural block diagram of an image recognition device provided by an embodiment of the present disclosure. For ease of explanation, only the parts related to the embodiment of the present disclosure are shown. Figure 2 The image recognition device 20 includes: an information acquisition module 21, an image processing module 22 and an image updating module 23.

[0071] The information acquisition module 21 is used to acquire the first information of the feature body and the first information of the target in the first image; An image processing module 22, configured to obtain target second information based on feature body first information and target first information, wherein the feature body first information is information of the feature body in the first image, the target first information is information of the target in the first image, and the target second information is actual information of the target; The image updating module 23 is used to update the GIS electronic map based on the target second information.

[0072] In one embodiment of the present disclosure, the image recognition device 20 further includes: an image acquisition module; An image acquisition module, used to establish a first coordinate system based on a first origin, wherein the first origin is a point in the target area; Determine second information of the feature body, wherein the second information of the feature body is actual information of the feature body; A first image is acquired based on a first device.

[0073] In one embodiment of the present disclosure, the image acquisition module is specifically used for the second information of the feature body, including: the coordinates of the center point of the feature body in the first coordinate system, the color of the feature body and the second contour information of the feature body.

[0074] In one embodiment of the present disclosure, the image processing module 22 is specifically used to determine the coordinates of the center point of the feature body based on the color of the feature body; Acquire the first contour information of the feature body and the first contour information of the target based on image segmentation; Obtaining target second contour information based on the feature body first contour information and the target first contour information; The target position information is determined based on the coordinates of the center point of the feature body and a first distance between the center point of the feature body and the target.

[0075] In one embodiment of the present disclosure, the image processing module 22 is further configured to obtain the first contour information of the feature body and the first contour information of the target based on image segmentation; Obtaining a first ratio based on the first contour information of the feature body and the second contour information of the feature body; The second contour information of the target is obtained based on the first ratio and the first contour information of the target.

[0076] In one embodiment of the present disclosure, the image processing module 22 is further configured to determine a second distance between the center point of the feature body and the target based on the first distance between the center point of the feature body and the target and the first ratio; The target position information is determined based on the coordinates of the feature body center point and the second distance.

[0077] In one embodiment of the present disclosure, the image updating module 23 is specifically configured to determine the second ratio; The GIS electronic map is updated based on the second scale and the target second information.

[0078] In one embodiment of the present disclosure, the image recognition device 20 further includes: an update frequency module; An update frequency module, used to determine the importance of each coordinate point in the first coordinate system; The update frequency is determined based on the importance of each coordinate point.

[0079] See also Figure 3 , Figure 3 A schematic block diagram of an electronic device provided by an embodiment of the present disclosure. Figure 3 The electronic device 300 in the embodiment shown may include: one or more processors 301, one or more input devices 302, one or more output devices 303 and one or more memories 304. The processors 301, input devices 302, output devices 303 and memories 304 communicate with each other via a communication bus 305. The memory 304 is used to store computer programs, which include program instructions. The processor 301 is used to execute the program instructions stored in the memory 304. The processor 301 is configured to call the program instructions to execute the functions of each module / unit in the above-mentioned device embodiments, such as Figure 2 The functions of modules 21 to 23 are shown.

[0080] It should be understood that in the embodiment of the present disclosure, the processor 301 may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0081] The input device 302 may include a touch panel, a fingerprint collection sensor (for collecting the user's fingerprint information and fingerprint direction information), a microphone, etc., and the output device 303 may include a display (LCD, etc.), a speaker, etc.

[0082] The memory 304 may include a read-only memory and a random access memory, and provide instructions and data to the processor 301. A portion of the memory 304 may also include a non-volatile random access memory. For example, the memory 304 may also store information about the device type.

[0083] In a specific implementation, the processor 301, input device 302, and output device 303 described in the embodiments of the present disclosure can execute the implementation methods described in the first and second embodiments of the image recognition method provided in the embodiments of the present disclosure, and can also execute the implementation methods of the electronic device described in the embodiments of the present disclosure, which will not be repeated here.

[0084] In another embodiment of the present disclosure, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, wherein the computer program includes program instructions, and when the program instructions are executed by the processor, all or part of the processes in the above-mentioned embodiment method are implemented, and the computer program can also be completed by instructing the relevant hardware through the computer program. The computer program can be stored in a computer-readable storage medium, and when the computer program is executed by the processor, the steps of each of the above-mentioned method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form, etc. The computer-readable medium can include: any entity or device capable of carrying computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium, etc.

[0085] The computer-readable storage medium may be an internal storage unit of the electronic device of any of the aforementioned embodiments, such as a hard disk or memory of the electronic device. The computer-readable storage medium may also be an external storage device of the electronic device, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (SecureDigital, SD) card, a flash card (Flash Card), etc. equipped on the electronic device. Furthermore, the computer-readable storage medium may also include both an internal storage unit of the electronic device and an external storage device. The computer-readable storage medium is used to store computer programs and other programs and data required by the electronic device. The computer-readable storage medium may also be used to temporarily store data that has been output or is to be output.

[0086] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in terms of function in the above description. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this disclosure.

[0087] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the electronic devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0088] In the several embodiments provided in the present application, it should be understood that the disclosed electronic devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces or units, or it can be an electrical, mechanical or other form of connection.

[0089] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the embodiments of the present disclosure.

[0090] In addition, each functional unit in each embodiment of the present disclosure may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0091] The above are only specific embodiments of the present disclosure, but the protection scope of the present disclosure is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed in the present disclosure, and these modifications or replacements should be included in the protection scope of the present disclosure. Therefore, the protection scope of the present disclosure should be based on the protection scope of the claims.

Claims

1. An image recognition method, characterized in that: include: Acquire first feature body information and first target information in the first image; Obtaining target second information based on the feature first information and the target first information, wherein the feature first information is information of the feature in the first image, the target first information is information of the target in the first image, and the target second information is actual information of the target; The GIS electronic map is updated based on the target second information.

2. The image recognition method according to claim 1, characterized in that: Before acquiring the feature body information and the target first information in the first image, the method further includes: Establishing a first coordinate system based on a first origin, wherein the first origin is a point in the target area; Determine second information of the feature body, wherein the second information of the feature body is actual information of the feature body.

3. The image recognition method according to claim 2, characterized in that: The second information of the feature body includes: coordinates of a center point of the feature body in the first coordinate system, a color of the feature body, and second contour information of the feature body.

4. The image recognition method according to claim 3, characterized in that: The obtaining the target second information based on the feature body first information and the target first information includes: Determine the coordinates of the center point of the feature body based on the color of the feature body; Acquire the first contour information of the feature body and the first contour information of the target based on image segmentation; Obtaining target second contour information based on the feature body first contour information and the target first contour information; The target position information is determined based on the coordinates of the center point of the feature body and a first distance between the center point of the feature body and the target.

5. The image recognition method according to claim 4, characterized in that: The obtaining the second contour information of the target based on the first information of the feature body and the first information of the target includes: Acquire the first contour information of the feature body and the first contour information of the target based on image segmentation; Obtaining a first ratio based on the first contour information of the feature body and the second contour information of the feature body; The second contour information of the target is obtained based on the first ratio and the first contour information of the target.

6. The image recognition method according to claim 5, characterized in that: The determining the target position information based on the coordinates of the center point of the feature body and the first distance between the center point of the feature body and the target includes: Determine a second distance between the center point of the feature body and the target based on the first distance between the center point of the feature body and the target and the first ratio; The target position information is determined based on the feature body center point coordinates and the second distance.

7. The image recognition method according to claim 1, characterized in that: The updating of the GIS electronic map based on the target second information includes: determining a second ratio; The GIS electronic map is updated based on the second scale and the target second information.

8. An image recognition device, characterized in that: include: An information acquisition module, used for acquiring first information of a feature body and first information of a target in a first image; An image processing module, configured to obtain target second information based on the feature body first information and the target first information, wherein the feature body first information is information of the feature body in the first image, the target first information is information of the target in the first image, and the target second information is actual information of the target; An image updating module is used to update the GIS electronic map based on the target second information.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images