Image processing method, device and system

Abstract

The invention discloses an image processing method, device and system, and the method comprises the steps: obtaining a first image which comprises a target object; performing image recognition on the first image, and determining the attribute of the target object; segmenting the first image to obtain a second image of the target object; based on the attribute of the target object, the second image is sent to the target display device, and the attributes of objects contained in the image received by the target display device are the same. According to the invention, the technical problem of low monitoring efficiency caused by too many monitored images and target objects in the prior art is solved.

Description

[0001] This invention is a divisional application with application number 2020112417016, application date November 9, 2020, and invention name “Image processing method, device and system”. Technical Field

[0002] The present invention relates to the field of image processing, and in particular to an image processing method, device and system. Background Art

[0003] The image transmission system includes an acquisition end and a receiving end; wherein the acquisition end is connected to an image source device to acquire images taken by the image source device and encode the images and send them to the receiving end; the receiving end is connected to a display device and decodes the encoded data before displaying the images on the display device.

[0004] The image transmission system can realize monitoring functions in various scenarios, such as military areas, laboratories, etc. The images taken by each image source device usually include multiple target objects, which may include buildings, people, vehicles, specific areas, etc. Usually, the images taken by multiple image source devices are displayed on the display device in the monitoring room, and there may be multiple target objects in each image. When the administrator pays attention to multiple target objects in multiple images at the same time, it is easy to miss or misread them, resulting in low efficiency in monitoring the target objects.

[0005] To address the above-mentioned problems, no effective solution has been proposed yet. Summary of the invention

[0006] The embodiments of the present invention provide an image processing method, device and system to at least solve the technical problem in the related art that the monitoring efficiency is too low due to too many monitored images and target objects.

[0007] According to one aspect of an embodiment of the present invention, there is provided an image processing method, comprising: acquiring a first image, wherein the first image comprises: a target object; performing image recognition on the first image to determine attributes of the target object; segmenting the first image to obtain a second image of the target object; and based on the attributes of the target object, sending the second image to a target display device, wherein the attributes of the object contained in the image received by the target display device are the same.

[0008] Optionally, based on the attributes of the target object, sending the second image to the target display device includes: determining a target receiving end based on the attributes of the target object, wherein the target receiving end is connected to the target display device; sending the second image to the target receiving end, wherein the target receiving end is used to control the target display device to display the second image.

[0009] Optionally, determining the target receiving end based on the attribute of the target object includes: determining first identification information of the second image based on the attribute of the target object; and determining the target receiving end according to the first identification information.

[0010] Optionally, based on the attributes of the target object, determining the first identification information of the second image includes: matching the second image with multiple pre-stored images to obtain a successfully matched target image, wherein the attributes of the object contained in the target image are the same as the attributes of the target object; obtaining the second identification information of the successfully matched target image; and determining that the first identification information is the second identification information.

[0011] Optionally, when the target receiving end receives multiple second images, the target receiving end is used to splice the multiple second images and control the target display device to display the spliced ​​image.

[0012] Optionally, segmenting the first image to obtain a second image of the target object includes: acquiring position information of the target object in the first image; and segmenting the first image according to the position information to obtain the second image.

[0013] Optionally, segmenting the first image according to the position information to obtain the second image includes: determining a segmentation area where the target object is located in the first image according to the position information; and segmenting the first image according to the segmentation area to obtain the second image.

[0014] Optionally, sending the second image to the target receiving end includes: encoding the second image; and sending the encoded second image to the target receiving end, wherein the target receiving end is used to decode the encoded second image to obtain the second image.

[0015] Optionally, before acquiring the first image, the method also includes: acquiring an original image set, wherein the original image set is a set of images acquired by an acquisition device; matching each original image in the original image set with a plurality of pre-stored images; and if a target original image in the original image set successfully matches a pre-stored target image, determining that the target original image is the first image.

[0016] According to another aspect of an embodiment of the present invention, there is provided an image processing apparatus, comprising: an acquisition module, for acquiring a first image, wherein the first image comprises: a target object; a recognition module, for performing image recognition on the first image to determine the attributes of the target object; a segmentation module, for segmenting the first image to obtain a second image of the target object; and a sending module, for sending the second image to a target display device based on the attributes of the target object, wherein the attributes of the object contained in the image received by the target display device are the same.

[0017] According to another aspect of an embodiment of the present invention, there is provided an image processing system, comprising: an image acquisition device, for acquiring a first image, wherein the first image comprises: a target object; a processor, arranged in the image acquisition device, for performing image recognition on the first image, determining attributes of the target object, and segmenting the first image to obtain a second image of the target object; a sending module, arranged in the image acquisition device, for sending a second image based on the attributes of the target object; and a target display device, for receiving the second image sent by the sending module, wherein the attributes of the object contained in the image received by the target display device are the same.

[0018] Optionally, the system also includes: a target receiving end connected to the target display device, wherein the target receiving end is determined by the image acquisition device based on the attributes of the target object, the target receiving end is used to receive the second image sent by the sending module, and is used to control the target display device to display the second image.

[0019] Optionally, the system further includes: an acquisition device for acquiring original images.

[0020] According to another aspect of an embodiment of the present invention, a computer-readable storage medium is provided. The computer-readable storage medium includes a stored program, wherein when the program is executed, the device where the computer-readable storage medium is located is controlled to execute the above-mentioned image processing method.

[0021] According to another aspect of an embodiment of the present invention, a processor is further provided, and the processor is used to run a program, wherein the above-mentioned image processing method is executed when the program is run.

[0022] According to an embodiment of the present invention, a first image can be acquired first, wherein the first image includes: a target object; image recognition is performed on the first image to determine the attributes of the target object; the first image is segmented to obtain a second image of the target object; and based on the attributes of the target object, the second image is sent to a target display device, wherein the attributes of the objects contained in the images received by the target display device are the same, thereby achieving monitoring of objects with the same attributes in one target display device, allowing an administrator to focus on observing target objects with the same attributes, thereby avoiding situations where the administrator misses or mis-observes target objects with multiple attributes in multiple images at the same time, resulting in low efficiency in monitoring the target object, thereby solving the technical problem in the related art of low monitoring efficiency due to too many monitored images and target objects. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0024] Figure 1 is a flow chart of an image processing method according to an embodiment of the present invention;

[0025] Figure 2 is a flowchart of another image processing method according to an embodiment of the present invention;

[0026] Figure 3 is a schematic diagram of an image processing system according to an embodiment of the present invention;

[0027] Figure 4 is a schematic diagram of a segmented image according to an embodiment of the present invention;

[0028] Figure 5 is a schematic diagram of an image processing device according to an embodiment of the present invention;

[0029] Figure 6 is a schematic diagram of another image processing system according to an embodiment of the present invention;

[0030] Figure 7 is a schematic diagram of yet another image processing system according to an embodiment of the present invention. DETAILED DESCRIPTION

[0031] 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.

[0032] It should be noted that the terms "first", "second", 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 interchanged 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.

[0033] Example 1

[0034] According to an embodiment of the present invention, an embodiment of an image processing method is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0035] Figure 1 is a flowchart of an image processing method according to an embodiment of the present invention. Figure 1 As shown, the method comprises the following steps:

[0036] Step S102, acquiring a first image.

[0037] The first image includes: a target object.

[0038] In the above steps, the first image may include one target object or multiple target objects, wherein the target object may be an object that the monitoring personnel needs to monitor, and the target object may be a building, a vehicle, a specific area, etc.

[0039] In an optional embodiment, the first image can be acquired through a shooting device, wherein the shooting device can be a camera, a camera, etc. installed in different monitoring scenes; the first image can also be acquired from a locally stored gallery; the first image taken by a remote shooting device can also be acquired through a network.

[0040] In another optional embodiment, the first image may be acquired according to a preset interval duration to avoid resource occupation caused by frequent acquisition of the first image.

[0041] Step S104: performing image recognition on the first image to determine the attributes of the target object.

[0042] In the above steps, the attributes of the target object may be color, type, size, etc., and the attributes of the target object are not limited here.

[0043] In an optional embodiment, the type of the target object can be used as the attribute of the target object, and the first image can be subjected to image recognition to determine the type of the target object. Exemplarily, the first image is subjected to image recognition to identify that the target object in the first image is a ship, and the type of the ship is a vehicle, then the attribute of the target object can be determined to be a vehicle.

[0044] The image recognition algorithm may be used to perform image recognition on the first image to determine the type of the target object. The features of the target object in the first image may be extracted to identify the target object. For example, the contour features of the target object in the first image may be extracted and the target object may be identified by comparing the contour features. If the contour of the target object is determined to be the contour of a ship, the target object may be determined to be a ship, thereby determining the attribute of the target object to be a means of transportation.

[0045] In another optional embodiment, the properties of the target object can be determined by comparing the first image with a pre-stored image, and when the target object in the first image is the same or similar to the object in the pre-stored image, the properties of the target object in the first image can be set to the properties of the object in the pre-stored image. The pre-stored image can be an image of an object of various properties pre-collected by the user.

[0046] Exemplarily, the pre-stored images may be ships, airplanes, trees, and flowers, wherein the attributes of ships and airplanes are both transportation tools, and the attributes of trees and flowers are plants. The first image acquired may include ships and airplanes, and by comparing the first image with the pre-stored images, it can be determined that the attributes of ships and airplanes in the first image are both transportation tools. The first image acquired may also include airplanes and trees, and by comparing the first image with the pre-stored images, it can be determined that the attributes of the airplane in the first image are transportation tools, and the attributes of the trees in the first image are plants.

[0047] Step S106, segmenting the first image to obtain a second image of the target object.

[0048] In the above steps, the second images obtained may be one or more. When the number of target objects is one, one second image may be obtained; when the number of target objects is two, two second images may be obtained.

[0049] In an optional embodiment, the first image may be segmented according to the location of the target object to obtain a second image of the target object.

[0050] Exemplarily, when the target object is located in the upper left corner of the first image, the image of the target object in the upper left corner may be segmented out separately to obtain the second image.

[0051] In another optional embodiment, the first image can be segmented according to a preset segmentation rule. Since in most monitoring scenarios, the objects of interest are fixed, or the objects of interest are fixed for a period of time, even if they change, the magnitude of the change will not be too large; therefore, the scene monitored by the monitoring device generally will not change much, and the first image of the monitoring scene obtained will not change too much; therefore, the preset segmentation rule can be set in advance according to the location of the target object in the monitoring scene. When the first image corresponding to the monitoring scene is obtained, the preset segmentation rule corresponding to the monitoring scene is directly retrieved from the monitoring device to segment the first image, thereby improving the efficiency of segmenting the first image.

[0052] Step S108: sending the second image to the target display device based on the attributes of the target object.

[0053] The attributes of the objects contained in the images received by the target display device are the same.

[0054] In the above steps, the display device may be a screen in a monitoring room, or any device that can display images.

[0055] In an optional embodiment, after segmenting to obtain one or more second images, the second images can be sent to a target display device according to the attributes of the target objects in the second images, that is, second images containing target objects with the same attributes are sent to the same display device, and second images containing target objects with different attributes are sent to different display devices, so that target objects of the same type can be monitored through one display device, and target objects of the same type can be monitored centrally, thereby avoiding omissions and misjudgments by monitoring personnel due to too many types of target objects displayed on one display device.

[0056] Exemplarily, the second images obtained by segmentation are images of airplanes, ships, flowers, and trees, respectively. It can be determined that the attributes of airplanes and ships are transportation tools, and the attributes of flowers and trees are plants. Then, the images of airplanes and ships can be sent to one display device, and the images of flowers and trees can be sent to another display device, thereby realizing the monitoring of the same type of target objects in one display device, avoiding the situation where the monitoring personnel miss or misjudge the target objects due to too many types of target objects being displayed in one display device.

[0057] Through the above embodiment, a first image can be obtained first, wherein the first image includes: a target object; image recognition is performed on the first image to determine the attributes of the target object; the first image is segmented to obtain a second image of the target object; based on the attributes of the target object, the second image is sent to a target display device, wherein the attributes of the objects contained in the images received by the target display device are the same, thereby achieving the monitoring of objects with the same attributes in one target display device, allowing administrators to focus on observing target objects with the same attributes, thereby avoiding the situation where administrators miss or misjudge target objects with multiple attributes in multiple images at the same time, resulting in low efficiency in monitoring the target object, thereby solving the technical problem of [keywords].

[0058] Optionally, based on the attributes of the target object, sending the second image to the target display device includes: determining a target receiving end based on the attributes of the target object, wherein the target receiving end is connected to the target display device; sending the second image to the target receiving end, wherein the target receiving end is used to control the target display device to display the second image.

[0059] The receiving end in the above steps can receive the second images sent by multiple acquisition ends, and can control the target display device to display the processed images after processing the received second images. The multiple received second images can be spliced ​​and then the target display device can be controlled to display the spliced ​​second images.

[0060] In an optional embodiment, a target display device can be determined according to the attributes of the target object, and a target receiving end connected to the target display device can be determined according to the target display device, and a second image with the same attributes of the target object can be sent to the same target receiving end. The target receiving end can then send the received second image with the same attributes of the target object to the target display device, so as to display the target objects with the same attributes on a target display device, thereby reducing the types of objects monitored by monitoring personnel and improving the efficiency of monitoring personnel in monitoring target objects.

[0061] Optionally, determining the target receiving end based on the attribute of the target object includes: determining first identification information of the second image based on the attribute of the target object; and determining the target receiving end according to the first identification information.

[0062] In the above steps, the first identification information may be an ID (Identity document, identification number), wherein the first identification information is used to distinguish target objects with different attributes.

[0063] In an optional embodiment, second images with the same target object attributes have the same first identification information. Therefore, based on the first identification information of the second images, second images with the same target object attributes can be sent to a target receiving end. Through the target receiving end, second images with the same target object attributes can be displayed on a display device connected to the target receiving end, so as to display target objects with the same attributes on a target display device, thereby reducing the types of monitored objects and improving the efficiency of monitoring personnel in monitoring target objects.

[0064] In another optional embodiment, the correspondence between the first identification information and the target receiving end can be set in advance. When it is necessary to determine the target receiving end based on the first identification information, the correspondence between the first identification information and the target receiving end can be retrieved first. In this way, the target receiving end corresponding to the first identification information can be quickly determined, thereby improving the efficiency of determining the target receiving end.

[0065] Optionally, based on the attributes of the target object, determining the first identification information of the second image includes: matching the second image with multiple pre-stored images to obtain a successfully matched target image, wherein the attributes of the object contained in the target image are the same as the attributes of the target object; obtaining the second identification information of the successfully matched target image; and determining that the first identification information is the second identification information.

[0066] In the above steps, the pre-stored multiple images may be images of objects with different attributes pre-stored by the user, wherein the pre-stored multiple images may be images of different objects collected by a collection device, or images of different objects collected on the network.

[0067] Exemplarily, the pre-stored multiple images may be images in which the object attribute in the images is a vehicle, such as an image of a ship or an image of an airplane, or may be images in which the object attribute in the images is a plant, such as an image of a flower or an image of a tree.

[0068] The second identification information in the above step is used to distinguish objects in the pre-stored multiple images, and may be an ID set for each image in advance according to the attributes of each object. Exemplarily, the pre-stored multiple images may be images of ships, images of airplanes, images of flowers, etc. The ID of the image of the ship may be 001, the ID of the image of the airplane may be 002, and the ID of the image of the flower may be 003.

[0069] Exemplarily, after the second image is segmented, the second image can be matched with a pre-stored image of a ship, an image of an airplane, an image of a flower, etc. If the second image matches the image of the airplane successfully, that is, the successfully matched target image is the pre-stored image of the airplane, then the ID of the second image can be determined to be the ID of the image of the airplane, that is, the ID of the second image is 002.

[0070] Optionally, when the target receiving end receives multiple second images, the target receiving end is used to splice the multiple second images and control the target display device to display the spliced ​​image.

[0071] In the above steps, when the target receiving end receives multiple second images, the target receiving end splices the multiple second images and controls the target display device to display the spliced ​​images, so that the target objects with the same attributes in the second images can be displayed on the target display device at the same time, so that the monitoring personnel can monitor multiple target objects with the same attributes at the same time, thereby improving the monitoring efficiency.

[0072] Optionally, segmenting the first image to obtain a second image of the target object includes: acquiring position information of the target object in the first image; and segmenting the first image according to the position information to obtain the second image.

[0073] In the above steps, the position information of the target object may be the coordinate information of the target object, and a coordinate system may be established in the first image. Exemplarily, the coordinate system may be established by taking the lower left corner of the first image as the center of the circle, taking the bottom edge of the first image as the X-axis, and taking the left edge of the first image as the Y-axis.

[0074] In an optional embodiment, the coordinate information of the target object may be a set of coordinate points of the target object contour in the above-mentioned coordinate system, and the first image may be segmented according to the set of coordinate points of the target object contour, wherein the segmented first image may include the set of coordinate points of the target object contour.

[0075] In another optional embodiment, a segmentation line can be determined based on the coordinate point of the center of the target object in the first image, and the first image can be segmented based on the segmentation line to ensure that multiple target objects in the first image can be segmented smoothly. For example, when there are two target objects in the first image, a segmentation line can be determined based on the coordinate information of the two objects, and the first image can be segmented by the segmentation line. When there are three target objects in the first image, two segmentation lines can be determined based on the coordinate information of the three objects, and the first image can be segmented based on the two segmentation lines. It is also possible that when there is one target object in the first image, the first image is not segmented.

[0076] Optionally, segmenting the first image according to the position information to obtain the second image includes: determining a segmentation area where the target object is located in the first image according to the position information; and segmenting the first image according to the segmentation area to obtain the second image.

[0077] The segmented area in the above step may be an area where the target object can be fully displayed.

[0078] In an optional embodiment, the coordinate information of the target object can be the coordinates of the center of the target object in the above-mentioned coordinate system and a set of coordinate points of the target object's contour. The coordinate point of the center of the target object can be used as the center of the segmentation area, and the segmentation area can be expanded to completely contain the coordinate point of the target object's contour. At this time, the first image can be segmented according to the segmentation area.

[0079] In another optional embodiment, the segmented area can also be the minimum area in which the target object can be fully displayed, thereby reducing the area occupied by irrelevant background in the second image. By only displaying the target object in the second image, the monitoring personnel can monitor the target object more efficiently.

[0080] The segmented area in the above steps can be any shape such as a circle, a rectangle, a triangle, etc., and the shape of the segmented area is not limited here.

[0081] In another optional embodiment, the shape of the segmented area can be determined according to the shape of the target object; for example, if the target object is generally triangular, the image of the segmented area can be determined to be a triangle, thereby occupying the least segmented area to fully display the target object, thereby reducing the occupation of image resources.

[0082] In yet another optional embodiment, the shape of the segmented area may be a rectangle, which may facilitate the target receiving end to stitch the second image and display the stitched second image on a display device.

[0083] Optionally, sending the second image to the target receiving end includes: encoding the second image; and sending the encoded second image to the target receiving end, wherein the target receiving end is used to decode the encoded second image to obtain the second image.

[0084] In the above steps, the second image can be compressed by encoding the second image, thereby reducing the bandwidth resources occupied during the transmission of the second image.

[0085] In the above steps, the second image can be encoded according to the first identification information of the second image, so that the target receiving end can receive the encoded second image according to the first identification information, and decode the encoded second image according to the first identification information, so that the target receiving end controls the display device to display the second image with the same attributes of the target object.

[0086] In an optional embodiment, on the basis of encoding the second image, the second image can also be encrypted to improve the security of the second image transmission process and prevent someone from maliciously tampering with the second image. The encrypted second image is sent to the target receiving end, wherein the target receiving end is used to decrypt the encrypted second image and decode the second image to obtain the second image.

[0087] Optionally, before acquiring the first image, the method also includes: acquiring an original image set, wherein the original image set is a set of images acquired by an acquisition device; matching each original image in the original image set with a plurality of pre-stored images; and if a target original image in the original image set successfully matches a pre-stored target image, determining that the target original image is the first image.

[0088] In an optional embodiment, each pre-stored image contains a target object, wherein the multiple pre-stored images may be pre-stored by a user, or may be images containing target objects with different attributes acquired by a collection device.

[0089] In another optional embodiment, the original image sets may be classified according to the acquisition devices, with one acquisition device corresponding to one original image set, or multiple acquisition devices corresponding to one original image set.

[0090] In another optional embodiment, the original image set can also be established according to the time sequence. For example, the acquisition device can put the images acquired within one day into an original image set, so that the monitoring personnel can retrieve the original image set according to the date, which is convenient for the monitoring personnel to view the original images in the original image set.

[0091] In another optional embodiment, a set of original images of a specified date may be obtained first, and an original image set of the most recent date may be selected, and each original image in the original image set may be matched with a plurality of pre-stored images; wherein each pre-stored image has a target object, and when a target original image in the original image set has a target object having the same attributes as a target image in the pre-stored target image, it may be determined that the target original image in the original set successfully matches the pre-stored target image, and at this time, it may be determined that the target original image is the first image, and thus, in the subsequent processing of the first image, it may be ensured that the target object exists in the first image.

[0092] Exemplarily, when there are airplanes and ships in the target original image in the original image set, when matching with the pre-stored aircraft image, it can be determined that the airplane in the target original image successfully matches the airplane in the pre-stored aircraft image. At this time, it can be determined that there is an airplane with the same attributes as the pre-stored target image in the target original image, that is, it can be determined that the target original image is the first image. In this way, after the first image is subsequently processed, the airplane in the first image can be displayed on a display device for monitoring by monitoring personnel.

[0093] In another optional embodiment, if the target original image in the original image set does not successfully match the pre-stored target image, it can be determined that the target original image does not contain a target object with the same attributes as the pre-stored target image, that is, the target original image does not contain the target object that the monitoring personnel needs to monitor. At this time, the original image may not be displayed, which helps to reduce the burden on the monitoring personnel to monitor the target object.

[0094] Combine the following Figure 2 and Figure 4 A preferred embodiment of the present invention is described in detail. Figure 2 As shown, the method may include the following steps:

[0095] Step S201: the S1 module of the acquisition terminal 1 acquires the image taken by the image source device and sends the acquired image data to the processing module.

[0096] In the above steps, the S1 module of the acquisition terminal 1 acquires the image captured by the image source device and sends the acquired image data to the processing module. It should be noted that one S1 module corresponds to one image source device.

[0097] like Figure 3 As shown, the image data collected by the S1 module in the acquisition terminal 1 includes the target object A and the target object B; the image data collected by the S1 module in the acquisition terminal 2 includes the target object a and the target object b.

[0098] Step S202: the processing module identifies each target object from the received image data according to the preset target object image.

[0099] It should be noted that, in most monitoring scenarios, the target objects are fixed or fixed for a period of time, and even if they change, the magnitude of the change will not be too large. Therefore, the images of the target objects can be preset in the processing module so that the processing module can identify each target object from the image. Exemplarily, the target objects include buildings, vehicles, and a specific area. The images of buildings, vehicles, and specific areas can be preset in the processing module.

[0100] In the above steps, the processing module identifies each target object from the image data sent from the S1 module according to the preset image of the target object.

[0101] Step S203: the processing module segments the image data according to the positions of the identified target objects in the image to generate a plurality of thumbnail data.

[0102] In the above steps, the processing module has identified each target object in the image, and can determine the area where each target object is located according to the position of each target object in the image, and then divide the image into multiple small images according to the area where each target object is located.

[0103] Optionally, the bounding rectangle of each target object may be determined as the location. Considering the user experience, the four sides of the bounding rectangle may be enlarged by several dozen pixels, and the enlarged rectangle is used as the location.

[0104] refer to Figure 4 , Figure 4 The target objects in the image are airplanes, trees, and streetlights. The area contained in the bounding rectangle of the target object is the target object area. Rectangle 1 is the area where the airplane is, rectangle 2 is the area where the streetlight is, and rectangle 3 is the area where the tree is. The image can be divided into three small images according to the three areas, and each small image includes a target object.

[0105] Step S204: the processing module determines the category ID of each thumbnail data according to the category of the target object included in each thumbnail data, and sends each thumbnail data to the S2 module according to the category ID carried by the thumbnail data.

[0106] It should be noted that each target object image preset in the processing module corresponds to a category, and each category corresponds to a category ID. For example, if the target object is an airplane, the category corresponding to the airplane image is transportation. For another example, if the target object is a ship, the category corresponding to the ship image is transportation. For another example, if the target object is a building, the category corresponding to the building image is building. The category ID corresponding to the transportation category is 001, and the category ID corresponding to the building category is 002.

[0107] In the above steps, the processing module determines the category ID of the thumbnail of each target object according to the category ID corresponding to the preset image of the target object. Specifically, the processing module uses the preset image of the target object to identify the target object in the image. If the identification is successful, the category ID of the preset image of the target object can be determined as the category ID of the thumbnail including the identified target object.

[0108] Exemplarily, the processing module successfully identifies the target object in the image based on the image of the preset target object, and the A picture generated by image segmentation includes the target object; it is known that the category ID corresponding to the image of the preset target object is 001; then, the category ID of the A picture is 001.

[0109] Optionally, the target objects included in the small images with the same category ID belong to the same category.

[0110] refer to Figure 3 The processing module of acquisition end 1 divides the image into picture A including target object A, and picture B including target object B; the processing module of acquisition end 2 divides the image into picture a including target object a, and picture b including target object b.

[0111] Step S205, the S2 module encodes each thumbnail data respectively to generate multiple thumbnail encoded data; the acquisition end sends each thumbnail encoded data to the corresponding receiving end according to the preset allocation rule and the category ID of each thumbnail data.

[0112] The preset allocation rules in the above steps include the correspondence between the category ID of the thumbnail and the receiving end. For example, if monitoring room 1 is responsible for monitoring the target objects of the vehicle category, then the category ID of the vehicle can be set to correspond to the receiving end of monitoring room 1; if monitoring room 2 is responsible for monitoring the target objects of the building category, then the category ID of the building can be set to correspond to the receiving end of monitoring room 2.

[0113] refer to Figure 3 , set the type ID of picture A to 001, the type ID of picture B to 002, the type of picture a to 001, and the type of picture b to 004; the preset allocation rule is that type ID = 001 corresponds to receiving end 1, and type ID = 002 corresponds to receiving end 2; then, acquisition end 1 can send the encoded data of picture A to receiving end 1, and send the encoded data of picture B to receiving end 2, and acquisition end 2 can send the encoded data of picture a to receiving end 1, and send the encoded data of picture b to receiving end 2.

[0114] Step S206: The receiving end decodes the received thumbnail data to obtain image data; and displays the image data on a display device.

[0115] like Figure 3 As shown, after the R module of the receiving end 1 decodes the received coded data of the A picture and the a picture, the A picture and the a picture are displayed on the display device 1, and after the R module of the receiving end 2 decodes the received coded data of the B picture and the b picture, the B picture and the b picture are displayed on the display device 2. Each small picture can be displayed on each screen or on the same screen.

[0116] It should be noted that in the above steps, one receiving end can receive the same type of target objects in images captured by multiple image source devices. For example, if the category corresponding to the receiving end is vehicles, the receiving end receives small images including vehicles segmented from the images captured by each image source device. This is conducive to the administrator to monitor each target object efficiently and with high quality.

[0117] refer to Figure 3 , Figure 3 FIG. 1 is a schematic diagram of an image processing system of the present invention. Figure 3 As shown, the acquisition end 1 is connected to the image source device 1, and the acquisition end 2 is connected to the image source device 2; the acquisition end 1 and the acquisition end 2 include an S1 module, a processing module and an S2 module; the S1 module is used to acquire images, the processing module is used to identify the target object from the image, and segment the image based on the target object to generate multiple small images, and the S2 module is used to encode each small image separately; the receiving end 1 is connected to the display device 1, and the receiving end 2 is connected to the display device 2, and the receiving end includes an R module, and the R module is used to decode the received encoded data and display the decoded restored image on the display device.

[0118] Example 2

[0119] According to an embodiment of the present invention, an image processing device is also provided, which can execute the image processing method in the above embodiment. The specific implementation method and preferred application scenario are the same as those in the above embodiment and will not be described in detail here.

[0120] Figure 5 is a schematic diagram of an image processing device according to an embodiment of the present invention. Figure 5 As shown, the device comprises:

[0121] The acquisition module 52 is used to acquire a first image, wherein the first image includes: a target object;

[0122] The recognition module 54 is used to perform image recognition on the first image to determine the attributes of the target object;

[0123] A segmentation module 56, configured to segment the first image to obtain a second image of the target object;

[0124] The sending module 58 is used to send the second image to the target display device based on the attributes of the target object, wherein the attributes of the objects contained in the images received by the target display device are the same.

[0125] Optionally, the sending module includes: a determination unit, used to determine the target receiving end based on the attributes of the target object, wherein the target receiving end is connected to the target display device; a sending unit, used to send the second image to the target receiving end, wherein the target receiving end is used to control the target display device to display the second image.

[0126] Optionally, the determination unit includes: a first determination subunit, used to determine first identification information of the second image based on the attribute of the target object; and a second determination subunit, used to determine the target receiving end according to the first identification information.

[0127] Optionally, the first determination subunit is used to match the second image with multiple pre-stored images to obtain a successfully matched target image, wherein the attributes of the object contained in the target image are the same as the attributes of the target object; obtain second identification information of the successfully matched target image; and determine that the first identification information is the second identification information.

[0128] Optionally, the apparatus further includes: when the target receiving end receives multiple second images, the target receiving end is used to splice the multiple second images and control the target display device to display the spliced ​​image.

[0129] Optionally, the segmentation module includes: an acquisition unit, used to acquire position information of the target object in the first image; and a segmentation unit, used to segment the first image according to the position information to obtain the second image.

[0130] Optionally, the segmentation unit includes: a third determination subunit, used to determine a segmentation area where the target object is located in the first image according to the position information; and a segmentation subunit, used to segment the first image according to the segmentation area to obtain the second image.

[0131] Optionally, the sending unit includes: an encoding subunit, used to encode the second image; and a sending subunit, used to send the encoded second image to a target receiving end, wherein the target receiving end is used to decode the encoded second image to obtain the second image.

[0132] Optionally, the device also includes: an acquisition module for acquiring an original image set, wherein the original image set is a set of images acquired by an acquisition device; a matching module for matching each original image in the original image set with a plurality of pre-stored images; and a determination module for determining that a target original image in the original image set is a first image when a target original image in the original image set is successfully matched with a pre-stored target image.

[0133] Example 3

[0134] According to an embodiment of the present invention, an image processing system is also provided. The system can execute the image processing method in the above embodiment. The specific implementation method and preferred application scenario are the same as those in the above embodiment and will not be described in detail here.

[0135] Figure 6 is a schematic diagram of an image processing system according to an embodiment of the present invention. Figure 6 As shown, the system includes:

[0136] The image acquisition device 60 is used to acquire a first image, wherein the first image includes: a target object;

[0137] The processor 62 is provided in the image acquisition device 60 and is used to perform image recognition on the first image, determine the attribute of the target object, and segment the first image to obtain a second image of the target object;

[0138] A sending module 64, provided in the image acquisition device 60, for sending the second image based on the attributes of the target object;

[0139] The target display device 66 is used to receive the second image sent by the sending module 64, wherein the attributes of the objects contained in the image received by the target display device 66 are the same.

[0140] Alternatively, if Figure 7 As shown, the system also includes:

[0141] The acquisition device 70 is connected to the image acquisition device 60 and is used to acquire the original image;

[0142] The target receiving end 72 is connected to the target display device 66, wherein the target receiving end 72 is determined by the image acquisition device 60 based on the attributes of the target object, and is used to receive the second image sent by the sending module 64, and to control the target display device 66 to display the second image.

[0143] Example 4

[0144] According to an embodiment of the present invention, a computer-readable storage medium is further provided. The computer-readable storage medium includes a stored program. When the program is executed, the device where the computer-readable storage medium is located is controlled to execute the image processing method in the above-mentioned embodiment 1.

[0145] Example 5

[0146] According to an embodiment of the present invention, a processor is further provided, and the processor is used to run a program, wherein the image processing method in the above-mentioned embodiment 1 is executed when the program is run.

[0147] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0148] In the above embodiments of the present invention, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0149] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units can be a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0150] 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 units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0151] In addition, each functional unit in each embodiment of the present invention 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.

[0152] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, magnetic disk or optical disk and other media that can store program codes.

[0153] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. An image processing method, characterized in that: include: Acquire a first image, wherein the first image includes: a target object; Performing image recognition on the first image to determine the attributes of the target object; Segmenting the first image based on the position of the target object in the first image to obtain a second image of the target object; Based on the attributes of the target object, the second image is sent to a target receiving end, wherein the target receiving end is used to control a target display device connected to the target receiving end to display the second image, and the same target display device is used to display the target object with the same attributes.

2. The method according to claim 1, characterized in that Based on the attribute of the target object, sending the second image to a target display device includes: Determining a target receiving end based on the attribute of the target object, wherein the target receiving end is connected to the target display device; The second image is sent to the target receiving end, wherein the target receiving end is used to control the target display device to display the second image.

3. The method according to claim 2, characterized in that Based on the attribute of the target object, determining the target receiving end includes: Determining first identification information of the second image based on the attribute of the target object; The target receiving end is determined according to the first identification information.

4. The method according to claim 3, characterized in that Determining first identification information of the second image based on the attribute of the target object includes: Matching the second image with a plurality of pre-stored images to obtain a successfully matched target image, wherein the attributes of the object contained in the target image are the same as the attributes of the target object; Acquire second identification information of the successfully matched target image; Determine that the first identification information is the second identification information.

5. The method according to claim 2, characterized in that: In the case that the target receiving end receives a plurality of second images, the target receiving end is used to splice the plurality of second images and control the target display device to display the spliced ​​images.

6. The method according to claim 1, characterized in that Segmenting the first image to obtain a second image of the target object includes: Acquire location information of the target object in the first image; The first image is segmented according to the position information to obtain the second image.

7. The method according to claim 6, characterized in that Segmenting the first image according to the position information to obtain the second image includes: Determine a segmented area where the target object is located in the first image according to the position information; The first image is processed according to the segmented areas to obtain the second image.

8. The method according to claim 2, characterized in that: Sending the second image to the target receiving end includes: encoding the second image; The encoded second image is sent to the target receiving end, wherein the target receiving end is used to decode the encoded second image to obtain the second image.

9. The method according to claim 1, characterized in that: Before acquiring the first image, the method further includes: Acquire an original image set, wherein the original image set is a set of images acquired by an acquisition device; Matching each original image in the original image set with a plurality of pre-stored images; If the target original image in the original image set successfully matches the pre-stored target image, the target original image is determined to be the first image.

10. An image processing device, characterized in that: include: An acquisition module, configured to acquire a first image, wherein the first image includes: a target object; A recognition module, used to perform image recognition on the first image to determine the attributes of the target object; a segmentation module, configured to segment the first image based on the position of the target object in the first image to obtain a second image of the target object; A sending module sends the second image to a target receiving end based on the attributes of the target object, wherein the target receiving end is used to control a target display device connected to the target receiving end to display the second image, and the same target display device is used to display the target object with the same attributes.

11. An image processing system, characterized in that: include: An image acquisition device, used to acquire a first image, wherein the first image includes: a target object; a processor, arranged in the image acquisition device, configured to perform image recognition on the first image, determine the attribute of the target object, and segment the first image based on the position of the target object in the first image to obtain a second image of the target object; A sending module, arranged in the image acquisition device, for sending the second image based on the attribute of the target object; The target display device is used to receive the second image sent by the sending module, wherein the attributes of the objects contained in the image received by the target display device are the same.

12. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored program, wherein when the program is executed, the device where the computer-readable storage medium is located is controlled to execute the image processing method according to any one of claims 1 to 9.

13. A processor, characterized in that: The processor is used to run a program, wherein the program executes the image processing method according to any one of claims 1 to 9 when running.

Images