Image processing method, device, electronic device and storage medium

Abstract

The present disclosure provides an image processing method, apparatus, electronic device, storage medium, and program product, relating to the fields of artificial intelligence technology, particularly image processing and autonomous driving technology. A specific implementation scheme comprises: obtaining a first initial result based on image information of a target vehicle image, wherein part of the target vehicle information in the target vehicle image is obscured; obtaining a second initial result based on vehicle contour information in the target vehicle image; and determining a target result based on the first initial result and the second initial result.

Description

Technical Field

[0001] The present disclosure relates to the fields of artificial intelligence technology, in particular to the fields of image processing and autonomous driving technology, and specifically to image processing methods, devices, electronic devices, storage media, and program products. Background Art

[0002] Computer vision technology offers enormous potential for improving image processing capabilities. Computer vision is the study of how electronic devices can "see," using cameras and computers to replace the human eye in identifying, tracking, and measuring objects. This technology offers significant benefits for the development of applications in public safety, information security, financial security, and driving safety. Summary of the Invention

[0003] The present disclosure provides an image processing method, apparatus, electronic device, storage medium, and program product.

[0004] According to one aspect of the present disclosure, an image processing method is provided, comprising: obtaining a first initial result based on image information of a target vehicle image, wherein part of information of a target vehicle in the target vehicle image is blocked; obtaining a second initial result based on vehicle contour information of the target vehicle image; and determining a target result based on the first initial result and the second initial result.

[0005] According to another aspect of the present disclosure, an image processing device is provided, including: a first processing module for obtaining a first initial result based on image information of a target vehicle image, wherein part of the information of the target vehicle in the target vehicle image is blocked; a second processing module for obtaining a second initial result based on vehicle contour information of the target vehicle image; and a determination module for determining a target result based on the first initial result and the second initial result.

[0006] According to another aspect of the present disclosure, an electronic device is provided, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform a method as disclosed herein.

[0007] According to another aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to cause the computer to execute the method of the present disclosure.

[0008] According to another aspect of the present disclosure, a computer program product is provided, comprising a computer program, wherein the computer program implements the method of the present disclosure when executed by a processor.

[0009] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present disclosure, nor are they intended to limit the scope of the present disclosure. Other features of the present disclosure will become readily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] The accompanying drawings are used to better understand the present invention and do not constitute a limitation of the present invention.

[0011] Figure 1 Schematically illustrates an exemplary system architecture to which the information processing method and apparatus according to an embodiment of the present disclosure may be applied;

[0012] Figure 2 The flowchart of the information processing method according to the embodiment of the present disclosure is schematically shown;

[0013] Figure 3 A schematic diagram of a scenario for acquiring a target vehicle image according to an embodiment of the present disclosure is schematically shown;

[0014] Figure 4 The following schematically shows a flow chart of determining a target vehicle image according to an embodiment of the present disclosure;

[0015] Figure 5 Schematically shows a flow chart for determining a second initial result according to an embodiment of the present disclosure;

[0016] Figure 6 A block diagram schematically shows an information processing device according to an embodiment of the present disclosure; and

[0017] Figure 7 The block diagram schematically shows an electronic device suitable for implementing the information processing method according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0018] The following description of exemplary embodiments of the present disclosure is made in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding. These details should be considered as merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0019] The present disclosure provides an image processing method, apparatus, electronic device, storage medium, and program product.

[0020] According to an embodiment of the present disclosure, an image processing method is provided, comprising: obtaining a first initial result based on image information of a target vehicle image, wherein part of information of a target vehicle in the target vehicle image is blocked; obtaining a second initial result based on vehicle contour information of the target vehicle image; and determining a target result based on the first initial result and the second initial result.

[0021] In the technical solution disclosed herein, the collection, storage, use, processing, transmission, provision, disclosure and application of user personal information involved comply with the provisions of relevant laws and regulations, take necessary confidentiality measures, and do not violate public order and good morals.

[0022] In the technical solution disclosed herein, the user's authorization or consent is obtained before obtaining or collecting the user's personal information.

[0023] Figure 1 An exemplary system architecture to which the information processing method and apparatus according to an embodiment of the present disclosure can be applied is schematically shown.

[0024] It should be noted that Figure 1 The examples shown are merely examples of system architectures to which the embodiments of the present disclosure may be applied, to help those skilled in the art understand the technical content of the present disclosure, but do not mean that the embodiments of the present disclosure may not be used in other devices, systems, environments or scenarios.

[0025] like Figure 1 As shown, the system architecture 100 according to this embodiment may include an information collection device 101, a network 102, and a server 103. The network 102 is used to provide a medium for a communication link between the information collection device 101 and the server 103. The network 102 may include various connection types, such as wired and / or wireless communication links, etc.

[0026] The information collection device 101 can interact with the server 103 via the network 102 to receive or send messages, etc. The information collection device 101 and the server 103 can be installed with applications for enabling communication between the two, such as map applications, image processing applications, trajectory prediction applications, etc. (only as examples).

[0027] The information collection device 101 may be a device with image or video collection capabilities, including but not limited to a camera or driving recorder mounted on, for example, an autonomous driving vehicle 104 , or a road camera installed on a road.

[0028] Server 103 can be integrated into the autonomous vehicle 104 or located at a remote location capable of communicating with the vehicle terminal. It can be implemented as a distributed server cluster consisting of multiple servers or as a single server, which will not be discussed further here.

[0029] The server 103 may be a server that provides various services, such as a background management server that provides image processing support for the target vehicle image sent by the information acquisition device 101 (for example only). For example, the server 103 receives the target vehicle image transmitted by the information acquisition device 101 via the network 102. When it is determined that part of the target vehicle information in the target vehicle image is blocked, a first initial result can be obtained based on the image information of the target vehicle image; and a second initial result can be obtained based on the vehicle contour information of the target vehicle image. Based on the first initial result and the second initial result, a target result is determined. The target result is then used to assist the autonomous driving vehicle in making driving decisions and obtaining a corresponding obstacle avoidance driving plan.

[0030] It should be noted that the information processing method provided in the embodiment of the present disclosure can generally be executed by the server 103. Accordingly, the information processing device provided in the embodiment of the present disclosure can also be set in the server 103.

[0031] It should be understood that Figure 1 The number of information collection devices, networks and servers in the embodiment is merely illustrative. Any number of information collection devices, networks and servers may be used as required.

[0032] It should be noted that the sequence numbers of the operations in the following method are only used to indicate the operation for the purpose of description, and should not be regarded as indicating the order in which the operations should be performed. Unless explicitly stated, the method does not need to be performed in the order shown.

[0033] Figure 2 The flowchart of the information processing method according to the embodiment of the present disclosure is schematically shown.

[0034] like Figure 2 As shown, the method includes operations S210 to S230.

[0035] In operation S210 , a first initial result is obtained based on image information of a target vehicle image, wherein part of information of the target vehicle in the target vehicle image is blocked.

[0036] In operation S220 , a second initial result is obtained based on the vehicle contour information of the target vehicle image.

[0037] In operation S230 , a target result is determined based on the first initial result and the second initial result.

[0038] According to embodiments of the present disclosure, image information may refer to representative or characteristic pixel information within an image. Image information may include, for example, color information, texture information, shape information, and spatial relationship information. Features can be extracted from image information through feature extraction, allowing a computer to perform tasks such as detection and recognition using the extracted features.

[0039] According to embodiments of the present disclosure, vehicle profile information may refer to: vehicle appearance information. For example, the vehicle's appearance information displayed in a two-dimensional image. Vehicle profile information may include information such as the vehicle's shape, the ratio of the vehicle's length, width, and height, and the curvature of its curves. Different types of vehicles have different vehicle profile information. Vehicle type can be identified based on vehicle profile information.

[0040] According to an embodiment of the present disclosure, the first initial result, the second initial result, and the target result can all be used to characterize the category of the target vehicle in the target vehicle image. The target vehicle category can include police cars, tank trucks, coal trucks, muck trucks, concrete trucks, sanitation trucks, fire trucks, ambulances, and the like.

[0041] According to other embodiments of the present disclosure, a first initial result may be obtained solely based on the image information of the target vehicle image, and the first initial result may be used as the target result. However, this is not a limitation. A second initial result may also be obtained solely based on the vehicle outline information of the target vehicle image, and the second initial result may be used as the target result.

[0042] According to embodiments of the present disclosure, partial occlusion of target vehicle information in a target vehicle image may refer to the loss of partial information about the target vehicle. For example, a portion of the target vehicle's body may be obscured, such that only information about the front or rear of the target vehicle, for example, is visible in the image. The partial information about the target vehicle may include partial image information and partial vehicle outline information.

[0043] According to an embodiment of the present disclosure, when part of the information of the target vehicle in the target vehicle image is blocked, different processing means are used to process different information respectively to determine the target result, that is, the target result is determined based on the first initial result and the second initial result. Compared with using a single processing means to process a single information to determine the target result, the accuracy of the result is improved.

[0044] Figure 3 A schematic diagram of a scenario for acquiring a target vehicle image according to an embodiment of the present disclosure is schematically shown.

[0045] like Figure 3As shown, an information collection device mounted on autonomous vehicle 310 can be used to collect environmental information on the road, such as road information, pedestrian information, and vehicle information. Based on the collected environmental information, the type and status of obstacles can be determined. This in turn guides the autonomous vehicle 310's driving decisions, improving autonomous driving safety.

[0046] like Figure 3 As shown, the camera 350 installed at the intersection can also be used to collect information about the environment around the intersection. Based on the real-time collected driving status information of vehicles passing through the intersection, it is determined whether the vehicle has violated the rules such as speeding, overweight, abnormal trajectory, running a red light, etc., playing a monitoring and prevention role.

[0047] Taking the information collection device mounted on autonomous vehicle 310 as an example, autonomous vehicle 310 may acquire a target vehicle image with vehicle 330 as the target vehicle while collecting environmental information, such as environmental information from the oncoming lane 320. However, due to a pedestrian 340 crossing the sidewalk between vehicle 330 and autonomous vehicle 310, a portion of vehicle 330 is obscured in the acquired target vehicle image. Consequently, part of the information about target vehicle 330 is obscured in the resulting target vehicle image.

[0048] According to the embodiments of the present disclosure, as the number of vehicles traveling on the road, pedestrians walking, etc. increases, part of the vehicle information of the target vehicle in the target vehicle image is likely to be blocked. In this case, the accuracy of determining the target result based on the first initial result and the second initial result provided by the embodiments of the present disclosure is improved, and the scope of application is getting wider and wider.

[0049] Figure 4 The figure schematically shows a flow chart of acquiring a target vehicle image according to another embodiment of the present disclosure.

[0050] like Figure 4 As shown, an information collection device may be used to collect environmental information on the road to obtain an initial vehicle image 410. The initial vehicle image 410 includes a target vehicle 420, multiple other vehicles 430 other than the target vehicle 420, and other objects such as a road 440.

[0051] like Figure 4 As shown, the initial vehicle image 410 can be detected to determine a candidate region for the target vehicle 420. Based on the candidate region, other objects other than the target vehicle in the initial vehicle image, such as multiple other vehicles, can be cropped out to obtain a target vehicle image 450 including the target vehicle with background information cropped out.

[0052] like Figure 4 As shown, the candidate area may refer to the location area of ​​the target vehicle, which may be selected using a detection frame 460. The type and shape of the detection frame are not limited. Figure 4 As shown, detection frame 460 is located outside target vehicle 420 and is rectangular. The position information of the four corners determines the detection frame information, thereby identifying the candidate area. However, this is not a limitation. The detection frame can also be located outside the target vehicle, bounded by the outer edge of the target vehicle and separated by a predetermined distance from the outer edge of the target vehicle. Any detection frame that can exclude background information in the initial vehicle image, such as other objects besides the target vehicle, will suffice.

[0053] According to embodiments of the present disclosure, a neural network model can be used to detect an initial vehicle image and determine candidate regions for the target vehicle. For example, the neural network model may include YOLOv3 (You Only Look Once, real-time object detection model), but is not limited thereto and may also include YOLOv4 or YOLOv5. Any neural network model capable of detecting candidate regions will suffice.

[0054] By using the method for determining the target vehicle image provided by the embodiment of the present disclosure, background information and other object information in the initial vehicle image can be removed, reducing the influence of pixel information and contour information of non-target vehicles, thereby improving recognition accuracy while reducing the amount of data processing.

[0055] According to other embodiments of the present disclosure, before executing operation S210, it may be determined whether the target vehicle is obscured based on the image information of the target vehicle image or the vehicle profile information of the target vehicle image. If it is determined that the target vehicle is obscured, the operation of determining the target result based on the first initial result and the second initial result provided in the embodiment of the present disclosure is executed. If it is determined that the target vehicle is not obscured, the first initial result may be used as the target result, and the operation of obtaining the second initial result based on the vehicle profile information of the target vehicle image may be abandoned; or the second initial result may be used as the target result, and the operation of obtaining the first initial result based on the image information of the target vehicle image may be abandoned.

[0056] According to an embodiment of the present disclosure, determining a target result based on a first initial result and a second initial result may include: if the first initial result and the second initial result are the same, using the first initial result as the target result; if the first initial result and the second initial result are the same, determining a confidence level of the first initial result and a confidence level of the second initial result; and using the result with a higher confidence level as the target result.

[0057] By using the image processing method provided by the embodiment of the present disclosure, different processing methods can be determined to identify the category of the target vehicle based on whether the target vehicle in the target vehicle image is obscured, thereby improving recognition accuracy and processing efficiency.

[0058] According to an embodiment of the present disclosure, for operation S210 , obtaining the first initial result based on image information of the target vehicle image may include: inputting the target vehicle image into an image processing model to obtain the first initial result.

[0059] According to the embodiments of the present disclosure, the type of image processing model is not limited. For example, it may include ResNet34 (residual network with 34 hidden layers), but is not limited to this. It may also include VGG16 (Visual Geometry Group, computer vision group), MobileNet (lightweight deep neural network), etc. Any model that can obtain a first initial result representing the category of the target vehicle based on the target vehicle image will be sufficient.

[0060] Figure 5 The flowchart of determining the second initial result according to an embodiment of the present disclosure is schematically shown.

[0061] like Figure 5 As shown, the method includes operations S510 to S530.

[0062] In operation S510 , blocked vehicle contour information of the target vehicle is determined based on the vehicle contour information of the target vehicle image to obtain the target vehicle contour information.

[0063] In operation S520, it is determined whether target reference vehicle profile information matching the target vehicle profile information exists in the reference vehicle profile information set. If it is determined that target reference vehicle profile information matching the target vehicle profile information exists in the reference vehicle profile information set, operation S530 is performed; if it is determined that target reference vehicle profile information matching the target vehicle profile information does not exist in the reference vehicle profile information set, operation S540 is performed.

[0064] In operation S530 , a second initial result is obtained based on the target reference vehicle profile information.

[0065] In operation S540 , the target vehicle contour information is input into a contour processing model to obtain a second initial result.

[0066] According to an embodiment of the present disclosure, before performing operation S510, the image processing method may further include: determining vehicle contour information based on the target vehicle image. A vehicle contour edge detection algorithm may be used to perform edge detection processing on the target vehicle image to obtain vehicle contour information. The vehicle contour edge detection algorithm may include a Canny edge detection algorithm, but is not limited thereto, and may also include a Sobel edge detection algorithm or a Prewitt edge detection algorithm. The type of vehicle contour edge detection algorithm is not limited, as long as it is a detection algorithm that can detect vehicle contour information from the target vehicle image.

[0067] According to an embodiment of the present disclosure, during operation S510, the occluded vehicle outline information of the target vehicle can be obtained by fitting based on the existing vehicle outline information of the target vehicle image. The target vehicle outline information, i.e., the complete outline information of the target vehicle, is obtained based on the existing vehicle outline information and the outline information of the occluded vehicle restored by fitting.

[0068] According to an embodiment of the present disclosure, based on the streamlined characteristics of the vehicle's outer contour, one or more of a circle fitting method, a curve fitting method, and a straight line fitting method can be used to fit the obscured vehicle contour information of the target vehicle based on the existing vehicle contour information, thereby realizing the restoration of the obscured vehicle contour information.

[0069] According to other embodiments of the present disclosure, operations S520, S530, and S540 can be performed based on existing vehicle profile information to obtain a second initial result. For example, a determination is made as to whether target baseline vehicle profile information matching the vehicle profile information in the target vehicle image exists in the baseline vehicle profile information set. If it is determined that target baseline vehicle profile information matching the target vehicle profile information exists in the baseline vehicle profile information set, a second initial result is obtained based on the target baseline vehicle profile information. If it is determined that target baseline vehicle profile information matching the target vehicle profile information does not exist in the baseline vehicle profile information set, the vehicle profile information of the target vehicle image is input into a profile processing model to obtain a second initial result.

[0070] According to an embodiment of the present disclosure, compared with obtaining the second initial result by using the vehicle contour information in the existing target vehicle image, obtaining the second initial result by using the target vehicle contour information can obtain more vehicle contour information. The higher the integrity of the information used, the higher the accuracy of the second initial result.

[0071] According to an embodiment of the present disclosure, in operations S520 and S530, baseline vehicle profile information for various types of vehicles may be pre-acquired to obtain a baseline vehicle profile information set. Multiple pieces of baseline vehicle profile information in the baseline vehicle profile information set may be mapped to the categories of baseline vehicles. When multiple pieces of target baseline vehicle profile information matching the target vehicle profile information are determined from the baseline vehicle profile information set, the categories of the baseline vehicles matching the target baseline vehicle profile information may be determined based on the mapping relationship, thereby determining a second initial result.

[0072] According to an embodiment of the present disclosure, determining multiple target reference vehicle profile information that matches the target vehicle profile information from the reference vehicle profile information set may include: performing similarity calculations on the multiple reference vehicle profile information in the reference vehicle profile information set and the target vehicle profile information, and selecting the reference vehicle profile information with the highest similarity or with the similarity reaching a similarity threshold as the target reference vehicle profile information.

[0073] According to an embodiment of the present disclosure, similarity calculation may be: scaling the baseline vehicle profile information or the target vehicle profile information in equal proportion, and then performing profile matching between the baseline vehicle profile information and the target vehicle profile information to obtain a similarity result. However, it is not limited to this. Similarity calculation may also be: extracting the features of the baseline vehicle profile information and the target vehicle profile information respectively to obtain their respective feature vectors. Calculating the similarity between the feature vector of the baseline vehicle profile information and the feature vector of the target vehicle profile information to obtain a similarity result. There is no limitation on the method of similarity calculation, as long as it is based on the target vehicle profile information and can determine the target baseline vehicle profile information from the baseline vehicle profile information set.

[0074] According to an embodiment of the present disclosure, the reference vehicle profile information in the reference vehicle profile information set is not exhaustive. Therefore, there may be target reference vehicle profile information that cannot be matched with the target vehicle profile information from the reference vehicle profile information set. In this case, operation S540 may be performed. In operation S540, the vehicle profile information of the target vehicle image may be input into the profile processing model to obtain a second initial result.

[0075] According to the embodiments of the present disclosure, the network structure of the contour processing model is not limited, as long as the model can obtain the second initial result representing the category of the target vehicle based on the target vehicle contour information.

[0076] For example, the contour processing model may include a convolutional neural network. For example, the contour processing model may include a cascaded first convolution layer, a first pooling layer, a second convolution layer, a second pooling layer, a third convolution layer, a fully connected layer, and an activation function. The sizes of the convolution kernels of the first convolution layer, the second convolution layer, and the third convolution layer are not limited and can be the same or different. However, this is not limited to this. The contour processing model may also include a recurrent neural network or a tree model.

[0077] According to an embodiment of the present disclosure, a method for generating a training sample is further provided, comprising: fusing a plurality of vehicle images with a background image to obtain a sample image, wherein at least two of the plurality of vehicle images in the sample image partially overlap.

[0078] According to an embodiment of the present disclosure, each of the multiple vehicle images may include only vehicle information. By using the vehicle images including only vehicle information to generate sample images, impurity information can be filtered out, thereby improving training efficiency.

[0079] According to the embodiments of the present disclosure, by fusing at least two partially overlapping vehicle images with a background image, the number and types of generated sample images can be increased, thereby increasing the data volume of training samples and avoiding overfitting.

[0080] According to embodiments of the present disclosure, the vehicle categories in sample images can be used as labels, and the labels and sample images can be used as training samples. The training samples are used to train an image processing model and a contour processing model, respectively. This allows the parameters of the image processing model and the contour processing model to be adjusted, achieving specialized tuning and improving the accuracy of the trained image processing model and the trained contour processing model.

[0081] Figure 6 The block diagram schematically shows an information processing device according to an embodiment of the present disclosure.

[0082] like Figure 6 As shown, the image processing apparatus 600 may include a first processing module 610 , a second processing module 620 , and a determination module 630 .

[0083] The first processing module 610 is configured to obtain a first initial result based on image information of a target vehicle image, wherein part of the information of the target vehicle in the target vehicle image is blocked.

[0084] The second processing module 620 is configured to obtain a second initial result based on the vehicle contour information of the target vehicle image.

[0085] The determination module 630 is configured to determine a target result based on the first initial result and the second initial result.

[0086] According to an embodiment of the present disclosure, the second processing module may include a contour restoration unit and a contour processing unit.

[0087] The contour restoration unit is used to determine the obscured vehicle contour information of the target vehicle based on the vehicle contour information of the target vehicle image, and obtain the target vehicle contour information.

[0088] The contour processing unit is used to obtain a second initial result based on the target vehicle contour information.

[0089] According to an embodiment of the present disclosure, the contour processing unit may include a screening subunit and a first determining subunit.

[0090] The screening subunit is configured to determine target reference vehicle profile information that matches the target vehicle profile information from the reference vehicle profile information set.

[0091] The first determining subunit is configured to obtain a second initial result based on the target reference vehicle profile information.

[0092] According to an embodiment of the present disclosure, the contour processing unit may further include a second determining subunit.

[0093] The second determining subunit is configured to input the target vehicle profile information into the profile processing model to obtain a second initial result when the target vehicle profile information is not included in the determination of the combination of the reference vehicle profile information.

[0094] According to an embodiment of the present disclosure, the image processing apparatus may further include a detection module and a cropping module.

[0095] The detection module is used to detect the initial vehicle image and determine the candidate area for the target vehicle, wherein the initial vehicle image includes other objects except the target vehicle.

[0096] The cropping module is used to obtain the target vehicle image based on the candidate area.

[0097] According to an embodiment of the present disclosure, the first processing module may include an image processing unit.

[0098] The image processing unit is used to input the target vehicle image into the image processing model to obtain a first initial result.

[0099] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0100] According to an embodiment of the present disclosure, an electronic device includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute a method as in the embodiment of the present disclosure.

[0101] According to an embodiment of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to cause a computer to execute a method according to an embodiment of the present disclosure.

[0102] According to an embodiment of the present disclosure, a computer program product includes a computer program. When the computer program is executed by a processor, the method according to the embodiment of the present disclosure is implemented.

[0103] Figure 7 A schematic block diagram of an example electronic device 700 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0104] like Figure 7 As shown, the device 700 includes a computing unit 701, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 702 or a computer program loaded from a storage unit 708 into a random access memory (RAM) 703. Various programs and data required for the operation of the device 700 can also be stored in the RAM 703. The computing unit 701, the ROM 702, and the RAM 703 are connected to each other via a bus 704. An input / output (I / O) interface 705 is also connected to the bus 704.

[0105] Various components in device 700 are connected to I / O interface 705, including an input unit 706, such as a keyboard, mouse, etc.; an output unit 707, such as various types of displays, speakers, etc.; a storage unit 708, such as a magnetic disk, optical disk, etc.; and a communication unit 709, such as a network card, modem, wireless communication transceiver, etc. The communication unit 709 allows device 700 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0106] The computing unit 701 can be a variety of general-purpose and / or specialized processing components with processing and computing capabilities. Some examples of the computing unit 701 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units that run machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The computing unit 701 performs the various methods and processes described above, such as the image processing method. For example, in some embodiments, the image processing method can be implemented as a computer software program that is tangibly contained in a machine-readable medium, such as the storage unit 708. In some embodiments, part or all of the computer program can be loaded and / or installed on the device 700 via the ROM 702 and / or the communication unit 709. When the computer program is loaded into the RAM 703 and executed by the computing unit 701, one or more steps of the image processing method described above can be performed. Alternatively, in other embodiments, the computing unit 701 can be configured to perform the image processing method by any other appropriate means (e.g., by means of firmware).

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

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

[0109] In the context of the present disclosure, a machine-readable medium can be a tangible medium that can contain or store a program for use by or in conjunction with an instruction execution system, device or equipment. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium can include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

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

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

[0112] A computer system may include a client and a server. The client and server are generally remote from each other and typically interact through a communication network. The client-server relationship arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server may be a cloud server, a server in a distributed system, or a server integrated with a blockchain.

[0113] It should be understood that the various forms of the processes shown above can be used to reorder, add, or delete steps. For example, the steps described in this disclosure can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved. This is not a limitation herein.

[0114] The above specific embodiments do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure shall be included within the scope of protection of this disclosure.

Claims

1. An image processing method, comprising: Based on image information of a target vehicle image, inputting the target vehicle image into an image processing model to obtain a first initial result, wherein part of the information of the target vehicle in the target vehicle image is blocked; Determining obscured vehicle contour information of the target vehicle based on existing vehicle contour information of the target vehicle image, and obtaining target vehicle contour information based on the existing vehicle contour information and the determined obscured vehicle contour information, wherein the target vehicle contour information is complete contour information of the target vehicle; performing similarity calculations on each of a plurality of reference vehicle profile information in the reference vehicle profile information set and the target vehicle profile information, determining reference vehicle profile information whose similarity reaches a similarity threshold as target reference vehicle profile information that matches the target vehicle profile information, and determining, based on the target reference vehicle profile information and through a mapping relationship, a reference vehicle category mapped to the target reference vehicle profile information, to obtain a second initial result, wherein the plurality of reference vehicle profile information in the reference vehicle profile information set is mapped to the reference vehicle category; In a case where there is no target reference vehicle profile information matching the target vehicle profile information in the reference vehicle profile information set, inputting the target vehicle profile information into a profile processing model to obtain the second initial result; and A target result is determined based on the first initial result and the second initial result, wherein the first initial result and the second initial result are obtained by using different processing means.

2. The method according to claim 1, further comprising: Detecting an initial vehicle image to determine a candidate region for the target vehicle, wherein the initial vehicle image includes other objects except the target vehicle; and Based on the candidate area, the target vehicle image is obtained.

3. An image processing device, comprising: a first processing module, configured to obtain a first initial result based on image information of a target vehicle image, wherein part of information of the target vehicle in the target vehicle image is blocked; A second processing module, configured to obtain a second initial result based on the vehicle profile information of the target vehicle image; and a determination module, configured to determine a target result based on the first initial result and the second initial result, wherein the first initial result and the second initial result are obtained by using different processing means, Wherein, the second processing module includes: a contour restoration unit, configured to determine the obscured vehicle contour information of the target vehicle based on the existing vehicle contour information of the target vehicle image, and obtain target vehicle contour information based on the existing vehicle contour information and the determined obscured vehicle contour information, wherein the target vehicle contour information is complete contour information of the target vehicle; and A contour processing unit is used to obtain the second initial result based on the target vehicle contour information, Wherein, the contour processing unit includes: a screening subunit, configured to respectively calculate similarities between a plurality of reference vehicle profile information in a reference vehicle profile information set and the target vehicle profile information, and determine reference vehicle profile information whose similarity reaches a similarity threshold as target reference vehicle profile information that matches the target vehicle profile information, wherein the plurality of reference vehicle profile information in the reference vehicle profile information set is mapped to a reference vehicle category; A first determining subunit is configured to determine, based on the target reference vehicle profile information, a reference vehicle category mapped to the target reference vehicle profile information through a mapping relationship to obtain the second initial result; and The second determining subunit is configured to input the target vehicle profile information into a profile processing model to obtain the second initial result when there is no target reference vehicle profile information matching the target vehicle profile information in the reference vehicle profile information set. Wherein, the first processing module includes: An image processing unit is used to input the target vehicle image into an image processing model to obtain the first initial result.

4. The apparatus according to claim 3, further comprising: a detection module, configured to detect an initial vehicle image and determine a candidate region for the target vehicle, wherein the initial vehicle image includes other objects besides the target vehicle; and A cropping module is used to obtain the target vehicle image based on the candidate area.

5. An electronic device comprising: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 2.

6. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to cause the computer to execute the method according to any one of claims 1 to 2.

7. A computer program product comprising a computer program, which, when executed by a processor, implements the method according to any one of claims 1 to 2.

Images