CN114708498A

CN114708498A - Image processing method, image processing apparatus, electronic device, and storage medium

Info

Publication number: CN114708498A
Application number: CN202210244098.XA
Authority: CN
Inventors: 吴宏涛; 张军; 舒茂; 孟颖; 牛秉青; 周晓旭; 周丽军; 何琨
Original assignee: Beijing Baidu Netcom Science and Technology Co Ltd; Shanxi Transportation Technology Research and Development Co Ltd
Current assignee: Beijing Baidu Netcom Science and Technology Co Ltd; Shanxi Transportation Technology Research and Development Co Ltd
Priority date: 2022-03-11
Filing date: 2022-03-11
Publication date: 2022-07-05

Abstract

The present disclosure provides an image processing method, an image processing apparatus, an electronic device, a storage medium, and a program product, which relate to the technical field of artificial intelligence, and in particular, to the technical field of image processing and automatic driving. The specific implementation scheme is as follows: obtaining a first initial result based on the image information of the target vehicle image, wherein part of the information of the target vehicle in the target vehicle image is blocked; obtaining a second initial result based on the vehicle contour information of the target vehicle image; and determining a target result based on the first initial result and the second initial result.

Description

Image processing method, image processing apparatus, electronic device, and storage medium

Technical Field

The present disclosure relates to the field of artificial intelligence technologies, and in particular, to the field of image processing and automatic driving technologies, and in particular, to an image processing method and apparatus, an electronic device, a storage medium, and a program product.

Background

Computer vision techniques offer great potential for improving the processing power of images. Computer vision is a science that studies how to use electronic equipment to "see", that is, a scientific technology that uses a camera and a computer to identify, track, measure, etc. a target instead of human eyes. The computer vision technology provides great help for the application development of public safety, information safety, financial safety and driving safety.

Disclosure of Invention

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

According to an aspect of the present disclosure, there is provided an image processing method including: obtaining a first initial result based on image information of a target vehicle image, wherein partial information of a target vehicle in the target vehicle image is blocked; obtaining a second initial result based on the vehicle contour information of the target vehicle image; and determining a target result based on the first initial result and the second initial result.

According to another aspect of the present disclosure, there is provided an image processing apparatus including: the first processing module is used for obtaining a first initial result based on image information of a target vehicle image, wherein partial information of a target vehicle in the target vehicle image is blocked; the second processing module is used for obtaining a second initial result based on the vehicle contour information of the target vehicle image; and a determination module to determine a target result based on the first initial result and the second initial result.

According to another aspect of the present disclosure, there is provided an electronic device including: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform a method according to the present disclosure.

According to another aspect of the present disclosure, there is provided a non-transitory computer readable storage medium having stored thereon computer instructions for causing the computer to perform a method as disclosed herein.

According to another aspect of the present disclosure, a computer program product is provided, comprising a computer program which, when executed by a processor, implements a method as disclosed herein.

It should be understood that the statements in this section do not necessarily identify key or critical features of the embodiments of the present disclosure, nor do they limit the scope of the present disclosure. Other features of the present disclosure will become apparent from the following description.

Drawings

The drawings are included to provide a better understanding of the present solution and are not to be construed as limiting the present disclosure. Wherein:

fig. 1 schematically illustrates an exemplary system architecture to which the information processing method and apparatus may be applied, according to an embodiment of the present disclosure;

FIG. 2 schematically shows a flow chart of an information processing method according to an embodiment of the disclosure;

FIG. 3 schematically illustrates a scene schematic diagram of acquiring an image of a target vehicle, according to an embodiment of the disclosure;

FIG. 4 schematically illustrates a flow chart for determining a target vehicle image according to an embodiment of the present disclosure;

FIG. 5 schematically shows a flow chart for determining a second initial result according to an embodiment of the disclosure;

fig. 6 schematically shows a block diagram of an information processing apparatus according to an embodiment of the present disclosure; and

fig. 7 schematically shows a block diagram of an electronic device adapted to implement an information processing method according to an embodiment of the present disclosure.

Detailed Description

Exemplary embodiments of the present disclosure are described below with reference to the accompanying drawings, in which various details of embodiments of the present disclosure are included to assist understanding, and which are to be considered as merely exemplary. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present disclosure. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.

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

In the technical scheme of the disclosure, the collection, storage, use, processing, transmission, provision, disclosure, application and other processing of the personal information of the related user are all in accordance with the regulations of related laws and regulations, necessary confidentiality measures are taken, and the customs of the public order is not violated.

In the technical scheme of the disclosure, before the personal information of the user is obtained or collected, the authorization or the consent of the user is obtained.

Fig. 1 schematically shows an exemplary system architecture to which the information processing method and apparatus may be applied according to an embodiment of the present disclosure.

It should be noted that fig. 1 is only an example of a system architecture 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, and does not mean that the embodiments of the present disclosure may not be applied to other devices, systems, environments or scenarios.

As shown in fig. 1, a system architecture 100 according to this embodiment may include an information collecting apparatus 101, a network 102, and a server 103. Network 102 serves as a medium for providing a communication link between information-collecting device 101 and server 103. Network 102 may include various connection types, such as wired and/or wireless communication links, and so forth.

The information collecting apparatus 101 may interact with the server 103 via the network 102 to receive or transmit messages or the like. The information collection device 101 and the server 103 may have installed thereon applications for enabling communication connection therebetween, such as a map-type application, an image processing-type application, a trajectory prediction-type application, and the like (for example only).

The information collecting apparatus 101 may be an apparatus having an image or video collecting function, including but not limited to a camera mounted on, for example, the autonomous vehicle 104, a drive recorder, and may also be a road camera mounted on a road, and the like.

The server 103 may be integrated on the autonomous vehicle 104 or may be provided at a remote end capable of establishing communication with the in-vehicle terminal. The method may be implemented as a distributed server cluster composed of a plurality of servers, or may be implemented as a single server, which is not described herein again.

The server 103 may be a server that provides various services, such as a background management server (for example only) that provides image processing support for the target vehicle image transmitted by the information collecting apparatus 101. For example, the server 103 receives the target vehicle image transmitted by the information collecting apparatus 101 through the network 102. In the case that it is determined that part of the information of the target vehicle in the target vehicle image is occluded, a first initial result may be obtained based on the image information of the target vehicle image; and obtaining a second initial result 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. And the target result is utilized to assist the automatic driving vehicle to complete the driving decision, and a corresponding obstacle avoidance driving scheme is obtained.

It should be noted that the information processing method provided by the embodiment of the present disclosure may be generally executed by the server 103. Accordingly, the information processing apparatus provided by the embodiment of the present disclosure may also be provided in the server 103.

It should be understood that the number of information gathering devices, networks, and servers in fig. 1 is merely illustrative. There may be any number of information collection devices, networks, and servers, as desired for implementation.

It should be noted that the sequence numbers of the respective operations in the following methods are merely used as representations of the operations for description, and should not be construed as representing the execution order of the respective operations. The method need not be performed in the exact order shown, unless explicitly stated.

Fig. 2 schematically shows a flow chart of an information processing method according to an embodiment of the present disclosure.

As shown in fig. 2, the method includes operations S210 to S230.

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

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

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

According to an embodiment of the present disclosure, the image information may refer to: representative or characteristic pixel information in an image. The image information may include, for example, color information, texture information, shape information, spatial relationship information, and the like. The features can be extracted from the image information by means of feature extraction, so that the computer can complete tasks such as detection, identification and the like through the extracted features.

According to an embodiment of the present disclosure, the vehicle contour information may refer to: vehicle profile information. For example, the vehicle shape information displayed in the two-dimensional plane image. The vehicle contour information may include information on the outer shape of the vehicle, the ratio of the length, width, height of the vehicle to each other, and the curvature of the curve. The vehicle profile information differs for different types of vehicles. The category of the vehicle may be identified based on the vehicle profile information.

According to the embodiment of the disclosure, the first initial result, the second initial result and the target result can be used for representing the category of the target vehicle in the target vehicle image. The category of target vehicle may include police cars, tank trucks, coal trucks, muck trucks, concrete cars, sanitation cars, fire trucks, ambulances, and the like.

According to other embodiments of the present disclosure, the first initial result may be obtained based solely on the image information of the target vehicle image, and the first initial result may be used as the target result. But is not limited thereto. Or simply based on the vehicle contour information of the target vehicle image, obtaining a second initial result, and taking the second initial result as a target result.

According to an embodiment of the present disclosure, the occlusion of the partial information of the target vehicle in the target vehicle image may refer to: part of the information of the target vehicle is lost. For example, a part of the body of the target vehicle is occluded so that information such as the head or tail of the target vehicle can only be seen from the image. The partial information of the target vehicle may include partial image information of the target vehicle and partial vehicle contour information.

According to the embodiment of the disclosure, in the case that part of the information of the target vehicle in the target vehicle image is occluded, different information is processed by different processing means respectively to determine the target result, that is, the target result is determined based on the first initial result and the second initial result, and compared with the case that a single processing means is used to process a single information to determine the target result, the accuracy of the result is improved.

FIG. 3 schematically shows a scene schematic diagram for acquiring an image of a target vehicle according to an embodiment of the disclosure.

As shown in fig. 3, environmental information on a road, such as road information, pedestrian information, and vehicle information, may be collected using an information collection device mounted on an autonomous vehicle 310. Based on the collected environmental information, the type of the obstacle and the state of the obstacle are determined. Thereby providing guidance for the driving decision of the autonomous vehicle 310 and improving the safety of autonomous driving.

As shown in fig. 3, the intersection-mounted camera 350 may also be used to collect information about the surroundings of the intersection. Whether the vehicle has illegal behaviors such as overspeed, overweight, abnormal track, red light running and the like is determined based on the running state information of the vehicle passing through the intersection collected in real time, and the functions of monitoring and preventing are achieved.

Taking the information collection device loaded on the autonomous vehicle 310 as an example, the autonomous vehicle 310 may be a target vehicle image of the vehicle 330 as a target vehicle, which is acquired in the process of collecting surrounding environment information, for example, environment information of the opposite lane 320. Because a pedestrian 340 is crossing the road on the sidewalk between the vehicle 330 and the autonomous vehicle 310, part of the body of the vehicle 330 is blocked by the pedestrian 340 in the collected target vehicle image about the vehicle 330. And then part of the information of the target vehicle 330 in the finally obtained target vehicle image is occluded.

According to the embodiment of the present disclosure, as the number of vehicles, pedestrians, and the like traveling on the road increases, it is highly likely that part of the vehicle information of the target vehicle in the target vehicle image is occluded, and in this case, the accuracy of determining the target result based on the first initial result and the second initial result provided by the embodiment of the present disclosure increases, and the application range becomes larger and larger.

FIG. 4 schematically shows a flowchart for acquiring an image of a target vehicle according to another embodiment of the present disclosure.

As shown in fig. 4, the information acquisition device may be used to acquire environmental information on a road, and obtain an initial vehicle image 410. The initial vehicle image 410 includes a target vehicle 420, and also includes a plurality of other vehicles 430 other than the target vehicle 420, and other objects such as a road 440.

As shown in fig. 4, an initial vehicle image 410 may be detected, determining candidate regions for a target vehicle 420. Based on the candidate region, other objects in the initial vehicle image other than the target vehicle, for example, other vehicles, may be cut out, resulting in a target vehicle image 450 including the target vehicle with background information cut out.

As shown in fig. 4, the candidate area may refer to a location area of the target vehicle, which may be framed using the detection block 460. The type and shape of the detection frame are not limited. As shown in fig. 4, the detection frame 460 is located at the periphery of the target vehicle 420, and has a rectangular shape, and information of the detection frame is determined by position information of four corners, thereby identifying candidate regions. But is not limited thereto. The detection frame may also be located at a periphery of the target vehicle, bounded by an outer edge of the target vehicle, a predetermined distance from the outer edge of the target vehicle. Any detection frame may be used as long as it can exclude background information in the initial vehicle image, for example, other objects than the target vehicle.

According to the embodiment of the disclosure, the initial vehicle image can be detected by utilizing a neural network model, and the candidate region aiming at the target vehicle is determined. For example, the neural network model may include YOLOv3 (young Only Look Once, real-time object detection model), but is not limited thereto, and may also include YOLOv4 or YOLOv 5. Any neural network model may be used as long as it can detect a candidate region.

By using the method for determining the target vehicle image provided by the embodiment of the disclosure, background information and other object information in the initial vehicle image can be removed, and the influence of pixel information and contour information of non-target vehicles is reduced, so that the data processing amount is reduced, and the identification accuracy is improved.

According to other embodiments of the present disclosure, before performing operation S210, it may be determined whether the target vehicle is occluded based on image information of the target vehicle image or vehicle contour information of the target vehicle image. In the case that the target vehicle is determined to be occluded, the operation of determining the target result based on the first initial result and the second initial result provided by the embodiment of the present disclosure is performed. In the case that the target vehicle is determined not to be occluded, the first initial result can be used as the target result, and the operation of executing the vehicle contour information based on the target vehicle image to obtain a second initial result is abandoned; or the second initial result is used as the target result, and the operation of obtaining the first initial result is abandoned to be executed based on the image information of the target vehicle image.

According to an embodiment of the present disclosure, determining the target result based on the first initial result and the second initial result may include: and taking the first initial result as a target result under the condition that the first initial result and the second initial result are the same. In the case that the first initial result and the second initial result are identical, the confidence of the first initial result and the confidence of the second initial result are determined. And taking the result with high confidence as a target result.

By using the image processing method provided by the embodiment of the disclosure, the type of the target vehicle can be identified by determining different processing modes based on whether the target vehicle in the target vehicle image is blocked, so that the identification precision is improved, and the processing efficiency is improved.

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

According to the embodiment of the present disclosure, the type of the image processing model is not limited, and for example, the model may include ResNet34 (residual network, hidden layer includes 34 layers), but is not limited thereto, and may also include VGG16(Visual Geometry Group), MobileNet (lightweight deep neural network), and the like. Any model may be used as long as it can obtain the first initial result representing the category of the target vehicle based on the target vehicle image.

Fig. 5 schematically shows a flow chart for determining a second initial result according to an embodiment of the present disclosure.

As shown in fig. 5, the method includes operations S510 to S530.

In operation S510, occluded vehicle contour information of the target vehicle is determined based on the vehicle contour information of the target vehicle image, resulting in target vehicle contour information.

In operation S520, it is determined whether target reference vehicle contour information matching the target vehicle contour information exists in the set of reference vehicle contour information. In a case where it is determined that there is target reference vehicle contour information matching the target vehicle contour information in the set of reference vehicle contour information, performing operation S530; in a case where it is determined that there is no target reference vehicle contour information matching the target vehicle contour information in the set of reference vehicle contour information, operation S540 is performed.

In operation S530, a second initial result is obtained based on the target reference vehicle contour information.

In operation S540, the target vehicle contour information is input into the contour processing model, resulting in a second initial result.

According to an embodiment of the present disclosure, before performing operation S510, the image processing method may further include: based on the target vehicle image, vehicle contour information is determined. The vehicle contour information can be obtained by performing edge detection processing on the target vehicle image by using a vehicle contour edge detection algorithm. The vehicle contour edge detection algorithm may include a Canny (Canny) edge detection algorithm, but is not limited thereto, and may also include a Sobel (Sobel) edge detection algorithm or a Prewitt (daravit) edge detection algorithm. The type of the vehicle contour edge detection algorithm is not limited as long as it is a detection algorithm capable of detecting vehicle contour information from a target vehicle image.

According to an embodiment of the present disclosure, in performing operation S510, the occluded vehicle contour information of the target vehicle may be fitted based on the existing vehicle contour information of the target vehicle image. And obtaining the target vehicle contour information, namely the complete contour information of the target vehicle, based on the existing vehicle contour information and the contour information of the shielded vehicle restored in a fitting mode.

According to the embodiment of the disclosure, the occluded vehicle contour information of the target vehicle can be obtained by fitting based on the streamline characteristics of the contour of the vehicle and one or more of a circle fitting mode, a curve fitting mode and a straight line fitting mode and based on the existing vehicle contour information, so that the occluded vehicle contour information is restored.

According to other embodiments of the present disclosure, operations S520, S530, and S540 may be performed based on existing vehicle contour information, resulting in a second initial result. For example, it is determined whether there is target reference vehicle contour information in the set of reference vehicle contour information that matches the vehicle contour information in the target vehicle image. And obtaining a second initial result based on the target reference vehicle contour information under the condition that the target reference vehicle contour information matched with the target vehicle contour information exists in the reference vehicle contour information set. And under the condition that the target reference vehicle contour information matched with the target vehicle contour information does not exist in the reference vehicle contour information set, inputting the vehicle contour information of the target vehicle image into the contour processing model to obtain a second initial result.

According to the embodiment of the disclosure, more vehicle contour information can be obtained compared with the method that the second initial result is obtained by utilizing the vehicle contour information in the existing target vehicle image, and the accuracy of the second initial result is higher as the integrity of the utilized information is higher.

According to an embodiment of the present disclosure, in operations S520 and S530, reference vehicle contour information of various types of vehicles may be acquired in advance, resulting in a set of reference vehicle contour information. A plurality of reference vehicle profile information of the set of reference vehicle profile information may be mapped to a category of the reference vehicle. In the case where a plurality of pieces of target reference vehicle contour information matching the target vehicle contour information are determined from the set of reference vehicle contour information, the reference vehicle category matching the target reference vehicle contour information may be determined by the mapping relationship, and the second initial result may be determined therefrom.

According to an embodiment of the present disclosure, determining a plurality of target reference vehicle contour information matching the target vehicle contour information from the set of reference vehicle contour information may include: and respectively carrying out similarity calculation on the plurality of pieces of reference vehicle contour information in the reference vehicle contour information set and the target vehicle contour information, and taking the reference vehicle contour information with the highest similarity or the similarity reaching a similarity threshold as the target reference vehicle contour information.

According to embodiments of the present disclosure, the similarity calculation may be: and carrying out equal-scale scaling on the reference vehicle contour information or the target vehicle contour information, and then carrying out contour matching on the reference vehicle contour information and the target vehicle contour information to obtain a similarity result. But is not limited thereto. The similarity calculation may also be: and respectively extracting the reference vehicle contour information and the target vehicle contour information to obtain respective feature vectors. And calculating the similarity between the characteristic vector of the reference vehicle contour information and the characteristic vector of the target vehicle contour information to obtain a similarity result. The method of calculating the similarity is not limited, and any calculation method may be used as long as the target reference vehicle contour information can be specified from the reference vehicle contour information set based on the target vehicle contour information.

According to the embodiment of the present disclosure, the reference vehicle contour information in the reference vehicle contour information set cannot be exhausted, so there is target reference vehicle contour information that cannot be matched to the target vehicle contour information from the reference vehicle contour information set. In this case, operation S540 may be performed. In operation S540, vehicle contour information of the target vehicle image may be input into the contour processing model, resulting in a second initial result.

According to the embodiment of the present disclosure, the network structure of the contour processing model is not limited as long as it is a model that can obtain the second initial result representing the category of the target vehicle based on the target vehicle contour information.

For example, the contour processing model may include a convolutional neural network, e.g., the contour processing model may include a cascade of a first convolutional layer, a first pooling layer, a second convolutional layer, a second pooling layer, a third convolutional layer, a fully-connected layer, and an activation function. The sizes of the convolution kernels of the first convolution layer, the convolution kernels of the second convolution layer, and the convolution kernels of the third convolution layer are not limited, and may be the same or different. But is not limited thereto. The contour processing model may also include a recurrent neural network, or a tree model, etc.

According to an embodiment of the present disclosure, there is also provided a training sample generation method, including: and fusing the plurality of vehicle images and the background image to obtain a sample image. At least two of the plurality of vehicle images in the sample image partially overlap.

According to the embodiment of the disclosure, each of the plurality of vehicle images may include only the vehicle information, and the sample image is generated using the vehicle image including only the vehicle information, so that the foreign matter information can be filtered out, and the training efficiency can be improved.

According to the embodiment of the disclosure, at least two vehicle images are fused with the background image in a partially overlapping mode, so that the number and the types of generated sample images are large, the data volume of the training samples is improved, and meanwhile, the overfitting phenomenon is avoided.

According to the embodiment of the disclosure, the category of the vehicle in the sample image can be used as a label, and the label and the sample image can be used as a training sample. The training samples are used for respectively training the image processing model and the contour processing model, so that the parameters of the image processing model and the contour processing model can be respectively adjusted, special tuning is realized, and the precision of the trained image processing model and the trained contour processing model is improved.

Fig. 6 schematically shows a block diagram of an information processing apparatus according to an embodiment of the present disclosure.

As shown in fig. 6, the image processing apparatus 600 may include a first processing module 610, a second processing module 620, and a determination module 630.

The first processing module 610 is configured to obtain a first initial result based on image information of a target vehicle image, where part of information of a target vehicle in the target vehicle image is occluded.

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

A determining module 630, configured to determine the target result based on the first initial result and the second initial result.

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

And the contour restoration unit is used for determining the shielded vehicle contour information of the target vehicle based on the vehicle contour information of the target vehicle image to obtain the target vehicle contour information.

And the contour processing unit is used for obtaining a second initial result based on the contour information of the target vehicle.

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

And the screening subunit is used for determining target reference vehicle contour information matched with the target vehicle contour information from the reference vehicle contour information set.

And the first determining subunit is used for obtaining a second initial result based on the target reference vehicle contour information.

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

And the second determining subunit is used for inputting the target vehicle contour information into the contour processing model under the condition that no target reference vehicle contour information exists in the combination of the reference vehicle contour information, and obtaining a second initial result.

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

The detection module is used for detecting an initial vehicle image and determining a candidate area for a target vehicle, wherein the initial vehicle image comprises other objects except the target vehicle.

And the cropping module is used for obtaining the target vehicle image based on the candidate area.

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

And the image processing unit is used for inputting the target vehicle image into the image processing model to obtain a first initial result.

The present disclosure also provides an electronic device, a readable storage medium, and a computer program product according to embodiments of the present disclosure.

According to an embodiment of the present disclosure, an electronic device includes: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform a method according to an embodiment of the disclosure.

According to an embodiment of the present disclosure, a non-transitory computer-readable storage medium having stored thereon computer instructions for causing a computer to perform a method as in an embodiment of the present disclosure.

According to an embodiment of the disclosure, a computer program product comprising a computer program which, when executed by a processor, implements a method as in an embodiment of the disclosure.

FIG. 7 illustrates a schematic block diagram of an example electronic device 700 that can be used to implement embodiments of the present disclosure. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be examples only, and are not meant to limit implementations of the disclosure described and/or claimed herein.

As shown in fig. 7, the device 700 comprises a computing unit 701, which may perform various suitable 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. In the RAM 703, various programs and data required for the operation of the device 700 can also be stored. The calculation unit 701, the ROM 702, and the RAM 703 are connected to each other by a bus 704. An input/output (I/O) interface 705 is also connected to bus 704.

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

Computing unit 701 may be a variety of general purpose and/or special purpose 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 specialized Artificial Intelligence (AI) computing chips, various computing units running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, and so forth. The calculation unit 701 executes the respective methods and processes described above, such as an image processing method. For example, in some embodiments, the image processing method may be implemented as a computer software program tangibly embodied in a machine-readable medium, such as storage unit 708. In some embodiments, part or all of a computer program may be loaded onto and/or installed onto device 700 via ROM 702 and/or communications 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 may be performed. Alternatively, in other embodiments, the computing unit 701 may be configured to perform the image processing method by any other suitable means (e.g., by means of firmware).

Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuitry, Field Programmable Gate Arrays (FPGAs), Application Specific Integrated Circuits (ASICs), Application Specific Standard Products (ASSPs), system on a chip (SOCs), Complex Programmable Logic Devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs that are executable and/or interpretable on a programmable system including at least one programmable processor, which may be special or general purpose, receiving data and instructions from, and transmitting data and instructions to, a storage system, at least one input device, and at least one output device.

Program code for implementing the methods of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the program codes, when executed by the processor or controller, cause the functions/operations specified in the flowchart and/or block diagram to be performed. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine or entirely on the remote machine or server.

In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, 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 disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

To provide for interaction with a user, the systems and techniques described here 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 a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which a user can provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, 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 may be received in any form, including acoustic, speech, or tactile input.

The systems and techniques described here can be implemented in a computing system that includes a back-end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back-end, middleware, 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: local Area Networks (LANs), Wide Area Networks (WANs), and the Internet.

The computer system may include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server 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 of a distributed system, or a server with a combined blockchain.

It should be understood that various forms of the flows shown above may be used, with steps reordered, added, or deleted. For example, the steps described in the present disclosure may be executed in parallel, sequentially, or in different orders, as long as the desired results of the technical solutions disclosed in the present disclosure can be achieved, and the present disclosure is not limited herein.

The above detailed description should not be construed as limiting the scope of the disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may be made, depending on design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present disclosure should be included in the scope of protection of the present disclosure.

Claims

1. An image processing method comprising:

obtaining a first initial result based on image information of a target vehicle image, wherein partial information of a target vehicle in the target vehicle image is blocked;

obtaining a second initial result based on the vehicle contour information of the target vehicle image; and

determining a target result based on the first initial result and the second initial result.

2. The method of claim 1, wherein the deriving a second initial result based on the vehicle contour information for the target vehicle image comprises:

determining the shielded vehicle contour information of the target vehicle based on the vehicle contour information of the target vehicle image to obtain the target vehicle contour information; and

and obtaining the second initial result based on the target vehicle contour information.

3. The method of claim 2, wherein the deriving the second initial result based on the target vehicle contour information comprises:

determining target reference vehicle contour information matched with the target vehicle contour information from a reference vehicle contour information set; and

and obtaining the second initial result based on the target reference vehicle profile information.

4. The method of claim 3, wherein the deriving the second initial result based on the target vehicle contour information further comprises:

and under the condition that the target reference vehicle contour information is not determined in the reference vehicle contour information combination, inputting the target vehicle contour information into a contour processing model to obtain the second initial result.

5. The method of any of claims 1 to 4, further comprising:

detecting an initial vehicle image and determining a candidate region for the target vehicle, wherein the initial vehicle image comprises other objects except the target vehicle; and

and obtaining the target vehicle image based on the candidate region.

6. The method of any of claims 1 to 5, wherein the deriving a first initial result based on image information of a target vehicle image comprises:

and inputting the target vehicle image into an image processing model to obtain the first initial result.

7. An image processing apparatus comprising:

the first processing module is used for obtaining a first initial result based on image information of a target vehicle image, wherein partial information of a target vehicle in the target vehicle image is blocked;

the second processing module is used for obtaining a second initial result based on the vehicle contour information of the target vehicle image; and

a determination module to determine a target result based on the first initial result and the second initial result.

8. The apparatus of claim 7, wherein the second processing module comprises:

the contour restoration unit is used for determining the occluded vehicle contour information of the target vehicle based on the vehicle contour information of the target vehicle image to obtain the target vehicle contour information; and

and the contour processing unit is used for obtaining the second initial result based on the target vehicle contour information.

9. The apparatus of claim 8, wherein the contour processing unit comprises:

the screening subunit is used for determining target reference vehicle contour information matched with the target vehicle contour information from a reference vehicle contour information set; and

and the first determining subunit is used for obtaining the second initial result based on the target reference vehicle contour information.

10. The apparatus of claim 9, wherein the contour processing unit further comprises:

and the second determining subunit is used for inputting the target vehicle contour information into a contour processing model to obtain a second initial result under the condition that the target reference vehicle contour information is not determined in the reference vehicle contour information combination.

11. The apparatus of any of claims 7 to 10, further comprising:

the detection module is used for detecting an initial vehicle image and determining a candidate region for the target vehicle, wherein the initial vehicle image comprises other objects except the target vehicle; and

12. The apparatus of any of claims 7 to 11, wherein the first processing module comprises:

and the image processing unit is used for inputting the target vehicle image into an image processing model to obtain the first initial result.

13. An electronic device, comprising:

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,

the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1 to 6.

14. A non-transitory computer readable storage medium having stored thereon computer instructions for causing the computer to perform the method of any one of claims 1 to 6.

15. 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 6.