CN113506325B

CN113506325B - Image processing method and device, electronic equipment and storage medium

Info

Publication number: CN113506325B
Application number: CN202110801140.9A
Authority: CN
Inventors: 施路平; 杨哲宇; 赵蓉
Original assignee: Tsinghua University
Current assignee: Tsinghua University
Priority date: 2021-07-15
Filing date: 2021-07-15
Publication date: 2024-04-12
Anticipated expiration: 2041-07-15
Also published as: CN113506325A

Abstract

The present disclosure relates to an image processing method and apparatus, an electronic device, and a storage medium, the method including: performing target feature extraction processing on the first color image to obtain target feature information of a target object; inputting the dynamic visual information acquired at the first moment into a first feature extraction network to acquire a first feature map; and determining the position information of the target object at the first moment according to the target characteristic information and the first characteristic diagram. According to the image processing method of the embodiment of the disclosure, the first feature map can be obtained by utilizing the dynamic visual information with higher acquisition frequency, and the position information of the target object at the first moment when the dynamic visual information is acquired can be determined based on the first feature map. Since the frequency of the dynamic visual information is higher than the acquisition frequency of the color images, the position information of a plurality of moments in the time period between two frames of color images can be determined through the first feature map, and the tracking of the motion trail or action of the moving object is facilitated.

Description

Image processing method and device, electronic equipment and storage medium

Technical Field

The disclosure relates to the field of computer technology, and in particular, to an image processing method and apparatus, an electronic device, and a storage medium.

Background

In the related art, the frame rate of the image or video frame collected by the camera or the camera is not high, and when a target moving at a high speed is tracked, the action of the target in a time period between two frames is difficult to track, so that the action or track of the target is omitted, and the tracking effect is poor.

Disclosure of Invention

The disclosure provides an image processing method and device, electronic equipment and a storage medium.

According to an aspect of the present disclosure, there is provided an image processing method including: performing target feature extraction processing on a target region in a first color image of a preset scene acquired in a first time period to acquire target feature information of a target object in the first color image; inputting the dynamic visual information of the preset scene acquired at the first moment in the first time period into a first feature extraction network to acquire a first feature map corresponding to the dynamic visual information at the first moment, wherein the acquisition frequency of the dynamic visual information is higher than that of the color image, the first feature extraction network is trained through a second feature extraction network, and the second feature extraction network is used for extracting the feature map of the color image; and determining the position information of the target object at the first moment according to the target characteristic information and the first characteristic diagram, wherein the target object is any object in the preset scene.

In one possible implementation manner, determining the location information of the target object at the first moment according to the target feature information and the first feature map includes: determining a convolution kernel parameter according to the target characteristic information; performing convolution processing on the first feature map according to the convolution kernel parameters to obtain a correlation thermodynamic diagram between the target feature information and the first feature map; and determining the position information of the target object at the first moment according to the related thermodynamic diagram.

In one possible implementation, the method further includes: and decoding the first feature map to obtain a second color image at the first moment.

In one possible implementation, the method further includes: and according to the position information, carrying out segmentation processing on the target object in the second color image to obtain a segmentation mask diagram of the target object.

In one possible implementation manner, performing a target feature extraction process on a target area in a first color image in a first time period of a preset scene to obtain target feature information of a target object in the first color image, where the target feature information includes: performing target detection processing on the first color image to obtain a target area where the target object is located; and carrying out target feature extraction processing on the target region to obtain the target feature information.

In one possible implementation, the method further includes: performing feature extraction processing on a sample color image of a sample scene through a pre-trained second feature extraction network to obtain a first sample feature map; performing feature extraction processing on sample dynamic visual information of the sample scene through a first feature extraction network to obtain a second sample feature map, wherein the sample dynamic visual information and the sample color image are acquired simultaneously; determining network loss of a first feature extraction network according to the first sample feature map and the second sample feature map; and training the first feature extraction network according to the network loss.

In one possible implementation, the first feature extraction network comprises a pulsed neural network and the second feature extraction network comprises a convolutional neural network.

According to an aspect of the present disclosure, there is provided an image processing apparatus including: the target feature information extraction module is used for carrying out target feature extraction processing on a target region in a first color image of a preset scene acquired in a first time period to obtain target feature information of a target object in the first color image; the feature map extraction module is used for inputting the dynamic visual information of the preset scene acquired at the first moment in the first time period into a first feature extraction network to acquire a first feature map corresponding to the dynamic visual information at the first moment, wherein the acquisition frequency of the dynamic visual information is higher than that of the color image, the first feature extraction network is trained through a second feature extraction network, and the second feature extraction network is used for extracting the feature map of the color image; and the position information determining module is used for determining the position information of the target object at the first moment according to the target characteristic information and the first characteristic diagram, wherein the target object is any object in the preset scene.

In one possible implementation, the location information determining module is further configured to: determining a convolution kernel parameter according to the target characteristic information; performing convolution processing on the first feature map according to the convolution kernel parameters to obtain a correlation thermodynamic diagram between the target feature information and the first feature map; and determining the position information of the target object at the first moment according to the related thermodynamic diagram.

In one possible implementation, the apparatus further includes: and the decoding module is used for decoding the first feature map to obtain a second color image at the first moment.

In one possible implementation, the apparatus further includes: and the segmentation module is used for carrying out segmentation processing on the target object in the second color image according to the position information to obtain a segmentation mask diagram of the target object.

In one possible implementation manner, the target feature information extraction module is further configured to: performing target detection processing on the first color image to obtain a target area where the target object is located; and carrying out target feature extraction processing on the target region to obtain the target feature information.

In one possible implementation, the apparatus further includes: the training module is used for carrying out feature extraction processing on the sample color image of the sample scene through a pre-trained second feature extraction network to obtain a first sample feature image; performing feature extraction processing on sample dynamic visual information of the sample scene through a first feature extraction network to obtain a second sample feature map, wherein the sample dynamic visual information and the sample color image are acquired simultaneously; determining network loss of a first feature extraction network according to the first sample feature map and the second sample feature map; and training the first feature extraction network according to the network loss.

According to an aspect of the present disclosure, there is provided an electronic apparatus including: a processor; a memory for storing processor-executable instructions; wherein the processor is configured to invoke the instructions stored in the memory to perform the above method.

According to an aspect of the present disclosure, there is provided a computer readable storage medium having stored thereon computer program instructions which, when executed by a processor, implement the above-described method.

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure. Other features and aspects of the present disclosure will become apparent from the following detailed description of exemplary embodiments, which proceeds with reference to the accompanying drawings.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the disclosure and together with the description, serve to explain the technical aspects of the disclosure.

FIG. 1 shows a flow chart of an image processing method according to an embodiment of the present disclosure;

FIG. 2 illustrates a schematic diagram of a thermodynamic diagram of interest in accordance with an embodiment of the present disclosure;

FIG. 3 shows a schematic diagram of a split network according to an embodiment of the present disclosure;

fig. 4 shows an application schematic of an image processing method according to an embodiment of the present disclosure;

fig. 5 shows a block diagram of an image processing apparatus according to an embodiment of the present disclosure;

FIG. 6 illustrates a block diagram of an electronic device according to an embodiment of the disclosure;

fig. 7 shows a block diagram of an electronic device according to an embodiment of the disclosure.

Detailed Description

Various exemplary embodiments, features and aspects of the disclosure will be described in detail below with reference to the drawings. In the drawings, like reference numbers indicate identical or functionally similar elements. Although various aspects of the embodiments are illustrated in the accompanying drawings, the drawings are not necessarily drawn to scale unless specifically indicated.

The word "exemplary" is used herein to mean "serving as an example, embodiment, or illustration. Any embodiment described herein as "exemplary" is not necessarily to be construed as preferred or advantageous over other embodiments.

The term "and/or" is herein merely an association relationship describing an associated object, meaning that there may be three relationships, e.g., a and/or B, may represent: a exists alone, A and B exist together, and B exists alone. In addition, the term "at least one" herein means any one of a plurality or any combination of at least two of a plurality, for example, including at least one of A, B, C, and may mean including any one or more elements selected from the group consisting of A, B and C.

Furthermore, numerous specific details are set forth in the following detailed description in order to provide a better understanding of the present disclosure. It will be understood by those skilled in the art that the present disclosure may be practiced without some of these specific details. In some instances, methods, means, elements, and circuits well known to those skilled in the art have not been described in detail in order not to obscure the present disclosure.

Fig. 1 shows a flowchart of an image processing method according to an embodiment of the present disclosure, as shown in fig. 1, including:

In step S11, performing target feature extraction processing on a target area in a first color image of a preset scene acquired in a first period of time to obtain target feature information of a target object in the first color image;

in step S12, inputting the dynamic visual information of the preset scene acquired at the first moment in the first time period into a first feature extraction network to obtain a first feature map corresponding to the dynamic visual information at the first moment, wherein the acquisition frequency of the dynamic visual information is higher than the acquisition frequency of the color image, the first feature extraction network is trained through a second feature extraction network, and the second feature extraction network is used for extracting the feature map of the color image;

in step S13, determining, according to the target feature information and the first feature map, location information of the target object at the first moment, where the target object is any object in the preset scene.

According to the image processing method of the embodiment of the disclosure, the first feature map can be obtained by utilizing the dynamic visual information with higher acquisition frequency, and the position information of the target object at the first moment when the dynamic visual information is acquired can be determined based on the first feature map. Because the frequency of the dynamic visual information is higher than the acquisition frequency of the color images, the position information of a plurality of moments in the time period between two frames of color images can be determined through the first feature map, so that the tracking of the motion trail or action of a moving object is facilitated, and the tracking effect is improved.

In a possible implementation manner, the image processing method may be performed by an electronic device such as a terminal device or a server, where the terminal device may be a User Equipment (UE), a mobile device, a User terminal, a cellular phone, a cordless phone, a personal digital assistant (Personal Digital Assistant, PDA), a handheld device, a computing device, an in-vehicle device, a wearable device, etc., and the method may be implemented by a processor invoking computer readable instructions stored in a memory. Alternatively, the method may be performed by a server.

In one possible implementation, the dynamic vision receptors (Dynamic visual receptors, DVS) are sensitive to the rate of change of light intensity, and each pixel can record the amount of change in light intensity at that pixel location, and when the amount of change exceeds a threshold, a positive or negative pulse, i.e., dynamic visual information, is generated.

For example, an Event Camera (Event Camera) is a dynamic vision receptor that can be used to obtain the rate of change of light intensity of a preset scene. When a target in a preset scene is abnormal or performs certain actions, the light intensity of the target in the event camera can change to a certain extent, and the event camera can acutely capture the change to obtain dynamic visual information.

In one possible implementation, the frame rate of the dynamic vision receptor is higher than that of a normal camera or webcam, e.g., the frame rate of a camera or a conventional webcam is about 100fps, while the frame rate of the dynamic vision receptor is about 1,000,000fps. Therefore, in the time interval between the photographing of two frames of images by a common camera or a video camera, multiple frames of dynamic visual information can be photographed.

In an example, the length of the first period may be equal to a time interval between two frames of color images (e.g., images or video frames) of the preset scene acquired by the camera or the camera, or may be a time interval between multiple frames of color images of the preset scene acquired. That is, the start-stop time of the first period may be the time at which the color image is acquired.

In another example, the start-stop time of the first period may not be the time when the color image is acquired, and the length of the first period may be smaller than the period between two frames of color images acquired by the camera or the video camera, which is only required to acquire at least one frame of color image in the first period. The present disclosure does not limit the length of the first time period and the starting time. For example, the start time of the first period may be before one frame of the color image is captured, and the end time of the first period may be after one frame of the color image is captured, and does not necessarily coincide with the time when the color image is captured.

In one possible implementation, since the frequency of capturing color images is low, it is difficult to track the target object by the color images in the time interval between capturing two frames of color images, and the frequency of capturing dynamic visual information is high, so that the target object may be tracked by the dynamic visual images, for example, the first time is the time in the time interval between capturing two frames of color images, and the position of the target object at the time may be determined using the dynamic visual information captured at the time. The method can acquire the positions of the target object at a plurality of moments in the time interval between two frames of color images, and further track the motion trail of the target object.

In one possible implementation, the dynamic visual information is acquired at a high frequency, but the amount of information in the dynamic visual information of a single frame is small, and the pixel data is sparse. Feature extraction is performed on dynamic visual information, so that feature images rich in information are difficult to obtain. Thus, the second feature extraction network may be employed to train the first feature extraction network, and feature extraction may be performed through the trained first feature extraction network. In an example, the first feature extraction network comprises a pulsed neural network and the second feature extraction network comprises a convolutional neural network. The present disclosure is not limited in the types of the first feature extraction network and the second feature extraction network. The second feature extraction network may be used to extract a feature map of a color image, which is a common image acquired by a camera or a video camera, and may have rich image information, and the feature map may be obtained by feature extraction processing of the second feature extraction network (for example, a convolutional neural network), and may include color information, position information of a target, contour information of the target, and the like. Training the first feature extraction network through the second feature extraction network can enable the feature map of the dynamic visual information acquired by the first feature extraction network to be close to the feature map of the color image acquired by the second feature extraction network, namely, the feature information contained in the feature map of the dynamic visual information acquired by the first feature extraction network is richer and more accurate. For example, for the color image and the dynamic visual information acquired simultaneously, the feature map of the color image extracted by the second feature extraction network is identical to or close to the feature map of the dynamic visual information extracted by the first feature extraction network through the above training.

In one possible implementation, the trained first feature extraction network may be used to perform feature extraction on the dynamic visual information at a first time, where the first time is any time within the first time period, for example, the first time may be a time in a time interval between two consecutive frames of color images acquired by a camera or a video camera. The position information of the target object in the above-described time interval may be acquired by performing feature extraction on dynamic visual information acquired at a time point in the time interval between two consecutive frames of color images (i.e., a time point at which a color image cannot be acquired).

In one possible implementation, the target object in the color image may be first identified, target feature information of the target object is obtained, and location information of the target object at the first moment is determined in the feature map of the dynamic visual information based on the target feature information.

In one possible implementation, in step S11, target feature information of the target object may be acquired in the color image. Step S11 may include: performing target detection processing on the first color image to obtain a target area where the target object is located; and carrying out target feature extraction processing on the target region to obtain the target feature information.

In one possible implementation, the target feature extraction process may be performed on the target region in the first color image to obtain the feature vector of the target object. For example, the target region where the target object is located may be detected first in the first color image (for example, the target region where the target object is located is detected by a neural network or the like), and then the feature extraction processing may be performed on the region where the target object is located (for example, the feature extraction processing may be performed on the region where the target object is located by a neural network such as a second feature extraction network) to obtain the target feature information of the target object.

In a possible implementation manner, in step S12, a first feature map of dynamic visual information at a first moment may be acquired through a first feature extraction network, where the feature information included in the first feature map is consistent with or close to feature information obtained by feature extraction of a color image.

In one possible implementation, the first time may be a time when any frame of dynamic visual information is acquired in the first period, and the first time may be different from the second time when the first color image is acquired, that is, if the target object in the preset scene moves in a time interval between the first time and the second time, the position information of the target object at the first time is different from the position information of the target object at the second time. Thus, after the target feature information of the target object is obtained in the color image, the position information of the target object is determined in the first feature map at the first time based on the target feature information.

In one possible implementation, in step S13, the location information of the target object at the first moment may be determined in the first feature map according to the target feature information of the target object. Step S13 may include: determining a convolution kernel parameter according to the target characteristic information; performing convolution processing on the first feature map according to the convolution kernel parameters to obtain a correlation thermodynamic diagram between the target feature information and the first feature map; and determining the position information of the target object at the first moment according to the related thermodynamic diagram.

In one possible implementation, the first feature map may be convolved according to target feature information of the target object. For example, the target feature information may be a feature vector, a convolution kernel parameter (such as a weight of a convolution kernel) may be determined by the feature vector of the target object, a convolution process is performed on the first feature map by a convolution layer having the convolution kernel parameter, and in a result of the convolution process (i.e., a thermodynamic diagram related between the feature vector and the first feature map), a pixel value of each pixel represents a similarity between the feature vector and each position in the first feature map. The pixel value of the position in the first feature map, at which the similarity with the feature vector of the target object is high, is higher, and the pixel value of the position in the first feature map, at which the similarity with the feature vector of the target object is low, is lower. The position with the highest feature similarity (for example, similarity is 1) between the first feature map and the feature vector is the position of the target object at the first moment.

Fig. 2 shows a schematic diagram of a thermodynamic diagram of interest in accordance with an embodiment of the present disclosure. The pixel value of each pixel in the correlation thermodynamic diagram between the feature vector and the third feature map may represent the similarity between the feature vector and each position in the third feature map, where the position with the highest similarity is the position of the target object in the third feature map. As shown in fig. 3, positional information of the positions of the target object a, the target object B, and the target object C in the third feature map is shown, respectively. Namely, the position information of the target object a, the target object B, and the target object C at the first time.

In one possible implementation manner, based on the foregoing manner, a first feature map of dynamic visual information of multiple moments may also be determined, and position information of the target object at the multiple moments may be determined.

In this way, the position information of the target object at the first moment can be obtained through the first feature map at the first moment, the position information of the target object can be obtained at a plurality of moments in the time interval of collecting the color image, the frequency of obtaining the position information of the target object is improved, and the tracking effect on the target object is improved.

In one possible implementation, the method further includes: and decoding the first feature map to obtain a second color image at the first moment. The first feature map of the dynamic visual information obtained by the trained first feature extraction network is consistent with or close to the feature map obtained by feature extraction of the color image, so that the first feature map can be decoded to obtain a second color image. And in the color image, the position of the target object is the position of the target object at the first moment (the position of the target object in the first color image may be changed).

In this way, by performing the decoding processing on the first feature map, the second color image at the first timing can be acquired, and also the color images at a plurality of timings in the time interval in which the color images are acquired can be acquired, and the acquisition frequency of the color images can be increased.

In an example, the target object in the second color image may be subjected to a segmentation process through a segmentation network to obtain a segmentation mask map, where the segmentation mask map may be used to represent the position and the contour of the target object, and in an example, the pixel value in the region where the target object is located is 1, and the pixel values in other regions are 0. The present disclosure does not limit the pixel values of the segmentation mask map.

Fig. 3 illustrates a schematic diagram of a segmentation network, as shown in fig. 3, that may include a segmentation mask map branch that may output a segmentation mask map of the target object and a score branch that may be used for a score of each pixel in the second color image, e.g., the score of a pixel may be a probability value, may represent a probability that the pixel is a pixel within an area of the target object, e.g., if the probability is greater than a probability threshold (e.g., 50%), according to an embodiment of the disclosure. The present disclosure does not limit the network structure of the split network.

In one possible implementation, the first feature extraction network may be trained prior to the feature extraction process using the first feature extraction network described above. The first feature extraction network may be trained by the second feature extraction network such that the feature map of the dynamic visual information extracted by the first feature extraction network is consistent with or close to the feature map of the color image extracted by the second feature extraction network. The second feature extraction network may be trained first and the first feature extraction network may be trained through the trained second feature extraction network.

In an example, for a second feature extraction network used to extract feature information of a color image, training may be performed with a sample color image with labeling information, for example, network loss of the second feature extraction network may be determined according to a difference between a feature map of the sample color image extracted by the second feature extraction network and the labeling information, and network parameters of the second feature extraction network may be adjusted using the network loss of the second feature extraction network to reduce the network loss. And after the training condition is met, obtaining a trained second feature extraction network. For example, the training condition may include a training number, that is, after reaching a preset training number, obtaining the trained second feature extraction network, and for another example, the training condition may include converging a network loss, that is, after converging the network loss to a preset interval, obtaining the trained second feature extraction network. The present disclosure does not limit the training conditions.

In an example, for training of the first feature extraction network, the feature map of the dynamic visual information extracted by the first feature extraction network may be made consistent or close to the feature map of the color image extracted by the second feature extraction network, and thus the first feature extraction network may be trained by the pre-trained second feature extraction network.

In one possible implementation, the sample color image and the sample dynamic visual information of the sample scene may be acquired simultaneously. In the sample color image and the sample dynamic visual information, the positions of the target objects are the same, and the first feature extraction network can be trained through the second feature extraction network, so that a second sample feature image obtained by the sample dynamic visual information extracted by the first feature extraction network is consistent with or close to a first sample feature image of the sample color image extracted by the first feature extraction network, for example, the position information of the target objects in the feature image can be consistent with or close to each other.

In one possible implementation, the network loss of the first feature extraction network may be determined by a feature difference between the first sample feature map and the second sample feature map, e.g., a difference in location information of the target object in the first sample feature map and the second sample feature map may be determined, and the network loss may be determined by the difference.

Further, network parameters of the first feature extraction network may be adjusted by the network loss to reduce network loss. And after the training conditions are met, obtaining a first trained feature extraction network. For example, the training condition may include a training number, that is, after reaching a preset training number, the trained first feature extraction network is obtained, and for another example, the training condition may include converging a network loss, that is, after converging the network loss to a preset interval, the trained first feature extraction network is obtained. The present disclosure does not limit the training conditions.

In one possible implementation manner, the trained first feature extraction network may be used in the fields of tracking a moving target object, for example, if the moving speed of the target object is high, when the position change of the target object in a time interval of acquiring a color image is high, the target object is difficult to be effectively tracked only through the color image, and the feature map of dynamic visual information in the time interval may be extracted by using the first feature extraction network, so as to determine the position information of the target object at the moment of acquiring the dynamic visual information, thereby improving the acquisition frequency of acquiring the position information of the target object and improving the tracking effect of the target object.

According to the image processing method of the embodiment of the disclosure, the first feature extraction network may be trained through the pre-trained second feature extraction network, so that the feature map of the dynamic visual information extracted by the first feature extraction network is consistent with or close to the feature map of the color image extracted by the second feature extraction network. And the feature map of the dynamic visual information in the time interval of acquiring the color image can be extracted by utilizing the first feature extraction network so as to acquire the position information of the target object at the moment of acquiring the dynamic visual information, so that the acquisition frequency of the position information of the target object is improved, and the tracking effect on the target object is improved.

Fig. 4 illustrates an application diagram of an image processing method according to an embodiment of the present disclosure, as illustrated in fig. 4, a camera or a camera may acquire a color image of a target object, and the frequency of acquiring the color image is low. If the moving speed of the target object is high, the position information of the target object may change greatly in the time interval of acquiring the color image, and the effect of tracking the target object only through the color image is poor.

In one possible implementation, the tracking effect may be enhanced by dynamic visual information that is acquired more frequently than the color image, so that multiple frames of dynamic visual information may be acquired during the time interval that the color image is acquired. However, the pixel data of the dynamic visual information is sparse, so that it is difficult to obtain a feature map with rich information, the first feature extraction network (the feature map for extracting the dynamic visual information) may be trained by the pre-trained second feature extraction network (the feature map for extracting the color image) so that the feature map of the dynamic visual information extracted by the first feature extraction network is consistent with or close to the feature map of the color image extracted by the second feature extraction network, and the feature map of any dynamic visual information in the time interval may be extracted by the first feature extraction network so as to determine the position information of the target object at the moment when the dynamic visual information is obtained by the feature map.

In one possible implementation manner, target feature information of a target object in a color image is acquired, for example, target detection processing may be performed on the color image through a neural network, a target area where the target object is located is determined, and target feature extraction processing is performed on the target area through a second feature extraction network, so as to obtain target feature information, for example, the target feature information may be a feature vector of the target object. For example, the feature vectors of target object 1, target object 2, … …, target object n in the color image may be determined.

Further, the convolution kernel parameters can be determined through the feature vectors, and the feature graphs of the dynamic visual information are subjected to convolution processing according to the convolution kernel parameters, so that a correlation thermodynamic diagram between the feature vectors of all the target objects and the feature graphs of the dynamic visual information is obtained, and further, the position information of the target objects can be determined. In the above manner, the position information of each target object at a plurality of times at which the dynamic visual information is obtained can be obtained.

Fig. 5 shows a block diagram of an image processing apparatus according to an embodiment of the present disclosure, as shown in fig. 5, the apparatus including: the target feature information extraction module 11 is configured to perform target feature extraction processing on a target area in a first color image of a preset scene acquired in a first period of time, so as to obtain target feature information of a target object in the first color image; the feature map extracting module 12 is configured to input the dynamic visual information of the preset scene acquired at the first time in the first period of time into a first feature extracting network, and obtain a first feature map corresponding to the dynamic visual information at the first time, where the acquisition frequency of the dynamic visual information is higher than the acquisition frequency of the color image, the first feature extracting network is trained by a second feature extracting network, and the second feature extracting network is used to extract the feature map of the color image; and the position information determining module 13 is configured to determine, according to the target feature information and the first feature map, position information of the target object at the first moment, where the target object is any object in the preset scene.

It will be appreciated that the above-mentioned method embodiments of the present disclosure may be combined with each other to form a combined embodiment without departing from the principle logic, and are limited to the description of the present disclosure. It will be appreciated by those skilled in the art that in the above-described methods of the embodiments, the particular order of execution of the steps should be determined by their function and possible inherent logic.

In addition, the disclosure further provides an image processing apparatus, an electronic device, a computer readable storage medium, and a program, where the foregoing may be used to implement any one of the image processing methods provided in the disclosure, and corresponding technical schemes and descriptions and corresponding descriptions referring to method parts are not repeated.

In some embodiments, functions or modules included in an apparatus provided by the embodiments of the present disclosure may be used to perform a method described in the foregoing method embodiments, and specific implementations thereof may refer to descriptions of the foregoing method embodiments, which are not repeated herein for brevity.

The disclosed embodiments also provide a computer readable storage medium having stored thereon computer program instructions which, when executed by a processor, implement the above-described method. The computer readable storage medium may be a non-volatile computer readable storage medium.

The embodiment of the disclosure also provides an electronic device, which comprises: a processor; a memory for storing processor-executable instructions; wherein the processor is configured to invoke the instructions stored in the memory to perform the above method.

The disclosed embodiments also provide a computer program product comprising computer readable code which, when run on a device, causes a processor in the device to execute instructions for implementing the image processing method as provided in any of the embodiments above.

The disclosed embodiments also provide another computer program product for storing computer readable instructions that, when executed, cause a computer to perform the operations of the image processing method provided in any of the above embodiments.

The electronic device may be provided as a terminal, server or other form of device.

Fig. 6 shows a block diagram of an electronic device 800, according to an embodiment of the disclosure. For example, electronic device 800 may be a mobile phone, computer, digital broadcast terminal, messaging device, game console, tablet device, medical device, exercise device, personal digital assistant, or the like.

Referring to fig. 6, an electronic device 800 may include one or more of the following components: a processing component 802, a memory 804, a power component 806, a multimedia component 808, an audio component 810, an input/output (I/O) interface 812, a sensor component 814, and a communication component 816.

The processing component 802 generally controls overall operation of the electronic device 800, such as operations associated with display, telephone calls, data communications, camera operations, and recording operations. The processing component 802 may include one or more processors 820 to execute instructions to perform all or part of the steps of the methods described above. Further, the processing component 802 can include one or more modules that facilitate interactions between the processing component 802 and other components. For example, the processing component 802 can include a multimedia module to facilitate interaction between the multimedia component 808 and the processing component 802.

The memory 804 is configured to store various types of data to support operations at the electronic device 800. Examples of such data include instructions for any application or method operating on the electronic device 800, contact data, phonebook data, messages, pictures, videos, and so forth. The memory 804 may be implemented by any type or combination of volatile or nonvolatile memory devices such as Static Random Access Memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic or optical disk.

The power supply component 806 provides power to the various components of the electronic device 800. The power components 806 may include a power management system, one or more power sources, and other components associated with generating, managing, and distributing power for the electronic device 800.

The multimedia component 808 includes a screen between the electronic device 800 and the user that provides an output interface. In some embodiments, the screen may include a Liquid Crystal Display (LCD) and a Touch Panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from a user. The touch panel includes one or more touch sensors to sense touches, swipes, and gestures on the touch panel. The touch sensor may sense not only an edge of a touch or slide action, but also a duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 808 includes a front camera and/or a rear camera. When the electronic device 800 is in an operational mode, such as a shooting mode or a video mode, the front camera and/or the rear camera may receive external multimedia data. Each front camera and rear camera may be a fixed optical lens system or have focal length and optical zoom capabilities.

The audio component 810 is configured to output and/or input audio signals. For example, the audio component 810 includes a Microphone (MIC) configured to receive external audio signals when the electronic device 800 is in an operational mode, such as a call mode, a recording mode, and a voice recognition mode. The received audio signals may be further stored in the memory 804 or transmitted via the communication component 816. In some embodiments, audio component 810 further includes a speaker for outputting audio signals.

The I/O interface 812 provides an interface between the processing component 802 and peripheral interface modules, which may be a keyboard, click wheel, buttons, etc. These buttons may include, but are not limited to: homepage button, volume button, start button, and lock button.

The sensor assembly 814 includes one or more sensors for providing status assessment of various aspects of the electronic device 800. For example, the sensor assembly 814 may detect an on/off state of the electronic device 800, a relative positioning of the components, such as a display and keypad of the electronic device 800, the sensor assembly 814 may also detect a change in position of the electronic device 800 or a component of the electronic device 800, the presence or absence of a user's contact with the electronic device 800, an orientation or acceleration/deceleration of the electronic device 800, and a change in temperature of the electronic device 800. The sensor assembly 814 may include a proximity sensor configured to detect the presence of nearby objects without any physical contact. The sensor assembly 814 may also include a light sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 814 may also include an acceleration sensor, a gyroscopic sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

The communication component 816 is configured to facilitate communication between the electronic device 800 and other devices, either wired or wireless. The electronic device 800 may access a wireless network based on a communication standard, such as WiFi,2G, or 3G, or a combination thereof. In one exemplary embodiment, the communication component 816 receives broadcast signals or broadcast related information from an external broadcast management system via a broadcast channel. In one exemplary embodiment, the communication component 816 further includes a Near Field Communication (NFC) module to facilitate short range communications. For example, the NFC module may be implemented based on Radio Frequency Identification (RFID) technology, infrared data association (IrDA) technology, ultra Wideband (UWB) technology, bluetooth (BT) technology, and other technologies.

In an exemplary embodiment, the electronic device 800 may be implemented by one or more Application Specific Integrated Circuits (ASICs), digital Signal Processors (DSPs), digital Signal Processing Devices (DSPDs), programmable Logic Devices (PLDs), field Programmable Gate Arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic elements for executing the methods described above.

In an exemplary embodiment, a non-transitory computer readable storage medium is also provided, such as memory 804 including computer program instructions executable by processor 820 of electronic device 800 to perform the above-described methods.

Fig. 7 illustrates a block diagram of an electronic device 1900 according to an embodiment of the disclosure. For example, electronic device 1900 may be provided as a server. Referring to FIG. 7, electronic device 1900 includes a processing component 1922 that further includes one or more processors and memory resources represented by memory 1932 for storing instructions, such as application programs, that can be executed by processing component 1922. The application programs stored in memory 1932 may include one or more modules each corresponding to a set of instructions. Further, processing component 1922 is configured to execute instructions to perform the methods described above.

The electronic device 1900 may also include a power component 1926 configured to perform power management of the electronic device 1900, a wired or wireless network interface 1950 configured to connect the electronic device 1900 to a network, and an input/output (I/O) interface 1958. The electronic device 1900 may operate an operating system based on a memory 1932, such as Windows Server ^TM ，Mac OS X ^TM ，Unix ^TM ,Linux ^TM ，FreeBSD ^TM Or the like.

In an exemplary embodiment, a non-transitory computer readable storage medium is also provided, such as memory 1932, including computer program instructions executable by processing component 1922 of electronic device 1900 to perform the methods described above.

The present disclosure may be a system, method, and/or computer program product. The computer program product may include a computer readable storage medium having computer readable program instructions embodied thereon for causing a processor to implement aspects of the present disclosure.

The computer readable storage medium may be a tangible device that can hold and store instructions for use by an instruction execution device. The computer readable storage medium may be, for example, but not limited to, an electronic storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of the computer-readable storage medium would include the following: portable computer disks, hard disks, random Access Memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), static Random Access Memory (SRAM), portable compact disk read-only memory (CD-ROM), digital Versatile Disks (DVD), memory sticks, floppy disks, mechanical coding devices, punch cards or in-groove structures such as punch cards or grooves having instructions stored thereon, and any suitable combination of the foregoing. Computer-readable storage media, as used herein, are not to be construed as transitory signals per se, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through waveguides or other transmission media (e.g., optical pulses through fiber optic cables), or electrical signals transmitted through wires.

The computer readable program instructions described herein may be downloaded from a computer readable storage medium to a respective computing/processing device or to an external computer or external storage device over a network, such as the internet, a local area network, a wide area network, and/or a wireless network. The network may include copper transmission cables, fiber optic transmissions, wireless transmissions, routers, firewalls, switches, gateway computers and/or edge servers. The network interface card or network interface in each computing/processing device receives computer readable program instructions from the network and forwards the computer readable program instructions for storage in a computer readable storage medium in the respective computing/processing device.

Computer program instructions for performing the operations of the present disclosure can be assembly instructions, instruction Set Architecture (ISA) instructions, machine-related instructions, microcode, firmware instructions, state setting data, or source or object code written in any combination of one or more programming languages, including an object oriented programming language such as Smalltalk, c++ or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The computer readable program instructions may be executed entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computer (for example, through the Internet using an Internet service provider). In some embodiments, aspects of the present disclosure are implemented by personalizing electronic circuitry, such as programmable logic circuitry, field Programmable Gate Arrays (FPGAs), or Programmable Logic Arrays (PLAs), with state information of computer readable program instructions, which can execute the computer readable program instructions.

Various aspects of the present disclosure are described herein with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the disclosure. It will be understood that each block of the flowchart illustrations and/or block diagrams, and combinations of blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer-readable program instructions.

These computer readable program instructions may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions/acts specified in the flowchart and/or block diagram block or blocks. These computer readable program instructions may also be stored in a computer readable storage medium that can direct a computer, programmable data processing apparatus, and/or other devices to function in a particular manner, such that the computer readable medium having the instructions stored therein includes an article of manufacture including instructions which implement the function/act specified in the flowchart and/or block diagram block or blocks.

The computer readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other devices to cause a series of operational steps to be performed on the computer, other programmable apparatus or other devices to produce a computer implemented process such that the instructions which execute on the computer, other programmable apparatus or other devices implement the functions/acts specified in the flowchart and/or block diagram block or blocks.

The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of instructions, which comprises one or more executable instructions for implementing the specified logical function(s). In some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

The computer program product may be realized in particular by means of hardware, software or a combination thereof. In an alternative embodiment, the computer program product is embodied as a computer storage medium, and in another alternative embodiment, the computer program product is embodied as a software product, such as a software development kit (Software Development Kit, SDK), or the like.

The foregoing description of the embodiments of the present disclosure has been presented for purposes of illustration and description, and is not intended to be exhaustive or limited to the embodiments disclosed. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the various embodiments described. The terminology used herein was chosen in order to best explain the principles of the embodiments, the practical application, or the improvement of technology in the marketplace, or to enable others of ordinary skill in the art to understand the embodiments disclosed herein.

Claims

1. An image processing method, comprising:

performing target feature extraction processing on a target region in a first color image of a preset scene acquired in a first time period to acquire target feature information of a target object in the first color image;

Inputting the dynamic visual information of the preset scene acquired at the first moment in the first time period into a first feature extraction network to acquire a first feature map corresponding to the dynamic visual information at the first moment, wherein the acquisition frequency of the dynamic visual information is higher than that of the color image, the first feature extraction network is trained through a second feature extraction network, and the second feature extraction network is used for extracting the feature map of the color image;

determining the position information of the target object at the first moment according to the target characteristic information and the first characteristic diagram, wherein the target object is any object in the preset scene;

determining, according to the target feature information and the first feature map, position information of the target object at the first moment, including:

determining a convolution kernel parameter according to the target characteristic information;

performing convolution processing on the first feature map according to the convolution kernel parameters to obtain a correlation thermodynamic diagram between the target feature information and the first feature map;

determining the position information of the target object at the first moment according to the related thermodynamic diagram;

The method further comprises the steps of:

performing feature extraction processing on a sample color image of a sample scene through a pre-trained second feature extraction network to obtain a first sample feature map;

performing feature extraction processing on sample dynamic visual information of the sample scene through a first feature extraction network to obtain a second sample feature map, wherein the sample dynamic visual information and the sample color image are acquired simultaneously;

determining network loss of a first feature extraction network according to the first sample feature map and the second sample feature map;

and training the first feature extraction network according to the network loss.

2. The method according to claim 1, wherein the method further comprises:

and decoding the first feature map to obtain a second color image at the first moment.

3. The method according to claim 2, wherein the method further comprises:

and according to the position information, carrying out segmentation processing on the target object in the second color image to obtain a segmentation mask diagram of the target object.

4. The method according to claim 1, wherein performing a target feature extraction process on a target region in a first color image in a first period of time of a preset scene to obtain target feature information of a target object in the first color image, includes:

Performing target detection processing on the first color image to obtain a target area where the target object is located;

and carrying out target feature extraction processing on the target region to obtain the target feature information.

5. The method of claim 1, wherein the first feature extraction network comprises a pulsed neural network and the second feature extraction network comprises a convolutional neural network.

6. An image processing apparatus, comprising:

the target feature information extraction module is used for carrying out target feature extraction processing on a target region in a first color image of a preset scene acquired in a first time period to obtain target feature information of a target object in the first color image;

the feature map extraction module is used for inputting the dynamic visual information of the preset scene acquired at the first moment in the first time period into a first feature extraction network to acquire a first feature map corresponding to the dynamic visual information at the first moment, wherein the acquisition frequency of the dynamic visual information is higher than that of the color image, the first feature extraction network is trained through a second feature extraction network, and the second feature extraction network is used for extracting the feature map of the color image;

The position information determining module is used for determining the position information of the target object at the first moment according to the target characteristic information and the first characteristic diagram, wherein the target object is any object in the preset scene;

the location information determination module is further to: determining a convolution kernel parameter according to the target characteristic information; performing convolution processing on the first feature map according to the convolution kernel parameters to obtain a correlation thermodynamic diagram between the target feature information and the first feature map; determining the position information of the target object at the first moment according to the related thermodynamic diagram;

the apparatus further comprises: the training module is used for carrying out feature extraction processing on the sample color image of the sample scene through a pre-trained second feature extraction network to obtain a first sample feature image; performing feature extraction processing on sample dynamic visual information of the sample scene through a first feature extraction network to obtain a second sample feature map, wherein the sample dynamic visual information and the sample color image are acquired simultaneously; determining network loss of a first feature extraction network according to the first sample feature map and the second sample feature map; and training the first feature extraction network according to the network loss.

7. An electronic device, comprising:

a processor;

a memory for storing processor-executable instructions;

wherein the processor is configured to invoke the instructions stored in the memory to perform the method of any of claims 1 to 5.

8. A computer readable storage medium having stored thereon computer program instructions, which when executed by a processor, implement the method of any of claims 1 to 5.