CN113506324A

CN113506324A - Image processing method and device, electronic equipment and storage medium

Info

Publication number: CN113506324A
Application number: CN202110801139.6A
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: 2021-10-15
Anticipated expiration: 2041-07-15
Also published as: CN113506324B

Abstract

The present disclosure relates to an image processing method and apparatus, an electronic device, and a storage medium, the method including: inputting dynamic visual information of a preset scene acquired at a first time within a first time period into a first feature extraction network to acquire a first feature map; inputting a first color image of a preset scene acquired at a second moment in a first time period into a second feature extraction network to acquire a second feature map; determining the characteristic variation between the second moment and the first moment according to the second characteristic diagram and the first characteristic diagram; and determining the position information of the target object at the first moment according to the first feature map and the feature variation. According to the image processing method disclosed by the embodiment of the disclosure, the second feature map can be obtained by utilizing the dynamic visual information with higher acquisition frequency, and the feature variation between the second feature map and the first feature map of the first color image is determined, so that the position information of the target object at the first moment is determined, and the tracking effect of the target object is improved.

Description

Image processing method and device, electronic equipment and storage medium

Technical Field

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

Background

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

Disclosure of Invention

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

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

In a possible implementation manner, determining, according to the first feature map and the feature variation, position information of a target object in the preset scene at the first time includes: according to the second feature map and the feature variation, performing feature updating processing on the second feature map to obtain a third feature map; performing target feature extraction processing on the first color image to obtain a feature vector of the target object; performing convolution processing on the third feature map according to the feature vector of the target object to obtain a related thermodynamic map between the feature vector and the third 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 third 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 image of the target object.

In one possible implementation, the method further includes: 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 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 obtained simultaneously; determining the network loss of the 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 image processing apparatus, the apparatus including: the first feature extraction module is used for inputting dynamic visual information of a preset scene acquired at a first time within a first time period into a first feature extraction network to acquire a first feature map; the second feature extraction module is used for inputting a first color image of the preset scene acquired at a second moment in the first time period into a second feature extraction network to acquire a second feature map, wherein the acquisition frequency of the dynamic visual information is higher than that of the color image, and the first feature extraction network is trained through the second feature extraction network; a feature variation determining module, configured to determine, according to the second feature map and the first feature map, a feature variation between the second time and the first time; and the position information determining module is used for determining the position information of the target object in the preset scene at the first moment according to the first feature map and the feature variation.

In one possible implementation, the location information determining module is further configured to: according to the second feature map and the feature variation, performing feature updating processing on the second feature map to obtain a third feature map; performing target feature extraction processing on the first color image to obtain a feature vector of the target object; performing convolution processing on the third feature map according to the feature vector of the target object to obtain a related thermodynamic map between the feature vector and the third 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 third 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 segmenting the target object in the second color image according to the position information to obtain a segmentation mask image of the target object.

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 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 obtained simultaneously; determining the network loss of the 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 an impulse 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 electronic device including: a processor; a memory for storing processor-executable instructions; wherein the processor is configured to invoke the memory-stored instructions to perform the above-described 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 present disclosure and, together with the description, serve to explain the principles of the disclosure.

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

FIG. 2 shows a schematic diagram of a feature update process according to an embodiment of the present disclosure;

FIG. 3 shows a schematic diagram of a related thermodynamic diagram in accordance with an embodiment of the present disclosure;

fig. 4 shows a schematic diagram of a split network according to an embodiment of the present disclosure;

fig. 5 shows an application schematic diagram of an image processing method according to an embodiment of the present disclosure;

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

FIG. 7 shows a block diagram of an electronic device according to an embodiment of the present disclosure;

fig. 8 illustrates a block diagram of an electronic device in accordance with an embodiment of the disclosure.

Detailed Description

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

The word "exemplary" is used exclusively 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" herein is merely an association describing an associated object, meaning that three relationships may exist, e.g., a and/or B, may mean: a exists alone, A and B exist simultaneously, 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, in the following detailed description, numerous specific details are set forth 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 that are well known to those skilled in the art have not been described in detail so as not to obscure the present disclosure.

Fig. 1 illustrates a flowchart of an image processing method according to an embodiment of the present disclosure, which includes, as illustrated in fig. 1:

in step S11, inputting the dynamic visual information of the preset scene obtained at the first time within the first time period into the first feature extraction network, so as to obtain a first feature map;

in step S12, inputting a first color image of the preset scene acquired at a second time within the first time period into a second feature extraction network to obtain a second feature map, where the acquisition frequency of dynamic visual information is higher than that of the color image, and the first feature extraction network is trained by the second feature extraction network;

in step S13, determining a feature variation amount between the second time and the first time based on the second feature map and the first feature map;

in step S14, position information of the target object in the preset scene at the first time is determined according to the first feature map and the feature variation.

According to the image processing method of the embodiment of the disclosure, the first feature map can be obtained by using the dynamic visual information with higher obtaining frequency, and the feature variation between the first feature map and the second feature map of the first color image is determined, so as to determine the position information of the target object at the first moment when the dynamic visual information is obtained. 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 a time period between two frames of color images can be determined through the characteristic variation, the tracking of the motion trail or the motion of a moving object is facilitated, and the tracking effect is improved.

In one possible implementation, the image processing method may be performed by an electronic device such as a terminal device or a server, 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 (PDA), a handheld device, a computing device, a vehicle-mounted device, a wearable device, or the like, and the method may be implemented by a processor calling a computer readable instruction stored in a memory. Alternatively, the method may be performed by a server.

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

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

In one possible implementation, the frame rate of the dynamic visual receptors is higher than that of a normal camera or webcam, for example, the frame rate of a camera or a conventional webcam is about 100fps, while the frame rate of the dynamic visual receptors is about 1,000,000 fps. Therefore, in the time interval between two frames of images shot by a common camera or a camera, a plurality of frames of dynamic visual information can be shot.

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

In another example, the start-stop time of the first time period may not be the time when the color image is acquired, and the length of the first time period may also be less than the time period between the two frames of color images acquired by the camera or the camera, so that only one frame of color image needs to be acquired in the first time period. The length and the starting time of the first time period are not limited by the present disclosure. For example, the start time of the first period may be before one frame of color image is captured, and the end time of the first period may be after one frame of color image is captured, and does not necessarily coincide with the time at which the color image is captured.

In one possible implementation, although the dynamic visual information is obtained frequently, the amount of information in the dynamic visual information of a single frame is small, and the pixel data is sparse. The characteristic extraction of the dynamic visual information is difficult to obtain a characteristic diagram with rich information. Therefore, the first feature extraction network may be trained by using the second feature extraction network, and feature extraction may be performed by using the trained first feature extraction network. In an example, the first feature extraction network comprises an impulse neural network and the second feature extraction network comprises a convolutional neural network. The present disclosure does not limit the type of the first feature extraction network and the second feature extraction network. The second feature extraction network may be configured to extract a feature map of a color image, where the color image is a general image acquired by a camera or a camera and may have rich image information, and the feature map with rich information may be obtained through feature extraction processing of the second feature extraction network (e.g., a convolutional neural network), and may include, for example, color information, position information of an object, object contour information, and the like. The first feature extraction network is trained through the second feature extraction network, so that the feature graph of the dynamic visual information acquired by the first feature extraction network is close to the feature graph of the color image acquired by the second feature extraction network, namely, the feature information contained in the feature graph 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, through the training, the feature map of the color image extracted by the second feature extraction network is consistent with or close to the feature map of the dynamic visual information extracted by the first feature extraction network.

In an example, since the dynamic visual information does not include color information, the position information and the object contour information of the object included in the feature map of the dynamic visual information extracted by the first feature extraction network may be made to be close to or identical with the position information and the object contour information of the object included in the feature map of the color image extracted by the second feature extraction network by the above training. The present disclosure does not limit the categories of information included in the feature map.

In a possible implementation manner, in step S11, the dynamic visual information of the preset scene acquired at the first time within the first time period may be input into the trained first feature extraction network for processing, so as to obtain a first feature map, where feature information included in the first feature map is consistent with or close to feature information obtained by performing feature extraction on the color image.

In a possible implementation manner, the first time may be a time at which any one frame of dynamic visual information is acquired within a first time period, and the first time may be different from a second time at which the first color image is acquired, that is, if a target object in the preset scene moves in a time interval between the first time and the second time, the position information and/or the contour information of the target object at the first time is different from the position information and/or the contour information of the target object at the second time.

In one possible implementation, in step S12, the second feature extraction network may acquire a second feature map of the first color image at a second time. As described above, the position information and/or contour information of the target object in the second feature map is different from the position information and/or contour information of the target object in the first feature map, that is, the second feature map contains different feature information from the first feature map, that is, the difference in feature information due to the motion of the target object.

In a possible implementation manner, due to the low acquisition frequency of the color images, it is difficult to track the target object through the color images in the time interval between the two frames of color images, and the dynamic visual image is acquired with a high frequency, so that the target object can be tracked through the dynamic visual image, for example, the first time is the time in the time interval between the two frames of color images, and the position of the target object at the time can be determined by using the dynamic visual information acquired at the time. By the method, the positions of the target object at a plurality of moments in the time interval between the two frames of color images are obtained, and the motion trail of the target object is tracked.

In an example, the position of the target object at the first time instant may be directly determined by a first feature map of the dynamic visual information acquired at the first time instant. The second feature map may also be updated by a feature difference between the first feature map and the second feature map, thereby obtaining a position of the target object at the first time. Because the first feature map is a feature map of dynamic visual information, the feature map may not include image information such as color information, and if a color image at a first time needs to be acquired after the position of the target object is determined, the effect of directly decoding the first feature map may not be good, so that the second feature map may be updated through a feature difference between the first feature map and the second feature map, that is, on the basis of the second feature map, information such as the position and the contour of the target object is updated, and image information such as color information of the second feature map may be retained, the acquired updated feature map includes not only the position information of the target object at the first time but also image information such as color information, and a color image with higher fidelity may be acquired after decoding.

In one possible implementation, in step S13, a feature difference between the first feature map and the second feature map, that is, a feature variation between the second time and the first time, which may include a variation of the position information of the target object, may be determined. The second feature map may be updated in step S14 by the feature variation, for example, the position of the target object in the second feature map is updated, and the position of the target object is determined by the updated feature map. Step S14 may include: according to the second feature map and the feature variation, performing feature updating processing on the second feature map to obtain a third feature map; performing target feature extraction processing on the first color image to obtain a feature vector of the target object; performing convolution processing on the third feature map according to the feature vector of the target object to obtain a related thermodynamic map between the feature vector and the third 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 second feature map may be updated by a feature variation, for example, the feature variation includes a variation of the position information of the target object, and the position information of the target object in the second feature map may be updated by the variation of the position information to obtain the third feature map. And further determining the position information of the target object at the first moment through the third feature map. Further, in this way, position information of the target object at a plurality of times at which the dynamic visual information is acquired can be obtained.

Fig. 2 shows a schematic diagram of a feature update process according to an embodiment of the present disclosure. As shown in FIG. 2, t may be₀And inputting the first color image obtained at the moment (second moment) into a second feature extraction network for processing to obtain a second feature map. And can convert t₁Dynamic visual information at a moment (first moment) is input into a first feature extraction network to obtain a first feature map. The first feature map may include a target object at t₁The position information of the time can be obtained by using the position information between the first characteristic diagram and the second characteristic diagramThe feature change amount updates the feature of the second feature map, for example, the position information of the target object in the second feature map is updated, a third feature map can be obtained, the third feature map can retain the image information such as the color information of the second feature map, and the position information of the target object can be updated to the position information of the target object at t₁Location information of the time of day.

In one possible implementation, the target object may be determined at t in the third feature map₁The position information of the time (first time), for example, the feature vector of the target object may be determined first. In an example, the first color image may be subjected to a target feature extraction process to obtain a feature vector of the target object. For example, the region where the target object is located may be detected in the first color image (for example, the region where the target object is located is detected by a neural network or the like), and then feature extraction processing may be performed on the region where the target object is located (for example, 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 a feature vector of the target object.

In one possible implementation, the convolution processing may be performed on the third feature map according to the feature vector of the target object, for example, a convolution kernel parameter may be determined by the feature vector of the target object, and the convolution processing performed by the convolution layer having the convolution kernel parameter may be performed, where in a result of the convolution processing (i.e., a correlation thermodynamic diagram between the feature vector and the third feature map), a pixel value of each pixel represents a similarity between the feature vector and each position in the third feature map. The third feature map has a high pixel value at a position where the similarity with the feature vector of the target object is high, and has a low pixel value at a position where the similarity with the feature vector of the target object is low. The position in the third feature map with the highest feature similarity (for example, similarity of 1) to the feature vector is the position of the target object at the first time.

Fig. 3 shows a schematic diagram of a related thermodynamic diagram 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, and the position with the highest similarity is the position of the target object in the third feature map. As shown in fig. 3, the position information of the positions of the target object a, the target object B, and the target object C in the third feature map is respectively shown. I.e. the position information of target object a, target object B and target object C at the first moment in time.

In a possible implementation manner, based on the above manner, the amount of feature change between the first feature map and the second feature map of the dynamic visual information at multiple time instants can be further determined, and the position information of the target object at multiple time instants can be determined.

In this way, the second feature map can be updated through the feature variation between the first feature map and the second feature map at the first moment to obtain the position information of the target object at the first moment, and the position information of the target object can be obtained at multiple moments in the time interval of acquiring the color image, so that the frequency of obtaining the position information of the target object is improved, and the tracking effect of the target object is improved.

In one possible implementation, the method further includes: and decoding the third feature map to obtain a second color image at the first moment. Since the third feature map can retain image information such as color information of the second feature map and update the position information of the target object, decoding the third feature map can obtain a color image after the position information of the target object is updated, that is, the second color image. In the color image, the position of the target object is the position of the target object at the first moment, and the color image also retains image information such as color information of the second characteristic diagram, so that the second color image has higher reality while accurately tracking the position information of the target object.

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

Fig. 4 shows a schematic diagram of a segmentation network according to an embodiment of the disclosure, as shown in fig. 4, the segmentation network 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, for example, the score of a pixel may be a probability value, which may indicate a probability that the pixel is a pixel in a region in which the target object is located, for example, if the probability is greater than a probability threshold (e.g., 50%), which may indicate that the pixel is located in the region in which the target object is located. The present disclosure does not limit the network structure of the split network.

In a possible implementation manner, before performing the feature extraction process using the first feature extraction network and the second feature extraction network, the first feature extraction network and the second feature extraction network may be trained. The first feature extraction network and the second feature extraction network may be trained separately.

In an example, for the second feature extraction network for extracting the feature information of the color image, the training may be performed by using the sample color image with the label information, for example, the network loss of the second feature extraction network may be determined according to the difference between the feature map of the sample color image extracted by the second feature extraction network and the label information, and the network parameter of the second feature extraction network may be adjusted by 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 a preset training number is reached, the trained second feature extraction network is obtained, and for example, the training condition may include network loss convergence, that is, after the network loss converges in a preset interval, the trained second feature extraction network is obtained. 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 to coincide with or be 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 second feature extraction network that is pre-trained.

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

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, for example, a position difference of a 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 position difference.

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

In a possible implementation manner, the trained first feature extraction network and second 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 fast, when the position of the target object changes greatly in a time interval of acquiring color images, it is difficult to effectively track the target object only through the color images, and the first feature extraction network may extract the feature map of the dynamic visual information in the time interval, and may determine the amount of change in the features between the feature map of the dynamic visual information and the feature map of the color image extracted by the second feature extraction network, and further determine the position information of the target object at the time of acquiring the dynamic visual information, so as to improve the acquisition frequency of the position information of the target object, and improve the tracking effect of the target object.

According to the image processing method disclosed by the embodiment of the disclosure, the first feature extraction network can be trained through the pre-trained second feature extraction network, so that the feature graph of the dynamic visual information extracted by the first feature extraction network is consistent with or close to the feature graph of the color image extracted by the second feature extraction network. The first feature extraction network can be used for extracting the feature map of the dynamic visual information in the time interval of obtaining the color image, and further the feature variation between the feature map of the dynamic visual information and the feature map of the color image extracted by the second feature extraction network can be determined, so that the position information of the target object at the moment of obtaining the dynamic visual information can be obtained, the obtaining frequency of obtaining the position information of the target object can be improved, and the tracking effect of the target object can be improved.

FIG. 5 is a schematic diagram illustrating an application of an image processing method according to an embodiment of the present disclosure, as shown in FIG. 5The camera or pick-up head can acquire a color image A of a target object (e.g., a eagle)₀The frequency of acquiring the color image by the camera or the camera is low, the moving speed of the target object is high, the position information of the target object may be changed greatly in the time interval of acquiring the color image, and the target object is tracked only by the color image.

In a possible implementation manner, the tracking effect can be enhanced by dynamic visual information, and the acquisition frequency of the dynamic visual information is higher than that of the color image, so that in the time interval of acquiring the color image, multiple frames of dynamic visual information, for example, a, can be acquired_t0、A_t1、A_t2、A_t3And the like. However, the pixel data of the dynamic visual information is sparse, and 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) can be trained through the pre-trained second feature extraction network (the feature map for extracting the color image) to make the feature map of the dynamic visual information extracted by the first feature extraction network 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 can be extracted through the first feature extraction network to determine the position information of the target object at the moment of acquiring the dynamic visual information through the feature map.

In one possible implementation, color image A may be extracted by a second feature extraction network₀The feature map of any dynamic visual information is extracted through the first feature extraction network, the feature variation between the two feature maps is caused by the action of the target object, and the feature map of the color image can be updated by using the feature map of the dynamic visual information. For example, the wing of the target object is moved, which causes the above-described feature variation, and the feature map of the color image can be updated using the feature variation.

In one possible implementation, the feature vector of the target object may be extracted, and the updated feature map may be subjected to convolution processing to obtain a correlation thermodynamic diagram between the feature vector and the feature map, so that the position information of the target object may be determined, for example, the position information of the wing of the target object at the time when the dynamic visual information is obtained may be determined. And then the position and the posture of the target object at the moment of obtaining the dynamic visual information can be obtained. In this way, the position and posture of the target object at a plurality of times of obtaining the dynamic visual information can be obtained.

Fig. 6 illustrates a block diagram of an image processing apparatus according to an embodiment of the present disclosure, which includes, as illustrated in fig. 6: the first feature extraction module 11 is configured to input dynamic visual information of a preset scene, which is acquired at a first time within a first time period, into a first feature extraction network to acquire a first feature map; a second feature extraction module 12, configured to input a first color image of the preset scene, acquired at a second time within the first time period, into a second feature extraction network to obtain a second feature map, where an acquisition frequency of dynamic visual information is higher than an acquisition frequency of the color image, and the first feature extraction network is trained through the second feature extraction network; a characteristic variation determining module 13, configured to determine, according to the second characteristic diagram and the first characteristic diagram, a characteristic variation between the second time and the first time; and a position information determining module 14, configured to determine, according to the first feature map and the feature variation, position information of a target object in the preset scene at the first time.

It is understood that the above-mentioned method embodiments of the present disclosure can be combined with each other to form a combined embodiment without departing from the logic of the principle, which is limited by the space, and the detailed description of the present disclosure is omitted. Those skilled in the art will appreciate that in the above methods of the specific embodiments, the specific order of execution of the steps should be determined by their function and possibly their inherent logic.

In addition, the present disclosure also provides an image processing apparatus, an electronic device, a computer-readable storage medium, and a program, which can be used to implement any one of the image processing methods provided by the present disclosure, and the descriptions and corresponding descriptions of the corresponding technical solutions and the corresponding descriptions in the methods section are omitted for brevity.

In some embodiments, functions of or modules included in the apparatus provided in the embodiments of the present disclosure may be used to execute the method described in the above method embodiments, and specific implementation thereof may refer to the description of the above method embodiments, and for brevity, will not be described again here.

Embodiments of the present disclosure also provide a computer-readable storage medium having stored thereon computer program instructions, which when executed by a processor, implement the above-mentioned method. The computer readable storage medium may be a non-volatile computer readable storage medium.

An embodiment of the present disclosure further provides an electronic device, including: a processor; a memory for storing processor-executable instructions; wherein the processor is configured to invoke the memory-stored instructions to perform the above-described method.

The embodiments of the present disclosure also provide a computer program product, which includes computer readable code, and when the computer readable code runs on a device, a processor in the device executes instructions for implementing the image processing method provided in any one of the above embodiments.

The embodiments of the present disclosure also provide another computer program product for storing computer readable instructions, which 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. 7 illustrates a block diagram of an electronic device 800 in accordance with an embodiment of the disclosure. For example, the electronic device 800 may be a mobile phone, a computer, a digital broadcast terminal, a messaging device, a game console, a tablet device, a medical device, a fitness device, a personal digital assistant, or the like terminal.

Referring to fig. 7, electronic device 800 may include one or more of the following components: processing component 802, memory 804, power component 806, multimedia component 808, audio component 810, input/output (I/O) interface 812, sensor component 814, and 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 components 802 may include one or more processors 820 to execute instructions to perform all or a portion of the steps of the methods described above. Further, the processing component 802 can include one or more modules that facilitate interaction 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 non-volatile 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 disks.

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 supplies, and other components associated with generating, managing, and distributing power for the electronic device 800.

The multimedia component 808 includes a screen that provides an output interface between the electronic device 800 and a user. 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 an input signal from a user. The touch panel includes one or more touch sensors to sense touch, slide, and gestures on the touch panel. The touch sensor may not only sense an edge of a touch or slide action, but also detect a duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 808 includes a front facing camera and/or a rear facing camera. The front camera and/or the rear camera may receive external multimedia data when the electronic device 800 is in an operation mode, such as a shooting mode or a video mode. Each front camera and rear camera may be a fixed optical lens system or have a focal length and optical zoom capability.

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 further be stored in the memory 804 or transmitted via the communication component 816. In some embodiments, audio component 810 also 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 keyboards, click wheels, buttons, etc. These buttons may include, but are not limited to: a home button, a volume button, a start button, and a lock button.

The sensor assembly 814 includes one or more sensors for providing various aspects of state assessment for the electronic device 800. For example, the sensor assembly 814 may detect an open/closed state of the electronic device 800, the relative positioning of components, such as a display and keypad of the electronic device 800, the sensor assembly 814 may also detect a change in the position of the electronic device 800 or a component of the electronic device 800, the presence or absence of user contact with the electronic device 800, orientation or acceleration/deceleration of the electronic device 800, and a change in the temperature of the electronic device 800. Sensor assembly 814 may include a proximity sensor configured to detect the presence of a nearby object 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 gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

The communication component 816 is configured to facilitate wired or wireless communication between the electronic device 800 and other devices. 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 an exemplary embodiment, the communication component 816 receives a broadcast signal or broadcast related information from an external broadcast management system via a broadcast channel. In an 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, micro-controllers, microprocessors or other electronic components for performing the above-described methods.

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

Fig. 8 illustrates a block diagram of an electronic device 1900 in accordance with an embodiment of the disclosure. For example, the electronic device 1900 may be provided as a server. Referring to fig. 8, electronic device 1900 includes a processing component 1922 further including one or more processors and memory resources, represented by memory 1932, for storing instructions, e.g., applications, executable by processing component 1922. The application programs stored in memory 1932 may include one or more modules that each correspond to a set of instructions. Further, the processing component 1922 is configured to execute instructions to perform the above-described method.

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 based on an operating system, such as Windows Server, stored in memory 1932^TM，Mac OS X^TM，Unix^TM,Linux^TM，FreeBSD^TMOr the like.

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

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

The computer readable storage medium may be a tangible device that can hold and store the instructions for use by the instruction execution device. The computer readable storage medium may be, for example, but not limited to, an electronic memory device, a magnetic memory device, an optical memory device, an electromagnetic memory device, a semiconductor memory 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: 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), a Static Random Access Memory (SRAM), a portable compact disc read-only memory (CD-ROM), a Digital Versatile Disc (DVD), a memory stick, a floppy disk, a mechanical coding device, such as punch cards or in-groove projection structures having instructions stored thereon, and any suitable combination of the foregoing. Computer-readable storage media as used herein is not to be construed as transitory signals per se, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through a waveguide or other transmission medium (e.g., optical pulses through a fiber optic cable), or electrical signals transmitted through electrical 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 via 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 transmission, wireless transmission, routers, firewalls, switches, gateway computers and/or edge servers. The network adapter 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.

The computer program instructions for carrying out operations of the present disclosure may be assembler 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 execute 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 type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider). In some embodiments, the electronic circuitry that can execute the computer-readable program instructions implements aspects of the present disclosure by utilizing the state information of the computer-readable program instructions to personalize the electronic circuitry, such as a programmable logic circuit, a Field Programmable Gate Array (FPGA), or a Programmable Logic Array (PLA).

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 storing the instructions comprises 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 flowchart 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 embodied in hardware, software or a combination thereof. In an alternative embodiment, the computer program product is embodied in a computer storage medium, and in another alternative embodiment, the computer program product is embodied in a Software product, such as a Software Development Kit (SDK), or the like.

Having described embodiments of the present disclosure, the foregoing description is intended to be exemplary, not exhaustive, and not limited to the disclosed embodiments. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The terminology used herein is chosen in order to best explain the principles of the embodiments, the practical application, or improvements made to the 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:

inputting dynamic visual information of a preset scene acquired at a first time within a first time period into a first feature extraction network to acquire a first feature map;

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

determining the feature variation between the second moment and the first moment according to the second feature map and the first feature map;

and determining the position information of the target object in the preset scene at the first moment according to the first feature map and the feature variation.

2. The method according to claim 1, wherein determining the position information of the target object in the preset scene at the first time according to the first feature map and the feature variation comprises:

according to the second feature map and the feature variation, performing feature updating processing on the second feature map to obtain a third feature map;

performing target feature extraction processing on the first color image to obtain a feature vector of the target object;

performing convolution processing on the third feature map according to the feature vector of the target object to obtain a related thermodynamic map between the feature vector and the third feature map;

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

3. The method of claim 2, further comprising:

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

4. The method of claim 3, further comprising:

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

5. The method of claim 1, further comprising:

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 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 obtained simultaneously;

determining the network loss of the 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.

6. The method of claim 1, wherein the first feature extraction network comprises an impulse neural network and the second feature extraction network comprises a convolutional neural network.

7. An image processing apparatus characterized by comprising:

the first feature extraction module is used for inputting dynamic visual information of a preset scene acquired at a first time within a first time period into a first feature extraction network to acquire a first feature map;

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

a feature variation determining module, configured to determine, according to the second feature map and the first feature map, a feature variation between the second time and the first time;

and the position information determining module is used for determining the position information of the target object in the preset scene at the first moment according to the first feature map and the feature variation.

8. The apparatus of claim 7, wherein the location information determining module is further configured to:

9. An electronic device, comprising:

a processor;

a memory for storing processor-executable instructions;

wherein the processor is configured to invoke the memory-stored instructions to perform the method of any of claims 1 to 6.

10. A computer readable storage medium having computer program instructions stored thereon, which when executed by a processor implement the method of any one of claims 1 to 6.