CN-122023857-A - Method, device, equipment and storage medium for object identification and charging management

Abstract

According to embodiments of the present disclosure, a method, apparatus, device, and storage medium for object recognition are provided. The method includes determining a reference feature set including a set of reference text features corresponding to a set of preset classifications and a set of reference image features corresponding to a set of reference images, wherein the reference images correspond to image regions in the sample image identified as respective preset classifications, and processing the target image based on the reference feature set to generate an object recognition result for the target image, the object recognition result indicating a target object in the target image that matches the set of preset classifications. Therefore, the embodiment of the invention can effectively improve the success rate of object identification of the model.

Inventors

• WEI YANAN
• CAI YEHE
• WANG RUI

Assignees

• 北京航迹科技有限公司

Dates

Publication Date

20260512

Application Date

20241111

Claims (12)

1. 1. An object recognition method, comprising: Determining a set of reference features comprising a set of reference text features corresponding to a set of preset classifications and a set of reference image features corresponding to a set of reference images, wherein the reference images correspond to image regions in the sample image identified as respective preset classifications, and And processing a target image based on the reference feature set to generate an object recognition result of the target image, wherein the object recognition result indicates a target object matched with the set of preset classifications in the target image.
2. 2. The method of claim 1, further comprising: Determining a target image area corresponding to the target object in the target image based on the object recognition result, the target image area corresponding to a target preset classification, and Updating the reference feature set based on the target image region.
3. 3. The method of claim 2, wherein updating the reference feature set based on the target image region comprises: determining candidate image features corresponding to the target image region, and Determining whether similarity information between the candidate image feature and the set of reference text features and/or the set of reference image features meets a preset condition, and And in response to the similarity information meeting a preset condition, adding the candidate image features to the reference feature set to serve as new reference image features.
4. 4. A method according to claim 3, wherein determining whether similarity information between the candidate image feature and the set of reference text features and/or the set of reference image features meets a preset condition comprises: determining a first similarity of the candidate image feature to a first set of reference text features of the set of reference text features, the first set of reference text features and the target image region corresponding to the same target preset classification; Determining a second similarity of the candidate image feature to a second set of text features of the set of reference text features, the second set of text features and the target image region corresponding to different preset classifications, and And determining that the similarity information meets a preset condition based on the first similarity and the second similarity.
5. 5. The method of claim 4, wherein determining that the similarity information satisfies a preset condition based on the first similarity and the second similarity comprises: Determining a third similarity of the candidate image feature to at least one image feature of the set of reference image features, the at least one image feature corresponding to the target preset classification, in response to the first similarity being greater than a first threshold and the second similarity being less than a second threshold, and And in response to the third similarity being smaller than a third threshold, determining that the similarity information meets the preset condition.
6. 6. The method of claim 1, wherein the set of reference text features is determined by processing a set of text content corresponding to the set of preset classifications using a multi-modal pre-training model.
7. 7. The method of claim 1, wherein processing a target image based on the reference feature set to generate an object recognition result for the target image comprises: Determining a plurality of target image features corresponding to a plurality of feature scales based on the target image, and The plurality of target image features and the set of reference features are provided to an object recognition model to generate the object recognition result.
8. 8. The method of claim 1, wherein the target image comprises a traffic image and the set of preset classifications corresponds to classes of objects in a traffic scene.
9. 9. An apparatus for object recognition, comprising: a determination module configured to determine a set of reference features including a set of reference text features corresponding to a set of preset classifications and a set of reference image features corresponding to a set of reference images, wherein the reference images correspond to image regions in the sample image identified as respective preset classifications, and And a processing module configured to process a target image based on the reference feature set to generate an object recognition result of the target image, the object recognition result indicating a target object in the target image that matches the set of preset classifications.
10. 10. An electronic device, comprising: at least one processing unit, and At least one memory coupled to the at least one processing unit and storing instructions for execution by the at least one processing unit, the instructions when executed by the at least one processing unit cause the electronic device to perform the method according to any one of claims 1 to 8.
11. 11. A computer readable storage medium having stored thereon a computer program executable by a processor to implement a method according to any one of claims 1 to 8.
12. 12. A computer program product comprising computer executable instructions which when executed by a processor implement the method according to any one of claims 1 to 8.

Description

Method, device, equipment and storage medium for object identification and charging management Technical Field Example embodiments of the present disclosure relate generally to the field of computers and, more particularly, relate to a method, apparatus, device, and computer-readable storage medium for object recognition. Background With the vigorous development of intelligent driving technology, the object recognition technology is being subjected to unprecedented innovation as a key support for popularization. Conventional object recognition technology is usually used for recognizing objects in images based on text features of different categories, and has poor accuracy, so that the requirement of the current intelligent driving technology on the object recognition accuracy is difficult to meet. Disclosure of Invention In a first aspect of the present disclosure, there is provided a method of object recognition, the method comprising determining a set of reference features comprising a set of reference text features corresponding to a set of preset classifications and a set of reference image features corresponding to a set of reference images, wherein the reference images correspond to image regions in a sample image identified as respective preset classifications, and processing a target image based on the set of reference features to generate an object recognition result for the target image, the object recognition result being indicative of a target object in the target image that matches the set of preset classifications. In a second aspect of the present disclosure, an apparatus for providing object recognition is provided. The apparatus includes a determination module configured to determine a set of reference features including a set of reference text features corresponding to a set of preset classifications and a set of reference image features corresponding to a set of reference images, wherein the reference images correspond to image regions in a sample image identified as respective preset classifications, and a processing module configured to process a target image based on the set of reference features to generate an object recognition result for the target image, the object recognition result being indicative of a target object in the target image that matches the set of preset classifications. In a third aspect of the present disclosure, a terminal device is provided. The apparatus includes at least one processing unit, and at least one memory coupled to the at least one processing unit and storing instructions for execution by the at least one processing unit. The instructions, when executed by at least one processing unit, cause the apparatus to perform the method of the first aspect. In a fourth aspect of the present disclosure, a computer-readable storage medium is provided. The computer readable storage medium has stored thereon a computer program executable by a processor to implement the method of the first aspect. In a fifth aspect of the present disclosure, a computer program product is provided. The computer program product comprises computer executable instructions which, when executed by a processor, implement the method of the first aspect. It should be understood that what is described in this section of the disclosure is not intended to limit key features or essential features of the embodiments of the disclosure, nor is it intended to limit the scope of the disclosure. Other features of the present disclosure will become apparent from the following description. Drawings The above and other features, advantages and aspects of embodiments of the present disclosure will become more apparent by reference to the following detailed description when taken in conjunction with the accompanying drawings. In the drawings, wherein like or similar reference numerals denote like or similar elements, in which: FIG. 1 illustrates a schematic diagram of an example environment in which embodiments of the present disclosure may be implemented; FIG. 2 illustrates a flow chart of object recognition according to some embodiments of the present disclosure; FIG. 3A illustrates a frame diagram of an object recognition process according to some embodiments of the present disclosure; FIG. 3B illustrates a schematic diagram of a feature screening process according to some embodiments of the present disclosure; FIG. 4 illustrates a block diagram of an apparatus for object recognition according to some embodiments of the present disclosure; fig. 5 illustrates a block diagram of an electronic device capable of implementing various embodiments of the present disclosure. Detailed Description Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While certain embodiments of the present disclosure have been illustrated in the accompanying drawings, it is to be understood that the present disclosure may be embodied in various forms and should