Method and system for improving AI recognition rate based on video analysis technology

A technology of video analysis and recognition rate, applied in character and pattern recognition, machine learning, instruments, etc., can solve the problems of low recognition accuracy and low efficiency of recognition result optimization

Pending Publication Date: 2022-06-07
捻果科技(深圳)有限公司
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] This application provides a method and system for improving the recognition rate of AI based on video analysis technology, which solves the technical problems of low recognition accuracy and low optimization efficiency of recognition results in the actual use of AI. Based on video analysis technology, intelligent analysis The multi-angle video data of the identified object is combined with the collection angle to obtain the recognition result, and the recognition result is optimized, achieving the technical effect of improving the accuracy of AI recognition in the actual use process and improving the optimization efficiency of AI recognition results

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Method and system for improving AI recognition rate based on video analysis technology
  • Method and system for improving AI recognition rate based on video analysis technology
  • Method and system for improving AI recognition rate based on video analysis technology

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0028] like figure 1 As shown, the present application provides a method for improving AI recognition rate based on video analysis technology, wherein the method includes:

[0029] S100: Obtain first video data, where the first video data set includes multi-angle video collection data for the object to be identified;

[0030] Specifically, the object to be identified is any structure. Commonly, it can be flowers, trees, mechanical models, or other movable or immovable structures. The object to be identified is not specifically limited. It is a target structure recognized by AI. The system for improving the AI ​​recognition rate based on video analysis technology is mounted on the AI ​​recognition device. The AI ​​recognition device has a video capture module, and the video capture module includes a plurality of video capture devices. The video capture The device can be a camera or other real-time video capture device, and multiple video capture devices respectively capture mu...

Embodiment 2

[0072] Based on the same inventive concept as the method for improving AI recognition rate based on video analysis technology in the foregoing embodiment, such as Figure 5 As shown, the present application provides a system for improving AI recognition rate based on video analysis technology, wherein the system includes:

[0073] a first obtaining unit 11, the first obtaining unit 11 is configured to obtain first video data, and the first video data set includes multi-angle video collection data for the object to be identified;

[0074] The second obtaining unit 12, the second obtaining unit 12 is configured to perform video segmentation on the first video data according to the acquisition angle to obtain a plurality of sub-videos;

[0075] The third obtaining unit 13, the third obtaining unit 13 is configured to perform feature analysis according to a plurality of the sub-videos to obtain a plurality of identification results;

[0076] a first construction unit 14, the firs...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a method and system for improving the AI recognition rate based on the video analysis technology, and the method comprises the steps: obtaining first video data which comprises the multi-angle video collection data of a to-be-recognized object; performing video segmentation on the first video data according to an acquisition angle to obtain a plurality of sub-videos; performing feature analysis according to the plurality of sub-videos to obtain a plurality of recognition results; constructing a discrimination model; and discriminating and optimizing the accuracy rates of the plurality of recognition results through the discrimination model to obtain a first recognition result. The technical problems of low recognition accuracy and low recognition result optimization efficiency in the actual use process of AI are solved, the multi-angle video data of the recognized object are intelligently analyzed based on the video analysis technology, the recognition result is obtained in combination with the collection angle, the recognition result is optimized, and the recognition accuracy is improved. The technical effects of improving the recognition accuracy of the AI in the actual use process and improving the optimization efficiency of the recognition result of the AI are achieved.

Description

technical field [0001] The present invention relates to the technical field of artificial intelligence, in particular to a method and system for improving AI recognition rate based on video analysis technology. Background technique [0002] AI (Artificial Intelligence), common, AI recognition technology has been widely used in the daily work and life process at this stage, the automatic driving technology of automobiles, intelligent home appliance systems, intelligent robots or other related technology fields, AI recognition technology greatly It is convenient for people's daily work and life. AI recognition technology used in the automatic driving technology of cars can intelligently identify the current road vehicle driving conditions and avoid obstacles in time. AI recognition technology is suitable for smart home appliance systems, common, sweeping The robot can intelligently plan the cleaning range and intelligently identify obstacles. AI recognition technology can be u...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): G06V20/40G06V10/44G06V10/764G06K9/62G06N20/00
CPCG06N20/00G06F18/24
Inventor曾小菊孙志勇
Owner捻果科技(深圳)有限公司