A multi-category, multi-scale and multi-target capture method and system

Abstract

The present invention discloses a multi-category, multi-scale and multi-target capture method and system, belonging to the technical field of artificial intelligence and computer vision, comprising the following steps: acquiring panoramic video processing frames from miscellaneous scenes; performing intelligent real-time multi-category, multi-scale and multi-target detection ; Perform category-by-category online multi-target tracking; de-duplicate and select the best for snapshots; transmit the capture results to the server or data center. Real-time detection and analysis of videos with multiple categories, multiple scales, and many targets on a front-end camera, and efficient acquisition of classified, high-quality, and low-redundancy targets Object capture results.

Description

technical field [0001] The invention belongs to the technical field of artificial intelligence and computer vision, and in particular relates to a multi-category, multi-scale and multi-target capturing method and system. Background technique [0002] The traditional method of artificial naked eye security monitoring, or the method of sending the monitoring screen back to the server has been unable to "digest" the continuous massive video monitoring data in time, and the need for intelligent target capture is becoming more and more urgent. Some measures have been taken to improve traditional security monitoring technology: [0003] In the patent CN201911235029.7, a method, device and system for capturing a target are disclosed. The combination of the gun and the ball camera is used to perform target characteristics on the first monitoring screen of the gun and the second monitoring screen of the ball camera. Matching, capturing at least one target to be captured that is succ...

AI Technical Summary

Problems solved by technology

Although the system uses the Tornado framework or the Flask framework to build a data queue for sending video frames from multiple clients to the server, it is still impossible for the server to process huge amounts of data in a timely manner, facing the risk of system crashes in the case of large concurrent processing. Unable to effectively reduce data transmission pressure and storage pressure

[0005] The disadvantage of the existing technology is that many cameras on the market can only capture a single category or even a specific single target. For complex scenes of pedestrians, motor vehicles, and non-motor vehicles, multiple cameras are needed to capture them. Simultaneous deployment and control, in a complex scene where pedestrians, motor vehicles, and non-motor vehicles are mixed, it is impossible to realize real-time detection and analysis of videos with multiple categories, multiple scales, and many targets on one front-end camera. Obtain classified, high-quality image quality, and low-redundancy target object capture results

And, because the accuracy of its detection and tracking is not satisfactory, it is easy to cause more missed captures or repeated redundant captures, and the delay is relatively large

Images