Target detection method and device, storage medium and equipment

Abstract

The invention relates to a target detection method and device, a storage medium and a device. The method comprises the steps of obtaining a video stream; performing target detection on the first frameimage and the secondary frame image in sequence to obtain a first detection result and a second detection result, wherein the first frame of image is a first frame of image which meets a target detection condition and is not subjected to target detection in the video stream, and the secondary frame of image is a first frame of image which meets the target detection condition after the first frameof image; determining a video interval according to the first frame image and the secondary frame image, and performing target tracking on the images in the video interval in sequence based on the first detection result to obtain a target tracking result; and fusing the second detection result and the target tracking result to obtain a target detection result. According to the invention, high-precision target detection can be carried out on the video stream in real time.

Description

technical field [0001] The present disclosure relates to the technical field of computer vision, and in particular to an object detection method, device, storage medium and equipment. Background technique [0002] At present, in many scenarios where target detection is required, the degree of reliance on manual detection is still relatively obvious. For example, in the security inspection of items carried in public places such as subways and airports, it is often necessary to rely on security inspectors to perform security inspections on items. Use X-ray security inspection machines image objects, and security inspectors manually identify dangerous targets based on the imaging results; this manual inspection is time-consuming and labor-intensive, and has limited accuracy. The object detection method can be applied to the above-mentioned scenarios, but the speed, accuracy and intelligence level of the object detection method in related technologies still need to be improved. ...

AI Technical Summary

Problems solved by technology

[0002] At present, in many scenarios where target detection is required, the degree of reliance on manual detection is still relatively obvious. For example, in the security inspection of items carried in public places such as subways and airports, it is often necessary to rely on security inspectors to perform security inspections on items. Use X-ray security inspection machines image objects, and security inspectors manually identify dangerous targets based on the imaging results; this manual detection is time-consuming and labor-intensive, and has limited accuracy

The method of target detection can be applied to the above scenarios, but the speed, accuracy and level of intelligence of the target detection method in related technologies still need to be improved

Images