Detection method of small moving target with complex background based on two-stream method

Abstract

The present invention discloses a method for detecting small moving objects with complex background based on a dual-stream method. The method includes: 1. Using a method based on deep learning to process a single video frame image to obtain the appearance feature flow in space, and here On the basis of target detection; 2. Use the inter-frame difference method to process continuous video frame images to obtain temporal motion feature flow, and perform moving target detection on this basis; 3. 1 and 2 in the whole picture 4. Combine the appearance detection confidence of the deep learning target detector in 1 and the dual-stream fusion confidence in 3 to give the final detection result. While ensuring the real-time detection, the method of the invention effectively reduces the missed detection rate of the target, and suppresses the interference of the background to the detection, so as to realize the detection of a small target with a complex background with a high recall rate and a low false detection rate.

Description

technical field [0001] The invention belongs to the field of computer vision, and in particular relates to a method for detecting small moving targets with complex backgrounds based on a dual-stream method. Background technique [0002] In recent years, with the development of related technologies and the gradual opening of low-altitude airspace, airspace targets such as small unmanned aerial vehicles, model aircraft, gliders, and delta wings have gradually increased. Although this type of small aircraft brings many conveniences in aerial photography, plant protection, rescue, logistics, etc., due to the increasing number of people using such aircraft and the lack of supervision by relevant departments, the "black flight" of such aircraft The frequent occurrence of "indiscriminate flying" has brought various hidden dangers to public safety, personal safety and personal privacy. In order to deal with such hidden dangers, it is necessary to counteract drones that invade speci...

AI Technical Summary

Problems solved by technology

For scenes where visual detection technology is used to detect small targets in complex backgrounds, since the target is far away from the surveillance camera and the monitoring environment is complex, the acquired observation targets have weak signals, small imaging areas, weak shape or texture features, and no fixed movement rules. There are many challenges in achieving such goals with high accuracy, low false detection, and less missed detection.

Images