Small target detection method based on unmanned aerial vehicle image

Abstract

The invention discloses a small target detection method based on an unmanned aerial vehicle image, which improves a YOLOv4 target detection method into a method suitable for unmanned aerial vehicle image target detection based on cavity convolution and a multi-scale feature layer, and comprises the following steps: determining the size of a priori frame; performing feature extraction; performing multi-scale fusion in combination with hole convolution; constructing a feature pyramid; extracting a multi-feature layer for target detection; screening out a prediction box by utilizing the positionof the prediction box and the prediction score; therefore, the problems of target shielding and small target detection in an unmanned aerial vehicle environment are solved; the accuracy of target detection is improved; and the detection performance of small targets is ensured.

Description

technical field [0001] The invention relates to computer vision technology and target detection technology, in particular to a method for realizing small target detection based on unmanned aerial vehicle images. Background technique [0002] In today's daily life, monitoring is ubiquitous, especially in crowded places such as squares, stations, residential quarters, and traffic roads, where a large number of cameras are distributed for real-time monitoring. Monitoring can realize crime prevention, traffic control, key target tracking, etc., and plays a vital role in maintaining social security. If the traditional manual method is used to process all the monitoring content, there will be problems such as visual fatigue, missed detection, and false detection. The intelligent image monitoring technology belonging to the field of artificial intelligence can use advanced algorithms to process massive image data, and provide users with more useful key information according to act...

Images