Open AccessSmall sample vehicle target recognition method for unmanned aerial vehicle system based on deep learning
Author(s) -
Tingping Zhang,
Di Wan
Publication year - 2021
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1982/1/012077
Subject(s) - artificial intelligence , deep learning , computer science , aerial image , process (computing) , computer vision , feature extraction , sample (material) , object detection , feature (linguistics) , pattern recognition (psychology) , image (mathematics) , linguistics , philosophy , operating system , chemistry , chromatography
Vehicle target detection technology refers to the process of vehicle detection and recognition in the image data set of different backgrounds by means of feature extraction. The vehicle target detection technology based on deep learning shows obvious advantages in the accuracy and speed of target detection. With the development of science and technology, the detection and recognition of vehicles in UAV aerial images has become an important applied research direction. This paper studies the detection and recognition of UAV aerial vehicle based on deep learning, and proposes a new deep learning-based algorithm to solve the problem that incomplete vehicle targets in the UAV aerial vehicle based on YOLOV3 algorithm cannot be recognized, and vehicles close to the UAV aerial vehicle are missed. Experimental verification results show that, compared with the existing algorithms, the proposed algorithm can significantly improve the detection accuracy of UAV aerial vehicle based on deep learning while ensuring real-time performance.