Sie befinden Sich nicht im Netzwerk der Universität Paderborn. Der Zugriff auf elektronische Ressourcen ist gegebenenfalls nur via VPN oder Shibboleth (DFN-AAI) möglich. mehr Informationen...
Research on Target Detection algorithm based on Deep Learning Technology
Ist Teil von
2021 IEEE International Conference on Power Electronics, Computer Applications (ICPECA), 2021, p.137-142
Ort / Verlag
IEEE
Erscheinungsjahr
2021
Link zum Volltext
Quelle
IEL
Beschreibungen/Notizen
This paper summarizes the research progress of target detection using convolution neural network in recent years. These studies not only cover the design of all kinds of convolution neural network target detection algorithms, but also provide a deeper perspective for the development of computer vision. On the basis of consulting the data, this paper focuses on the representative Faster-RCNN, YOLO V3 and SSD algorithms. By reviewing their predecessor algorithms, covering the current mainstream target detection algorithms, and analyzing the technologies they use, summarize and analyze their advantages and disadvantages. And in the last part, it points out the still existing problems in target detection and the development direction in the future.