TY - GEN
T1 - Image recognition of small UAVs based on faster RCNN
AU - Zhao, Jingbin
AU - Wei, Shengjun
AU - Xie, Hui
AU - Zhong, Hao
N1 - Publisher Copyright:
© 2020 ACM.
PY - 2020/12/9
Y1 - 2020/12/9
N2 - Image recognition of small UAVs is the basis of anti-UAV technology based on photoelectric detection. In this paper, an automatic image recognition method for small UAVs based on Faster RCNN is proposed. The deep residual network is adopted to extract image features of small UAVs. Then, the extracted features are input into the region proposal network, which can generate a region box that contains UAVs. The final recognition result is obtained through classification and regression. After training and testing the recognition model based on the dataset which contains thousands of images of common UAV on the market, the result shows that the recall of UAV recognition is 98%, the average precision is close to 97%, and the misdetection rate is low. The results of samples show that UAVs can be accurately recognized with less time, so the model owns good recognition performance.
AB - Image recognition of small UAVs is the basis of anti-UAV technology based on photoelectric detection. In this paper, an automatic image recognition method for small UAVs based on Faster RCNN is proposed. The deep residual network is adopted to extract image features of small UAVs. Then, the extracted features are input into the region proposal network, which can generate a region box that contains UAVs. The final recognition result is obtained through classification and regression. After training and testing the recognition model based on the dataset which contains thousands of images of common UAV on the market, the result shows that the recall of UAV recognition is 98%, the average precision is close to 97%, and the misdetection rate is low. The results of samples show that UAVs can be accurately recognized with less time, so the model owns good recognition performance.
KW - Anti-UAV
KW - Image Recognition of Small UAVs
KW - Low Slow and Small Targets
KW - Photoelectric Detection
UR - http://www.scopus.com/inward/record.url?scp=85102933291&partnerID=8YFLogxK
U2 - 10.1145/3448823.3448844
DO - 10.1145/3448823.3448844
M3 - Conference contribution
AN - SCOPUS:85102933291
T3 - ACM International Conference Proceeding Series
BT - Proceedings of the 2020 4th International Conference on Vision, Image and Signal Processing, ICVISP 2020
PB - Association for Computing Machinery
T2 - 4th International Conference on Vision, Image and Signal Processing, ICVISP 2020
Y2 - 9 December 2020 through 11 December 2020
ER -