TY - GEN
T1 - A Small UAV Detection Method Based on Optical Flow and Visual Feature Fusion
AU - Li, Miao
AU - Wang, Hanzhuo
AU - Mao, Shengjian
AU - Shi, Zhiguo
AU - Tao, Ran
N1 - Publisher Copyright:
© 2023 IEEE.
PY - 2023
Y1 - 2023
N2 - The rapid growth of the unmanned aerial vehicle (UAV) market poses threats to public safety and personal privacy. Visual detection has become a cost-effective and important method for UAV detection, but it struggles with detecting small and distant UAVs that lack clear morphological features. To address this, we propose Fusion Net, a network detection approach that combines optical flow features with visual features for improved detection. Fusion Net utilizes Convolutional Neural Networks (CNNs) and Transformers for feature extraction and fusion, achieving excellent detection results. We also introduce Mask Augmentation, a new data augmentation method, to enhance network convergence and diversity in UAV scenes. Fusion Net, pre-trained on the Drone-vs-Bird dataset, exhibits excellent performance in detecting small drones, as demonstrated by its high detection accuracy in our self-made dataset evaluation.
AB - The rapid growth of the unmanned aerial vehicle (UAV) market poses threats to public safety and personal privacy. Visual detection has become a cost-effective and important method for UAV detection, but it struggles with detecting small and distant UAVs that lack clear morphological features. To address this, we propose Fusion Net, a network detection approach that combines optical flow features with visual features for improved detection. Fusion Net utilizes Convolutional Neural Networks (CNNs) and Transformers for feature extraction and fusion, achieving excellent detection results. We also introduce Mask Augmentation, a new data augmentation method, to enhance network convergence and diversity in UAV scenes. Fusion Net, pre-trained on the Drone-vs-Bird dataset, exhibits excellent performance in detecting small drones, as demonstrated by its high detection accuracy in our self-made dataset evaluation.
KW - Unmanned aerial vehicle detection
KW - feature fusion
KW - video object detection
UR - http://www.scopus.com/inward/record.url?scp=85186088681&partnerID=8YFLogxK
U2 - 10.1109/ICCT59356.2023.10419529
DO - 10.1109/ICCT59356.2023.10419529
M3 - Conference contribution
AN - SCOPUS:85186088681
T3 - International Conference on Communication Technology Proceedings, ICCT
SP - 1420
EP - 1427
BT - 2023 IEEE 23rd International Conference on Communication Technology
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 23rd IEEE International Conference on Communication Technology, ICCT 2023
Y2 - 20 October 2023 through 22 October 2023
ER -