TY - GEN
T1 - Deep Learning-Based UAV-To-UAV Small Target Detection
AU - Zuo, Guobiao
AU - Zhou, Kang
AU - Wang, Qiang
N1 - Publisher Copyright:
© Beijing HIWING Scientific and Technological Information Institute 2024.
PY - 2024
Y1 - 2024
N2 - In UAV-to-UAV detection, most of the target UAVs are small targets due to the changing viewpoints of the source UAVs and the unstable motion of the target UAVs. In order to improve the performance of UAV-to-UAV small target detection, we optimize its backbone network based on the YOLOv5 target detection algorithm by incorporating the channel-space self-attention mechanism to improve the attention to small target feature information. Meanwhile, we also propose a new loss function, Focal-CIoU, to make the network pay more attention to high-quality samples. In order to further improve the UAV localization accuracy, we also use the KMeans + + algorithm to cluster the anchor frames in order to make the set anchor frames more compatible with the UAV target. In addition, we also use various data enhancement strategies such as mosaic, blend, copy, and paste to increase the richness of the samples. Experimental results show that our proposed algorithm performs very excellently in the tiny UAV target detection task. And achieves a performance of 81.6% and 41.9% on AP50 and AP{50:95} metrics, respectively, which are 7% and 4.6% better compared to the original YOLOv5 algorithm. Our proposed algorithm is also more competitive compared to the current SOTA algorithm.
AB - In UAV-to-UAV detection, most of the target UAVs are small targets due to the changing viewpoints of the source UAVs and the unstable motion of the target UAVs. In order to improve the performance of UAV-to-UAV small target detection, we optimize its backbone network based on the YOLOv5 target detection algorithm by incorporating the channel-space self-attention mechanism to improve the attention to small target feature information. Meanwhile, we also propose a new loss function, Focal-CIoU, to make the network pay more attention to high-quality samples. In order to further improve the UAV localization accuracy, we also use the KMeans + + algorithm to cluster the anchor frames in order to make the set anchor frames more compatible with the UAV target. In addition, we also use various data enhancement strategies such as mosaic, blend, copy, and paste to increase the richness of the samples. Experimental results show that our proposed algorithm performs very excellently in the tiny UAV target detection task. And achieves a performance of 81.6% and 41.9% on AP50 and AP{50:95} metrics, respectively, which are 7% and 4.6% better compared to the original YOLOv5 algorithm. Our proposed algorithm is also more competitive compared to the current SOTA algorithm.
KW - Attention
KW - Loss
KW - Small target
KW - Target detection
KW - UAV-to-UAV
UR - http://www.scopus.com/inward/record.url?scp=85192554510&partnerID=8YFLogxK
U2 - 10.1007/978-981-97-1107-9_45
DO - 10.1007/978-981-97-1107-9_45
M3 - Conference contribution
AN - SCOPUS:85192554510
SN - 9789819711062
T3 - Lecture Notes in Electrical Engineering
SP - 485
EP - 494
BT - Proceedings of 3rd 2023 International Conference on Autonomous Unmanned Systems (3rd ICAUS 2023) - Volume I
A2 - Qu, Yi
A2 - Gu, Mancang
A2 - Niu, Yifeng
A2 - Fu, Wenxing
PB - Springer Science and Business Media Deutschland GmbH
T2 - 3rd International Conference on Autonomous Unmanned Systems, ICAUS 2023
Y2 - 9 September 2023 through 11 September 2023
ER -