Paper
14 February 2020 TLCS-Anchor: a new anchor strategy for detecting small-scale unmanned aerial vehicle
Tao Xiong, Jing Hu, Xinxin Lu, Kan Jiang, Xiangjun Li
Author Affiliations +
Proceedings Volume 11430, MIPPR 2019: Pattern Recognition and Computer Vision; 114301S (2020) https://doi.org/10.1117/12.2541789
Event: Eleventh International Symposium on Multispectral Image Processing and Pattern Recognition (MIPPR2019), 2019, Wuhan, China
Abstract
Faster R-CNN is a general-purpose detection algorithm that performs well in most cases. However, Faster R-CNN performs poorly on detecting small-scale UAVs. In order to improve the detection performance for small-scale UAVs, a new anchor strategy (TLCS-Anchor) which could be adopted by Faster R-CNN is proposed in this paper. Firstly, the anchor templates are designed to be suitable for the UAV dataset by using the clustering method so that the aspect ratios and scales for anchors are more targeted to UAVs. Then, a new compensation strategy of anchors is proposed to help detect small-scale UAVs in this paper, which could not only improve the number of anchors matched with the UAVs, but also alleviate the problem that small-scale UAVs can’t match with enough anchors to some extent. Experimental results show that TLCS-Anchor can help improve the detection performance for UAVs, especially for small-scale UAVs. In theory, TLCS-Anchor can also be used to detect other small-scale targets.
© (2020) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Tao Xiong, Jing Hu, Xinxin Lu, Kan Jiang, and Xiangjun Li "TLCS-Anchor: a new anchor strategy for detecting small-scale unmanned aerial vehicle", Proc. SPIE 11430, MIPPR 2019: Pattern Recognition and Computer Vision, 114301S (14 February 2020); https://doi.org/10.1117/12.2541789
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Unmanned aerial vehicles

Target detection

Detection and tracking algorithms

Analytical research

Convolution

Artificial intelligence

Data processing

RELATED CONTENT

Research on fire detection algorithm based on deep learning
Proceedings of SPIE (October 13 2022)
Object detection based on deep learning
Proceedings of SPIE (December 16 2021)
UAV image object detection network based on Yolo
Proceedings of SPIE (October 10 2023)
Topologically clustering: a method for discarding mismatches
Proceedings of SPIE (November 15 2007)

Back to Top