ComNet: Combinational Neural Network for Object Detection in UAV-Borne Thermal Images

Minglei Li Xingke Zhao Jiasong Li Liangliang Nan

Information Theory Probability Statistics Theory and Methods Machine Learning Data Analysis Statistics Theory and Methods,Data Analysis mathscidoc:2106.19001

IEEE Transactions on Geoscience and Remote Sensing, 2020.10
We propose a deep learning-based method for object detection in UAV-borne thermal images that have the capability of observing scenes in both day and night. Compared with visible images, thermal images have lower requirements for illumination conditions, but they typically have blurred edges and low contrast. Using a boundary-aware salient object detection network, we extract the saliency maps of the thermal images to improve the distinguishability. Thermal images are augmented with the corresponding saliency maps through channel replacement and pixel-level weighted fusion methods. Considering the limited computing power of UAV platforms, a lightweight combinational neural network ComNet is used as the core object detection method. The YOLOv3 model trained on the original images is used as a benchmark and compared with the proposed method. In the experiments, we analyze the detection performances of the ComNet models with different image fusion schemes. The experimental results show that the average precisions (APs) for pedestrian and vehicle detection have been improved by 2%~5% compared with the benchmark without saliency map fusion and MobileNetv2. The detection speed is increased by over 50%, while the model size is reduced by 58%. The results demonstrate that the proposed method provides a compromise model, which has application potential in UAV-borne detection tasks.
No keywords uploaded!
[ Download ] [ 2021-06-21 15:30:45 uploaded by liangliangnan ] [ 3058 downloads ] [ 0 comments ]
@inproceedings{minglei2020comnet:,
  title={ComNet: Combinational Neural Network for Object Detection in UAV-Borne Thermal Images},
  author={Minglei Li, Xingke Zhao, Jiasong Li, and Liangliang Nan},
  url={http://archive.ymsc.tsinghua.edu.cn/pacm_paperurl/20210621153045774057847},
  booktitle={IEEE Transactions on Geoscience and Remote Sensing},
  year={2020},
}
Minglei Li, Xingke Zhao, Jiasong Li, and Liangliang Nan. ComNet: Combinational Neural Network for Object Detection in UAV-Borne Thermal Images. 2020. In IEEE Transactions on Geoscience and Remote Sensing. http://archive.ymsc.tsinghua.edu.cn/pacm_paperurl/20210621153045774057847.
Please log in for comment!
 
 
Contact us: office-iccm@tsinghua.edu.cn | Copyright Reserved