A New Method of Different Neural Network Depth and Feature Map Size on Remote Sensing Small Target Detection

Authors

  • Yaming Cao National Space Science Center, Chinese Academy of Sciences
  • ZHEN YANG National Space Science Center, Chinese Academy of Sciences
  • CHEN GAO National Space Science Center, Chinese Academy of Sciences

DOI:

https://doi.org/10.4114/intartif.vol24iss68pp21-32

Keywords:

Convolutional neural networks (CNNs), YOLO V3, small target, remote sensing

Abstract

Convolutional neural networks (CNNs) have shown strong learning capabilities in computer vision tasks such as classification and detection. Especially with the introduction of excellent detection models such as YOLO (V1, V2 and V3) and Faster R-CNN, CNNs have greatly improved detection efficiency and accuracy. However, due to the special angle of view, small size, few features, and complicated background, CNNs that performs well in the ground perspective dataset, fails to reach a good detection accuracy in the remote sensing image dataset. To this end, based on the YOLO V3 model, we used feature maps of different depths as detection outputs to explore the reasons for the poor detection rate of small targets in remote sensing images by deep neural networks. We also analyzed the effect of neural network depth on small target detection, and found that the excessive deep semantic information of neural network has little effect on small target detection. Finally, the verification on the VEDAI dataset shows, that the fusion of shallow feature maps with precise location information and deep feature maps with rich semantics in the CNNs can effectively improve the accuracy of small target detection in remote sensing images.

Downloads

Download data is not yet available.

Downloads

Published

2021-09-30

How to Cite

Cao, Y., YANG, Z., & GAO, C. (2021). A New Method of Different Neural Network Depth and Feature Map Size on Remote Sensing Small Target Detection. Inteligencia Artificial, 24(68), 21–32. https://doi.org/10.4114/intartif.vol24iss68pp21-32