Martian Dust Devil Detection Based on Improved Faster R-CNN

Abstract

A dust devil is an important part of the Martian climate system, which can help us better understand scientific questions of the climate, surface–atmosphere interactions, aeolian processes, and regolith on Mars. Therefore, the automatic detection of dust devils from Mars orbiter images is becoming increasingly important for the scientific study and the planning of future robotic and manned missions. To improve the generalization, detection efficiency, and accuracy of the traditional approach in automatically detecting dust devils, we made several modifications to the faster region-based convolution neural network. Based on the characteristics of the dust devil, we proposed a Martian dust devil detection network (MDDD Net). The network uses the feature pyramid network to obtain a feature fusion map with rich location information and semantic information. The k-means++ algorithm is used to design reasonable anchor boxes to adapt to vary sized dust devils. The region of interest align unit is introduced to eliminate the mapping deviation between the feature map and the original image. Finally, the soft nonmaximum suppression algorithm is used to complete the screening of the bounding box. It can reduce missing detections caused by the overlapping between adjacent dust devil bounding boxes in the same image. The average precision and recall of MDDD Net on the dust devil dataset built in this article reach 90.1% and 96.5%, respectively.

Keywords

• Dust devil
• faster region-based convolution neural network (faster R-CNN)
• feature pyramid network (FPN)
• K-means++
• Mars
• region of interest align (ROI align)