The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Download
Publications Copernicus
Download
Citation
Articles | Volume XLIII-B3-2020
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLIII-B3-2020, 153–159, 2020
https://doi.org/10.5194/isprs-archives-XLIII-B3-2020-153-2020
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLIII-B3-2020, 153–159, 2020
https://doi.org/10.5194/isprs-archives-XLIII-B3-2020-153-2020

  21 Aug 2020

21 Aug 2020

ORIENTED VEHICLE DETECTION IN HIGH-RESOLUTION REMOTE SENSING IMAGES BASED ON FEATURE AMPLIFICATION AND CATEGORY BALANCE BY OVERSAMPLING DATA AUGMENTATION

N. Mo and L. Yan N. Mo and L. Yan
  • School of geodesy and geomatics, Wuhan University, China

Keywords: Oriented Vehicle Detection, Oversampling Data Augmentation, Feature Amplification, Center Loss

Abstract. Vehicles usually lack detailed information and are difficult to be trained on the high-resolution remote sensing images because of small size. In addition, vehicles contain multiple fine-grained categories that are slightly different, randomly located and oriented. Therefore, it is difficult to locate and identify these fine categories of vehicles. Considering the above problems in high-resolution remote sensing images, this paper proposes an oriented vehicle detection approach. First of all, we propose an oversampling and stitching method to augment the training dataset by increasing the frequency of objects with fewer training samples in order to balance the number of objects in each fine-grained vehicle category. Then considering the effect of the pooling operations on representing small objects, we propose to improve the resolution of feature maps so that detailed information hidden in feature maps can be enriched and they can better distinguish the fine-grained vehicle categories. Finally, we design a joint training loss function for horizontal and oriented bounding boxes with center loss, to decrease the impact of small between-class diversity on vehicle detection. Experimental verification is performed on the VEDAI dataset consisting of 9 fine-grained vehicle categories so as to evaluate the proposed framework. The experimental results show that the proposed framework performs better than most of competitive approaches in terms of a mean average precision of 60.7% and 60.4% in detecting horizontal and oriented bounding boxes respectively.