TY - GEN
T1 - Arbitrary-Oriented Dense Object Detection in Remote Sensing Imagery
AU - Yingxue, Chen
AU - Wenrui, Ding
AU - Hongguang, Li
AU - Yufeng, Wang
AU - Shuo, Liu
AU - Xiao, Zhifeng
N1 - Publisher Copyright:
© 2018 IEEE.
PY - 2018/7/2
Y1 - 2018/7/2
N2 - Automatic object detection in remote sensing images is of significant importance with widespread practical applications. However, complex backgrounds, small size and dense arrangement of objects, as well as the various orientations of the target pose great challenges for current object detection algorithms. In this paper, an arbitrary-oriented dense object detection network is proposed to predict the object area using oriented bounding boxes. Firstly, we present a method to predict the object angle according to the features in the proposal, which does not increase computation costs by utilizing weight sharing. Then, a bound conversion algorithm is built to generate the oriented bounding box of an object according to the result of axis-aligned horizontal box and predicted angle information. In addition, we employ a two-stage NMS algorithm to reduce the omission ratio for dense objects by introducing oriented boxes to compute overlapping ratio. Detailed evaluations on the DOTA dataset demonstrate the effectiveness of the proposed method.
AB - Automatic object detection in remote sensing images is of significant importance with widespread practical applications. However, complex backgrounds, small size and dense arrangement of objects, as well as the various orientations of the target pose great challenges for current object detection algorithms. In this paper, an arbitrary-oriented dense object detection network is proposed to predict the object area using oriented bounding boxes. Firstly, we present a method to predict the object angle according to the features in the proposal, which does not increase computation costs by utilizing weight sharing. Then, a bound conversion algorithm is built to generate the oriented bounding box of an object according to the result of axis-aligned horizontal box and predicted angle information. In addition, we employ a two-stage NMS algorithm to reduce the omission ratio for dense objects by introducing oriented boxes to compute overlapping ratio. Detailed evaluations on the DOTA dataset demonstrate the effectiveness of the proposed method.
KW - Index Trems-object detection
KW - arbitraty-oriented
KW - convolutional neural network
KW - remote sensing
UR - https://www.scopus.com/pages/publications/85063649136
U2 - 10.1109/ICSESS.2018.8663939
DO - 10.1109/ICSESS.2018.8663939
M3 - 会议稿件
AN - SCOPUS:85063649136
T3 - Proceedings of the IEEE International Conference on Software Engineering and Service Sciences, ICSESS
SP - 436
EP - 440
BT - ICSESS 2018 - Proceedings of 2018 IEEE 9th International Conference on Software Engineering and Service Science
A2 - Wenzheng, Li
A2 - Babu, M. Surendra Prasad
PB - IEEE Computer Society
T2 - 9th IEEE International Conference on Software Engineering and Service Science, ICSESS 2018
Y2 - 23 November 2018 through 25 November 2018
ER -