Laser & Optoelectronics Progress, Volume. 56, Issue 5, 051002(2019)
Object Detectionin of Remote Sensing Images Based on Convolutional Neural Networks
Figures & Tables(11)
Fig. 1. Schematic of rotation transformation. (a) Rotation principle; (b) target rotation
Fig. 4. Statistical figure of angle distribution. (a) Histogram of angle distribution; (b) targets with different orientations
Table 1. Performance comparison among different detection methods
View tableTable 1. Performance comparison among different detection methods
Detection method Detection time of image /s AP /% HOG+SVM 1.03 64.61 Faster R-CNN 0.31 96.58 Faster R-CNN+STN 0.31 97.31
Table 2. Comparison of detection results for different classes%
View tableTable 2. Comparison of detection results for different classes%
Detection method AP of plane AP of car AP of ship HOG+SVM 64.61 61.40 60.97 Faster R-CNN 96.58 88.35 84.87 Faster R-CNN+STN 97.31 89.71 84.76
Tools
Get Citation
Copy Citation Text
Pan Ou, Zheng Zhang, Kui Lu, Zeyang Liu. Object Detectionin of Remote Sensing Images Based on Convolutional Neural Networks[J]. Laser & Optoelectronics Progress, 2019, 56(5): 051002
Paper Information
Category: Image Processing
Received: Aug. 6, 2018
Accepted: Sep. 21, 2018
Published Online: Jul. 31, 2019
The Author Email: Zheng Zhang (seirios@buaa.edu.cn)
© Copyright 2018-2021 | Chinese Laser Press.
All Rights Reserved 沪ICP备15018463号-20