Zhihao Pan, Ying Chen. Full-Convolution Object Detection Network Based on Clustering Region Generation[J]. Laser & Optoelectronics Progress, 2019, 56(15): 151001
- Laser & Optoelectronics Progress
- Vol. 56, Issue 15, 151001 (2019)
Fig. 1. Structure of R-FCN
Fig. 2. Structure of RPN
Fig. 3. Detection results of R-FCN. (a) Inaccurate locating; (b) serious detection error
Fig. 4. Improved network frame
Fig. 5. Basic structure of RPN clustering network
Fig. 6. Clustering detection results. (a) Average IOU with different K values; (b) detection accuracy with different K values; (c) clustering consuming with different K values
Fig. 7. Comparison of detection results before and after algorithm improvement. (a) Detection results of R-FCN; (b) detection results of improved algorithm
|
Table 1. Detection results with different methods based on ResNet-50
|
Table 2. Detection results with different methods based on RseNet-101
|
Table 3. All kinds of detection results with different methods based on RseNet-101
|
Table 4. Experimental results of generalization of K value
Set citation alerts for the article
Please enter your email address
© Copyright 2018-2021 | Chinese Laser Press. All Rights Reserved 沪ICP备15018463号-20