Benyuan Lü, Zhenfu Zhuo, Yongsai Han, Lichao Zhang. Target Detection Based on Faster Region Convolution Neural Network[J]. Laser & Optoelectronics Progress, 2021, 58(22): 2210017
- Laser & Optoelectronics Progress
- Vol. 58, Issue 22, 2210017 (2021)
Fig. 1. Detection flow chart of the Faster-RCNN algorithm
Fig. 2. Detection steps of the RPN
Fig. 3. Detection results of small targets by traditional algorithm. (a) Original image; (b) missing alarm image
Fig. 4. Structure of the improved Faster-RCNN algorithm
Fig. 5. Experimental results of different algorithms. (a) Average detection accuracy; (b) detection speed; (c) accuracy comparison result; (d) speed comparison
Fig. 6. Detection results of the improved algorithm. (a) Target missed detection map; (b) traditional algorithm; (c) improved algorithm
|
Table 1. Detection accuracy and speed under different candidate regions
|
Table 2. Detection accuracy and speed under different candidate frame fluctuation ranges
|
Table 3. Influence of adaptive confidence threshold on algorithm performance
|
Table 4. Influence of APR on algorithm performance
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