Xiangsheng Zhang, Qing Shen. Multitarget Tracking Algorithm Based on an Improved YOLOv3 Algorithm[J]. Laser & Optoelectronics Progress, 2021, 58(16): 1610004
- Laser & Optoelectronics Progress
- Vol. 58, Issue 16, 1610004 (2021)
Fig. 1. Structure of standard convolution filters
Fig. 2. Structure of depthwise convolution filters
Fig. 3. Structure of pointwise convolution filters
Fig. 4. SENet structure
Fig. 5. Improved YOLOv3 network model structure diagram
Fig. 6. Multi-target tracking algorithm flow
Fig. 7. Intersection-over-union of different number of anchors
Fig. 8. Comparison of algorithm tracking results based on MOT15-PETS09 sequence. (a) YOLOv3-Deep-SORT tracking results; (b) our algorithm tracking results
Fig. 9. Comparison of algorithm tracking results based on MOT16-06 sequence. (a) YOLOv3-Deep-SORT tracking results; (b) our algorithm tracking results
Fig. 10. Comparison of algorithm tracking results based on ETHZ-eth02 sequence. (a) YOLOv3-Deep-SORT tracking results; (b) our algorithm tracking results
|
Table 1. Size of a priori boxes with different numbers of a priori boxes
|
Table 2. Target detection algorithm performance comparison results
|
Table 3. Comparison of the indicators of the test set on different sequences
|
Table 4. Comparison of evaluation indexes of multi-target tracking algorithms
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