Optics and Precision Engineering, Volume. 31, Issue 6, 860(2023)
Multi-object pedestrian tracking method based on improved high resolution neural network
Fig. 2. Structure diagram of bottleneck(left) and bottle2neck(right)
Fig. 4. Structural contrast diagram of basicblock(left) and 2ECA-basicblock(right)
Fig. 6. Visualization of tensors in the middle layer of the network
Fig. 7. Tracking results on Eth-PedCross2 (frames 46, 57 and 69 from left to right)
Fig. 8. Tracking results on MOT17-02-DPM (frames 1,50,100 and 150 from left to right)
Fig. 9. Tracking results on MOT20-04 (frames 0,10,50 and 100 from left to right)
|
|
|
|
|
|
Get Citation
Copy Citation Text
Hongying ZHANG, Pengyi HE, Xiaowen PENG. Multi-object pedestrian tracking method based on improved high resolution neural network[J]. Optics and Precision Engineering, 2023, 31(6): 860
Category: Information Sciences
Received: May. 26, 2022
Accepted: --
Published Online: Apr. 4, 2023
The Author Email: Hongying ZHANG (carole_zhang0716@163.com)