scholarly journals Auto-Zooming CNN-Based Framework for Real-Time Pedestrian Detection in Outdoor Surveillance Videos

IEEE Access ◽  
2019 ◽  
Vol 7 ◽  
pp. 105816-105826 ◽  
Author(s):  
Saghir Alfasly ◽  
Beibei Liu ◽  
Yongjian Hu ◽  
Yufei Wang ◽  
Chang-Tsun Li
Keyword(s):  
Real Time ◽  
Pedestrian Detection ◽  
Surveillance Videos

scholarly journals Building Feature Pool Effectively for Real-Time Pedestrian Detection

2018 ◽  
Vol 1069 ◽  
pp. 012107
Author(s):  
Jijun Yang ◽  
Yingdong Ma ◽  
Zhibin Zhang
Keyword(s):  
Real Time ◽  
Pedestrian Detection

scholarly journals Research on Lightweight Infrared Pedestrian Detection Model Algorithm for Embedded Platform

2021 ◽  
Vol 2021 ◽  
pp. 1-7
Author(s):  
Zhaoli Wu ◽  
Xin Wang ◽  
Chao Chen
Keyword(s):  
Real Time ◽  
Target Detection ◽  
Pedestrian Detection ◽  
Infrared Image ◽  
Far Infrared ◽  
Detection Algorithm ◽  
Model Parameters ◽  
Detection Accuracy ◽  
Detection Model ◽  
Embedded Platform

Due to the limitation of energy consumption and power consumption, the embedded platform cannot meet the real-time requirements of the far-infrared image pedestrian detection algorithm. To solve this problem, this paper proposes a new real-time infrared pedestrian detection algorithm (RepVGG-YOLOv4, Rep-YOLO), which uses RepVGG to reconstruct the YOLOv4 backbone network, reduces the amount of model parameters and calculations, and improves the speed of target detection; using space spatial pyramid pooling (SPP) obtains different receptive field information to improve the accuracy of model detection; using the channel pruning compression method reduces redundant parameters, model size, and computational complexity. The experimental results show that compared with the YOLOv4 target detection algorithm, the Rep-YOLO algorithm reduces the model volume by 90%, the floating-point calculation is reduced by 93.4%, the reasoning speed is increased by 4 times, and the model detection accuracy after compression reaches 93.25%.

Sign in / Sign up

Export Citation Format

Share Document