ABSTRACT
As more and more monitoring devices are deployed in various cities around the world, the technology of intelligent analysis and processing of video image data based on the computer is becoming more and more mature. This paper adopts an algorithm based on the combination of traditional ViBe and YOLO algorithm to realize the pedestrian detection of internal personnel in the surveillance video. Firstly, ViBe algorithm is used to detect pedestrians once, and some pedestrian frames are selected. Then the pedestrian frames are sent to YOLO network for secondary detection. The second pedestrian detection based on deep learning uses K-means algorithm to complete the clustering of prior frames, and then uses the CSPDarkNet53 network to extract pedestrian features. In order to improve the ability of YOLO small target detection, SPP-Net structure is added to the YOLO model to improve the accuracy of small target detection. The self-built pedestrian dataset used to train and test on the constructed network. The experimental results show that the detection algorithm based on the combination of ViBe and YOLO optimizes the regression of pedestrian boundary frame improves the positioning accuracy of pedestrians.
- Ren Shaoqing Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks.[J]. IEEE transactions on pattern analysis and machine intelligence, 2017, 39(6): 1137-1149.Google Scholar
- Qike Shao, Lu Li, Yu Zhou, Shihang Yan. Pedestrain detection in videos based on optimization algorithm using sliding window[J].Journal of Zhejiang University of Technology,2015,43(02):212-216..Google Scholar
- David G. Lowe. Distinctive Image Features from Scale-Invariant Keypoints[J]. International Journal of Computer Vision, 2004, 60(2): 91-110.Google ScholarDigital Library
- Yangyang YE,Chi ZHANG,Xiaoli HAO.ARPNET: attention region proposal network for 3D object detection[J].Science China(Information Sciences),2019,62(12):44-52.Google Scholar
- Haar-features training parameters analysis in boosting based machine learning for improved face detection[J]. International Journal of Advanced Technology and Engineering Exploration (IJATEE), 2021, 8(80).Google Scholar
- Yucong Song. Traffic sign recognition based on HOG feature extraction[J]. Journal of Measurements in Engineering, 2021, 9(3): 142-155.Google ScholarCross Ref
- Yifei Geng and Geng Yifei and Lu Xiaobo. Vehicle and Driver Detection on Highway Based on Cascade R-CNN[J]. Journal of Physics: Conference Series, 2020, 1575(1) : 012017-.Google ScholarCross Ref
- Le Zhang and Jinsong Wang and Zhiyong An. Vehicle recognition algorithm based on Haar-like features and improved Adaboost classifier[J]. Journal of Ambient Intelligence and Humanized Computing, 2021, : 1-9.Google ScholarCross Ref
- Jiandong Zhao Detection of crowdedness in bus compartments based on ResNet algorithm and video images[J]. Multimedia Tools and Applications, 2021, : 1-28.Google Scholar
- Okwuashi Onuwa Deep support vector machine for PolSAR image classification[J]. International Journal of Remote Sensing, 2021, 42(17) : 6498-6536.Google ScholarCross Ref
- Multi-scale Pedestrian Detection in Thermal Imaging Using Deep Convolutional Neural Network and Adaptive NMS[J]. Journal of Korean Institute of Information Technology, 2018, 16(9) : 85-94.Google ScholarCross Ref
- Hosang J , Benenson R , Schiele B . Learning non-maximum suppression[C]// 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE Computer Society, 2017.Google Scholar
- Qiaokang Liang Automatic Basketball Detection in Sport Video Based on R-FCN and Soft-NMS[C]. , 2019.Google Scholar
- Shaoqing Ren, Kaiming He, Ross Girshick, and Jian Sun. Faster r-cnn: Towards real-time object detection with region proposal networks. Proc. Advances in Neural Information Processing Systems, 2015.Google Scholar
- Fan Yang, Wongun Choi, and Yuanqing Lin. Exploit all the layers: Fast and accurate cnn object detector with scale dependent pooling and cascaded rejection classifiers. Proc. IEEE Conference on Computer Vision and Pattern Recognition, 2016.Google ScholarCross Ref
- Tianrui Liu, Mohamed Elmikaty , and Tania Stathaki. Sam-rcnn: Scale-aware multi-resolution multi-channel pedestrian detection. Proc. British Machine Vision Conference, 2018.Google Scholar
- Mengmeng Xu, Yancheng Bai, Sally Sisi Qu, and Bernard Ghanem. Semantic part rcnn for real-world pedestrian detection. Proc. IEEE Conference on Computer Vision and Pattern Recognition Workshop, 2019.Google Scholar
- Cao Jiale From Handcrafted to Deep Features for Pedestrian Detection: A Survey.[J]. IEEE transactions on pattern analysis and machine intelligence, 2021, PP.Google Scholar
- Chen Hui and Sun Shuai. U-YOLO: higher precision YOLOv4[C]. , 2021.Google Scholar
Recommendations
Real-time pedestrian detection via hierarchical convolutional feature
With the development of pedestrian detection technologies, existing methods can not simultaneously satisfy high quality detection and fast calculation for practical applications. Therefore, the goal of our research is to balance of pedestrian detection ...
Context-aware pedestrian detection especially for small-sized instances with Deconvolution Integrated Faster RCNN (DIF R-CNN)
Pedestrian detection is a canonical problem in computer vision. Motivated by the observation that the major bottleneck of pedestrian detection lies on the different scales of pedestrian instances in images, our effort is focused on improving the ...
Remote Pedestrian Detection Algorithm Based on Edge Information Input CNN
HPCCT '19: Proceedings of the 2019 3rd High Performance Computing and Cluster Technologies ConferenceIn order to solve remote pedestrian detection problem, the target need to be detected in the absence of information, a new pedestrian detection algorithm based on Convolution Neural Network (CNN) is proposed. The algorithm uses shallow layer edge ...
Comments