Research on real-time object detection based on Yolo algorithm

Yuxin Zhao; Shaodong Wang

doi:10.54097/hset.v7i.1091

Authors

Yuxin Zhao
Shaodong Wang

DOI:

https://doi.org/10.54097/hset.v7i.1091

Keywords:

Object detection, YOLO V5, Deep learning, Intelligent Security

Abstract

Carrying controlled knives and guns and ammunition in public places is a serious threat to public safety, and the target proportion of images in monitoring is small, and the recognition background is complex. The existing monitoring methods in public places have problems that can not be well recognized automatically. Therefore, the YOLOV5 model is proposed to be applied in Intelligent Security to improve public safety. Focusing on the target detection of contraband in public under the application scenario of Intelligent Security, the characteristics and requirements of the detection task are analyzed, and the viewpoint of applying YOLOV5 algorithm to real-time detection of contraband is put forward. The history and basic principles of YOLO series algorithms and target detection are summarized. YOLOV5 performance test was carried out systematically to verify the feasibility of the method. Then, the detection dataset is made, format conversion and labeling are carried out, and the training data is expanded, and the related detection experiments are carried out on the computer. The results show that the contraband detection method based on YOLOV5 has great potential in practical application.

Downloads

Download data is not yet available.

References

Papageorgiou C P, Oren M, Poggio T. A general framework for object detection[C]//Sixth International Conference on Computer Vision (IEEE Cat. No. 98CH36271). IEEE, 1998: 555-562.

Zeiler M D, Fergus R. Visualizing and understanding convolutional networks [C] //European conference on computer vision. Springer, Cham, 2014: 818-833.

Zhao Z Q, Bian H, Hu D, et al. Pedestrian detection based on fast R-CNN and batch normalization[C] //International Conference on Intelligent Computing. Springer, Cham, 2017: 735-746.

Grauman K, Leibe B. Visual object recognition (synthesis lectures on artificial intelligence and machine learning)[J]. Morgan & Claypool, 2011, 3.

Yaseen Z M, El-Shafie A, Jaafar O, et al. Artificial intelligence based models for stream-flow forecasting: 2000–2015[J]. Journal of Hydrology, 2015, 530: 829-844.

Schmaltz C, Rosenhahn B, Brox T, et al. Region-based pose tracking[C] //Iberian Conference on Pattern Recognition and Image Analysis. Springer, Berlin, Heidelberg, 2007: 56-63.

Bouwmans T, El Baf F, Vachon B. Background modeling using mixture of gaussians for foreground detection-a survey[J]. Recent patents on computer science, 2008, 1(3): 219-237.

Papageorgiou C, Poggio T. A trainable system for object detection[J]. International journal of computer vision, 2000, 38(1): 15-33.

He K, Zhang X, Ren S, et al. Spatial pyramid pooling in deep convolutional networks for visual recognition[J]. IEEE transactions on pattern analysis and machine intelligence, 2015, 37(9): 1904-1916.

Chen D, Hua G, Wen F, et al. Supervised transformer network for efficient face detection[C]//European Conference on Computer Vision. Springer, Cham, 2016: 122-138.

Najibi M, Rastegari M, Davis L S. G-cnn: an iterative grid based object detector[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2016: 2369-2377.

Wu D, Lv S, Jiang M, et al. Using channel pruning-based YOLO v4 deep learning algorithm for the real-time and accurate detection of apple flowers in natural environments[J]. Computers and Electronics in Agriculture, 2020, 178: 105742.