journal article·2019-09-03Open access

Investigation of a Promoted You Only Look Once Algorithm and Its Application in Traffic Flow Monitoring

Chang-Yu Cao, Jia-Chun Zheng, Yi-Qi Huang, Jing Liu, Cheng-Fu Yang

Applied Sciences· Volume 9· Issue 17

Abstract

We propose a high-performance algorithm while using a promoted and modified form of the You Only Look Once (YOLO) model, which is based on the TensorFlow framework, to enhance the real-time monitoring of traffic-flow problems by an intelligent transportation system. Real-time detection and traffic-flow statistics were realized by adjusting the network structure, optimizing the loss function, and introducing weight regularization. This model, which we call YOLO-UA, was initialized based on the weight of a YOLO model pre-trained while using the VOC2007 data set. The UA-CAR data set with complex weather conditions was used for training, and better model parameters were selected through tests and subsequent adjustments. The experimental results showed that, for different weather scenarios, the accuracy of the YOLO-UA was ~22% greater than that of the YOLO model before optimization, and the recall rate increased by about 21%. On both cloudy and sunny days, the accuracy, precision, and recall rate of the YOLO-UA model were more than 94% above the floating rate, which suggested that the precision and recall rate achieved a good balance. When used for video testing, the YOLO-UA model yielded traffic statistics with an accuracy of up to 100%; the time to count the vehicles in each frame was less than 30 ms and it was highly robust in response to changes in scenario and weather.
Source: crossref · Quality: baseline

Research context

OpenAlex topics: Traffic Prediction and Management Techniques · Autonomous Vehicle Technology and Safety · Traffic control and management

SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.

Affiliations

Navigation Institute, Jimei University, Xiamen 361021, China

School of Information Engineering, Jimei University, Xiamen 361021, China

Department of Chemical and Materials Engineering, National University of Kaohsiung, Kaohsiung 811, Taiwan

References (38)

Show source-provided references
1. Big Data Analytics in Intelligent Transportation Systems: A Survey10.1109/TITS.2018.2815678 ↗
2. A Compact Circularly Polarized Antenna for 5.8-GHz Intelligent Transportation System10.1109/LAWP.2016.2587771 ↗
3. Smart ITS Sensor for the Transportation Planning Based on IoT Approaches Using Serverless and Microservices Architecture10.1109/MITS.2018.2806620 ↗
4. Scale-Free Properties of Human Mobility and Applications to Intelligent Transportation Systems10.1109/TITS.2018.2866970 ↗
5. Sampling from Gaussian Markov Random Fields Using Stationary and Non-Stationary Subgraph Perturbations10.1109/TSP.2014.2375134 ↗
6. Application of Gaussian Algorithm in Traffic Statistics of Road Traffic
7. Video Vehicle Statistics Method Based on Background Modeling
8. Statistics of Video Traffic Flow Based on Vehicle Classifier
9. A Virtual Coiling Technique for Image-Based Aneurysm Models by Dynamic Path Planning10.1109/TMI.2012.2219626 ↗
10. Night traffic flow detection based on Kinect depth virtual coil
11. Coordinated Target Tracking Strategy for Multiple Unmanned Underwater Vehicles with Time Delays10.1109/ACCESS.2018.2793338 ↗
12. A Model-Based Joint Detection and Tracking Approach for Multi-Vehicle Tracking with Lidar Sensor10.1109/TITS.2015.2391131 ↗
13. Vehicle detection and tracking method based on multi-scale edge fusion and SURF feature matching
14. Region-based convolutional networks for accurate object detection and segmentation10.1109/TPAMI.2015.2437384 ↗
15. Spatial pyramid pooling in deep convolutional networks for visual recognition10.1109/TPAMI.2015.2389824 ↗
16. Girshick, R. (2015, January 7–13). Fast r-cnn. Proceedings of the IEEE International Conference on Computer Vision (ICCV), Santiago, Chile.10.1109/ICCV.2015.169 ↗
17. Toward Fast and Accurate Vehicle Detection in Aerial Images Using Coupled Region-Based Convolutional Neural Networks10.1109/JSTARS.2017.2694890 ↗
18. Fast Object Detection at Constrained Energy10.1109/TETC.2016.2577538 ↗
19. Real-Time Traffic Sign Recognition Based on Efficient CNNs in the Wild10.1109/TITS.2018.2843815 ↗
20. Squeeze and Excitation Rank Faster R-CNN for Ship Detection in SAR Images10.1109/LGRS.2018.2882551 ↗
21. Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks10.1109/TPAMI.2016.2577031 ↗
22. Selective search for object recognition10.1007/s11263-013-0620-5 ↗
23. Huang, G., Liu, Z., Van Der Maaten, L., and Weinberger, K.Q. (2017, January 21–26). Densely Connected Convolutional Networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.10.1109/CVPR.2017.243 ↗
24. Wang, R.J., Li, X., and Ling, C.X. (2019). Pelee: A Real-Time Object Detection System on Mobile Devices. arXiv.
25. Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.Y., and Alexander, C.B. (2016). SSD: Single Shot MultiBoxDetector. arXiv.10.1007/978-3-319-46448-0_2 ↗
26. Fast multi-feature pedestrian detection algorithm based on histogram of oriented gradient using discrete wavelet transform10.1007/s11042-015-2455-2 ↗
27. Liu, S., Huang, D., and Wang, Y. (2018). Receptive Field Block Net for Accurate and Fast Object Detection. arXiv.10.1007/978-3-030-01252-6_24 ↗
28. Tychsen-Smith, L., and Petersson, L. (2017, January 22–29). DeNet: Scalable Real-Time Object Detection with Directed Sparse Sampling. Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy.10.1109/ICCV.2017.54 ↗
29. Broken Corn Detection Based on an Adjusted YOLO with Focal Loss10.1109/ACCESS.2019.2916842 ↗
30. Ren, P., Fang, W., and Djahel, S. (2017, January 14–17). A novel YOLO-Based real-time people counting approach. Proceedings of the 2017 International Smart Cities Conference (ISC2), Wuxi, China.10.1109/ISC2.2017.8090864 ↗
31. Redmon, J., Divvala, S., Girshick, R., and Farhadi, A. (2016, January 27–30). You Only Look Once: Unified, Real-Time Object Detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.10.1109/CVPR.2016.91 ↗
32. Rezatofighi, H., Tsoi, N., Gwak, J.Y., Sadeghian, A., Reid, I., and Savarese, S. (2019). Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regression. arXiv.10.1109/CVPR.2019.00075 ↗
33. Redmon, J., and Farhadi, A. (2017, January 21–26). YOLO9000: Better, Faster, Stronger. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.10.1109/CVPR.2017.690 ↗
34. He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27–30). Deep Residual Learning for Image Recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.10.1109/CVPR.2016.90 ↗
35. Label Distribution-Based Facial Attractiveness Computation by Deep Residual Learning10.1109/TMM.2017.2780762 ↗
36. Lin, T., Goyal, P., Girshick, R., He, K., and Dollár, P. (2017, January 22–29). Focal Loss for Dense Object Detection. Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy.10.1109/ICCV.2017.324 ↗
37. He, K., Gkioxari, G., Dollár, P., and Girshick, R. (2017, January 22–29). Mask R-CNN. Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy.10.1109/ICCV.2017.322 ↗
38. Wen, L.Y., Du, D.W., Cai, Z.W., Lei, Z., Chang, M.C., Qi, H.G., Lim, I.W., Yang, M.H., and Lyu, S.W. (2015). UA-DETRAC: A New Benchmark and Protocol for Multi-Object Detection and Tracking. arXiv.