Video-Based Traffic Flow Analysis for Turning Volume Estimation at Signalized Intersections

Traffic flow analysis in complex areas (e.g., intersections and roundabouts) plays an important part in the development of intelligent transportation systems. Among several methods for analyzing traffic flow, image and video processing has emerged as a potential approach to extract the movements of vehicles in urban areas. In this regard, this study develops a traffic flow analysis method, which focuses on extracting traffic information based on Video Surveillance (CCTV) for turning volume estimation at complex intersections, using advanced computer vision technologies. Specifically, state-of-the-art techniques such as Yolo and DeepSORT for the detection, tracking, and counting of vehicles have enveloped to estimate the road traffic density. Regarding the experiment, we collected data from CCTV in an urban area during one day to evaluate our method. The evaluation shows the proposing results in terms of detecting, tracking and counting vehicles with monocular videos.

[1]  Yi Li,et al.  R-FCN: Object Detection via Region-based Fully Convolutional Networks , 2016, NIPS.

[2]  Fei Liu,et al.  A video-based real-time adaptive vehicle-counting system for urban roads , 2017, PloS one.

[3]  Ross B. Girshick,et al.  Fast R-CNN , 2015, 1504.08083.

[4]  Kaiming He,et al.  Mask R-CNN , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[5]  Yohan Dupuis,et al.  A Survey of Vision-Based Traffic Monitoring of Road Intersections , 2016, IEEE Transactions on Intelligent Transportation Systems.

[6]  Francisco Herrera,et al.  Deep Learning in Video Multi-Object Tracking: A Survey , 2019, Neurocomputing.

[7]  Jenq-Neng Hwang,et al.  Single-Camera and Inter-Camera Vehicle Tracking and 3D Speed Estimation Based on Fusion of Visual and Semantic Features , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[8]  Cheng-Lin Liu,et al.  Decision Controller for Object Tracking With Deep Reinforcement Learning , 2019, IEEE Access.

[9]  Ali Farhadi,et al.  YOLOv3: An Incremental Improvement , 2018, ArXiv.

[10]  Khaled Shaaban,et al.  Estimating Turning Movements at Signalized Intersections Using Artificial Neural Networks , 2019, IEEE Transactions on Intelligent Transportation Systems.

[11]  Yingjie Xia,et al.  Towards improving quality of video-based vehicle counting method for traffic flow estimation , 2016, Signal Process..

[12]  Khac-Hoai Nam Bui,et al.  Implementing A Deep Learning Framework for Short Term Traffic Flow Prediction , 2019, WIMS2019.

[13]  Khac-Hoai Nam Bui,et al.  VDS Data-Based Deep Learning Approach for Traffic Forecasting Using LSTM Network , 2019, EPIA.

[14]  Hao Luo,et al.  Detect or Track: Towards Cost-Effective Video Object Detection/Tracking , 2018, AAAI.

[15]  Shuyuan Yang,et al.  A Survey of Deep Learning-Based Object Detection , 2019, IEEE Access.

[16]  Ali Farhadi,et al.  You Only Look Once: Unified, Real-Time Object Detection , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[17]  Xindong Wu,et al.  Object Detection With Deep Learning: A Review , 2018, IEEE Transactions on Neural Networks and Learning Systems.

[18]  Kaiming He,et al.  Focal Loss for Dense Object Detection , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[19]  Jenq-Neng Hwang,et al.  CityFlow: A City-Scale Benchmark for Multi-Target Multi-Camera Vehicle Tracking and Re-Identification , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[20]  Dietrich Paulus,et al.  Simple online and realtime tracking with a deep association metric , 2017, 2017 IEEE International Conference on Image Processing (ICIP).

[21]  Jason J. Jung,et al.  Computational negotiation-based edge analytics for smart objects , 2019, Inf. Sci..

[22]  Jason J. Jung,et al.  Cooperative game-theoretic approach to traffic flow optimization for multiple intersections , 2017, Comput. Electr. Eng..

[23]  Wei Liu,et al.  SSD: Single Shot MultiBox Detector , 2015, ECCV.