• ISSN 0258-2724
  • CN 51-1277/U
  • EI Compendex
  • Scopus
  • Indexed by Core Journals of China, Chinese S&T Journal Citation Reports
  • Chinese S&T Journal Citation Reports
  • Chinese Science Citation Database
GAN Jiahua, MAO Xinhua, ZHAO Jing. Optimal Evacuation Model of Parking Vehicles in Dynamic Traffic Flows[J]. Journal of Southwest Jiaotong University, 2021, 56(1): 123-130. doi: 10.3969/j.issn.0258-2724.20190611
Citation: PENG Bo, TANG Ju, ZHANG Yuanyuan, CAI Xiaoyu, MENG Fanhe. Automatic Traffic State Recognition from Road Videos Based on 3D Convolution Neural Network[J]. Journal of Southwest Jiaotong University, 2021, 56(1): 153-159. doi: 10.3969/j.issn.0258-2724.20191169

Automatic Traffic State Recognition from Road Videos Based on 3D Convolution Neural Network

doi: 10.3969/j.issn.0258-2724.20191169
  • Received Date: 09 Dec 2019
  • Rev Recd Date: 16 Mar 2020
  • Available Online: 01 Apr 2020
  • Publish Date: 01 Feb 2021
  • In order to directlyextract effective traffic information from videos, a traffic state recognition method based on 3D CNN (3D convolutional neural networks)was put forward. Firstly, with the deep convolutional network C3D (convolutional 3D) as 3D CNN prototype, the number and position of convolutional layers, convolutional kernelsize and 3D convolutional depth were optimized and adjusted; thus 37 candidate models were built. Secondly, video datasets were established to systematically train and test candidate models, and a traffic state recognition model C3D* was proposed. Then, tests and analysis were conducted on traffic state recognition results of C3D* and existing 3D convolutional models. At last, traffic recognition results were compared between C3D* and commonly used 2D convolutional networks. The results show that for video traffic state recognition, the average F value of C3D* reaches 91.32%, which is 12.24%, 26.72% and 28.02% higher than that of C3D, R3D (region convolutional 3D network) and R(2+1)D (resnets adopting 2D spatial convolution and a 1D temporal convolution), respectively, demonstrating that the proposed model C3D* is more accurate and effective. Compared with image recognition results from LeNet, AlexNet, GoogleNet and VGG16, the average C3D* is 32.61%, 69.91%, 50.11% and 69.17% higher respectively, proving that 3D video convolution F value of outperforms 2D image convolution in terms of traffic status recognition.

     

  • WEI L, HONG Y D. Real-time road congestion detection based on image texture analysis[J]. Procedia Engineering, 2016, 137: 196-201. doi: 10.1016/j.proeng.2016.01.250
    SHI X, SHAN Z, ZHAO N. Learning for an aesthetic model for estimating the traffic state in the traffic video[J]. Neurocomputing, 2016, 181: 29-37. doi: 10.1016/j.neucom.2015.08.099
    崔华,袁超,魏泽发,等. 利用FCM对静态图像进行交通状态识别[J]. 西安电子科技大学学报,2017,44(6): 85-90.

    CUI Hua, YUAN Chao, WEI Zefa, et al. Traffic state recognition using state images and FCM[J]. Journal of Xidian University, 2017, 44(6): 85-90.
    LECUN Y, BOTTOU L, BENGIO Y, et al. Gradient-based learning applied to document recognition[J]. Proceedings of the IEEE, 1998, 86(11): 2278-2324. doi: 10.1109/5.726791
    Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition[C]//3rd International Conference on Learning Representations. San Diego: [s.n.], 2015: 1-14.
    JI S, XU W, YANG M, et al. 3D Convolutional neural networks for human action recognition[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013, 35(1): 221-231. doi: 10.1109/TPAMI.2012.59
    TRAN D, BOURDEV L, FERGUS R, et al. Learning spatiotemporal features with 3D convolutional networks[C]//IEEE International Conference on Computer Vision. Santiago: IEEE, 2015: 4489-4497.
    XU H, DAS A, SAENKO K. R-C3D: region convolutional 3D network for temporal activity detection[C]//IEEE International Conference on Computer Vision. Venice: IEEE, 2017: 5794-5803.
    TRAN D, WANG H, TORRESANI L, et al. A closer look at spatiotemporal convolutions for action recognition[C]//IEEE Conference on Computer Vision and Pattern Recognition. Salt Lake City: IEEE, 2018: 6450-6459.
  • Relative Articles

    [1]HU Lu, LIANG Zhimei, JIANG Yangsheng. Simulation Analysis on Influence of Congestion Propagation on Operation of Carsharing Systems[J]. Journal of Southwest Jiaotong University, 2023, 58(3): 499-510. doi: 10.3969/j.issn.0258-2724.20220231
    [2]JING Chunhui, ZHI Jinyi. Influence of Sharing Tasks on Automobile Driving Safety and Software Interactive Usability[J]. Journal of Southwest Jiaotong University, 2021, 56(2): 437-443. doi: 10.3969/j.issn.0258-2724.20200002
    [3]ZHU Xinping, HAN Songchen. Centralized Scheduling of Service Vehicles for Aircraft Turnaround Based on Partheno-Genetic Algorithm[J]. Journal of Southwest Jiaotong University, 2018, 53(2): 406-413. doi: 10.3969/j.issn.0258-2724.2018.02.026
    [4]GUOPeng, CHENG Wenming, ZHANGZeqiang. Improved Genetic Algorithm for Single Machine Scheduling Problems with Deteriorating Jobs[J]. Journal of Southwest Jiaotong University, 2011, 24(3): 506-511. doi: 3969/j.issn.0258-2724.2011.03.025
    [5]LIU Wei-Hua. Determination Method of the Optimal Revenue-Sharing Coefficient in Three-Echelon Logistics Service Supply Chain[J]. Journal of Southwest Jiaotong University, 2010, 23(5): 811-816. doi: 10. 3969/ j. issn. 0258-2724.
    [6]HU Feng, 2, WANG Guoyin, DAI Jin. Quick Discretization Algorithm for Rough Set Based on Dynamic Clustering[J]. Journal of Southwest Jiaotong University, 2010, 23(6): 977-983. doi: 10.3969/j.issn.0258-2724.201
    [7]ZHAO Dan, ZHANG Jiatai, SHU Haisheng, ZHAO Gang. Double Layer Genetic Algorithm for Integrated Scheduling Optimization of Part and Tool Flows[J]. Journal of Southwest Jiaotong University, 2010, 23(6): 926-931. doi: 10.3969/j.issn.0258-2724.2010.06.018
    [8]LIN Chuan, FENG Quanyuan. Information Sharing Strategies for Particle Swarm Optimization Algorithm[J]. Journal of Southwest Jiaotong University, 2009, 22(3): 437-441.
    [9]MA Yongjie, JIANG Zhaoyuan, YANG Zhimin. Dynamic Location Assignment of AS/RS Based on Genetic Algorithm[J]. Journal of Southwest Jiaotong University, 2008, 21(3): 415-421.
    [10]DAI Chaohua, ZHU Yunfang, CHEN Weirong. Cloud Theory-Based Genetic Algorithm[J]. Journal of Southwest Jiaotong University, 2006, 19(6): 729-732.
    [11]YANG Qing-ding, HUANG Pei-qing. Multi-stage OptimalOrdering Strategy for theM anufacturer under Uncertain Prices[J]. Journal of Southwest Jiaotong University, 2005, 18(5): 700-704.
    [12]JIXiao-li. Order AllocationM odel in Supply Chain and Hybrid Genetic Algorithm[J]. Journal of Southwest Jiaotong University, 2005, 18(6): 811-815.
    [13]GUAN Zhen-zhong, HUANG Shen-ze, SHIBen-shan. Dynam ic Pricing Policy of the SeasonalProducts Based on RevenueM anagement[J]. Journal of Southwest Jiaotong University, 2005, 18(5): 696-699.
    [14]QIUXiao-ping, TANG Yong-chuan, MENG Dan, XU Yang. Multivalue Coded Genetic Algorithm[J]. Journal of Southwest Jiaotong University, 2003, 16(2): 227-130.
    [15]ZHANG Si-cai, ZHANG Fang-xiao. Application of Genetic Algorithms in Structural Optimization Design with Discrete Variables[J]. Journal of Southwest Jiaotong University, 2003, 16(2): 146-150.
    [16]YANGwei, HEYi一gong, DuWEN. ComPuterAidedCyclingArrangementofPostalTruckS[J]. Journal of Southwest Jiaotong University, 2001, 14(4): 407-411.
    [17]YEHUAI-zhen, ZHOUXIAN-wei, CHENCHANG-he. AnAssignmentModelofDynamieTransPortation NetworkFlowsforSystemOPtimization[J]. Journal of Southwest Jiaotong University, 2001, 14(4): 396-400.
    [18]HUChang-liu. AMultiscale EstimationMethod of Signal Based onMultiple Threshold Processing[J]. Journal of Southwest Jiaotong University, 2001, 14(1): 80-83.
    [19]DU Wen, LIN Shu-rong, ZΗΟUXian-wei. Batch Parallel Algorithm of Assignment Problem of Dynamic Transportation Network Flows for System Optimization[J]. Journal of Southwest Jiaotong University, 2001, 14(5): 453-456.
    [20]CHEN Yan-ru, PUYun. Solving Traffic Equilibrium Assignment Problem with Genetic Algorithm[J]. Journal of Southwest Jiaotong University, 2000, 13(1): 44-47.
  • Cited by

    Periodical cited type(2)

    1. 韦杨兴. 预应力孔道压浆料试验检测分析. 中国建筑金属结构. 2024(09): 97-99 .
    2. 陈雁群. 铜尾渣对预应力孔道压浆料性能的影响研究. 江西建材. 2023(11): 47-48+51 .

    Other cited types(0)

  • Created with Highcharts 5.0.7Amount of accessChart context menuAbstract Views, HTML Views, PDF Downloads StatisticsAbstract ViewsHTML ViewsPDF Downloads2024-052024-062024-072024-082024-092024-102024-112024-122025-012025-022025-032025-0401020304050
    Created with Highcharts 5.0.7Chart context menuAccess Class DistributionFULLTEXT: 22.6 %FULLTEXT: 22.6 %META: 70.5 %META: 70.5 %PDF: 6.8 %PDF: 6.8 %FULLTEXTMETAPDF
    Created with Highcharts 5.0.7Chart context menuAccess Area Distribution其他: 15.4 %其他: 15.4 %其他: 0.2 %其他: 0.2 %上海: 0.4 %上海: 0.4 %东莞: 0.2 %东莞: 0.2 %临汾: 0.4 %临汾: 0.4 %伦敦: 0.2 %伦敦: 0.2 %佛山: 0.5 %佛山: 0.5 %保定: 0.1 %保定: 0.1 %兰州: 0.3 %兰州: 0.3 %北京: 10.0 %北京: 10.0 %十堰: 0.5 %十堰: 0.5 %南京: 1.6 %南京: 1.6 %南充: 0.1 %南充: 0.1 %南宁: 0.1 %南宁: 0.1 %南昌: 0.1 %南昌: 0.1 %南通: 0.4 %南通: 0.4 %卡尔斯鲁厄: 0.4 %卡尔斯鲁厄: 0.4 %台州: 0.2 %台州: 0.2 %合肥: 0.3 %合肥: 0.3 %咸宁: 0.1 %咸宁: 0.1 %哈尔滨: 0.1 %哈尔滨: 0.1 %哥伦布: 0.3 %哥伦布: 0.3 %嘉兴: 0.3 %嘉兴: 0.3 %天津: 1.6 %天津: 1.6 %安庆: 0.1 %安庆: 0.1 %宣城: 0.4 %宣城: 0.4 %帕尔马: 0.3 %帕尔马: 0.3 %常州: 0.3 %常州: 0.3 %广州: 1.9 %广州: 1.9 %张家口: 1.5 %张家口: 1.5 %德里: 0.2 %德里: 0.2 %惠州: 0.2 %惠州: 0.2 %成都: 2.8 %成都: 2.8 %扬州: 0.9 %扬州: 0.9 %昆明: 0.7 %昆明: 0.7 %朝阳: 0.4 %朝阳: 0.4 %来宾: 0.2 %来宾: 0.2 %杭州: 0.1 %杭州: 0.1 %株洲: 0.1 %株洲: 0.1 %格兰特县: 0.1 %格兰特县: 0.1 %桂林: 0.1 %桂林: 0.1 %榆林: 0.1 %榆林: 0.1 %武汉: 0.1 %武汉: 0.1 %池州: 0.2 %池州: 0.2 %沈阳: 0.2 %沈阳: 0.2 %洛阳: 0.3 %洛阳: 0.3 %淄博: 0.1 %淄博: 0.1 %深圳: 0.3 %深圳: 0.3 %清远: 0.1 %清远: 0.1 %温州: 0.4 %温州: 0.4 %湖州: 0.1 %湖州: 0.1 %湛江: 0.1 %湛江: 0.1 %漯河: 3.6 %漯河: 3.6 %潍坊: 0.1 %潍坊: 0.1 %烟台: 0.1 %烟台: 0.1 %玉溪: 0.2 %玉溪: 0.2 %珠海: 0.2 %珠海: 0.2 %石家庄: 0.6 %石家庄: 0.6 %绵阳: 0.1 %绵阳: 0.1 %芒廷维尤: 17.9 %芒廷维尤: 17.9 %芜湖: 0.2 %芜湖: 0.2 %芝加哥: 0.6 %芝加哥: 0.6 %衡水: 0.1 %衡水: 0.1 %襄阳: 0.1 %襄阳: 0.1 %西宁: 20.9 %西宁: 20.9 %西安: 0.3 %西安: 0.3 %许昌: 0.1 %许昌: 0.1 %诺沃克: 0.3 %诺沃克: 0.3 %贵阳: 0.7 %贵阳: 0.7 %运城: 0.7 %运城: 0.7 %邯郸: 0.2 %邯郸: 0.2 %郑州: 0.8 %郑州: 0.8 %重庆: 1.0 %重庆: 1.0 %金华: 0.1 %金华: 0.1 %银川: 0.1 %银川: 0.1 %长春: 0.1 %长春: 0.1 %长沙: 4.1 %长沙: 4.1 %阜新: 0.5 %阜新: 0.5 %陇南: 0.1 %陇南: 0.1 %青岛: 0.8 %青岛: 0.8 %其他其他上海东莞临汾伦敦佛山保定兰州北京十堰南京南充南宁南昌南通卡尔斯鲁厄台州合肥咸宁哈尔滨哥伦布嘉兴天津安庆宣城帕尔马常州广州张家口德里惠州成都扬州昆明朝阳来宾杭州株洲格兰特县桂林榆林武汉池州沈阳洛阳淄博深圳清远温州湖州湛江漯河潍坊烟台玉溪珠海石家庄绵阳芒廷维尤芜湖芝加哥衡水襄阳西宁西安许昌诺沃克贵阳运城邯郸郑州重庆金华银川长春长沙阜新陇南青岛

Catalog

    通讯作者: 陈斌, bchen63@163.com
    • 1. 

      沈阳化工大学材料科学与工程学院 沈阳 110142

    1. 本站搜索
    2. 百度学术搜索
    3. 万方数据库搜索
    4. CNKI搜索

    Figures(6)  / Tables(5)

    Article views(613) PDF downloads(55) Cited by(2)
    Proportional views
    Related

    /

    DownLoad:  Full-Size Img  PowerPoint
    Return
    Return