Video processing techniques for traffic flow monitoring: A survey
The DOI matches its Crossref record; 55 of the 55 references it cites were found in a registry or an index.
Abstract
Video-based traffic flow monitoring is a fast emerging field based on the continuous development of computer vision. A survey of the state-of-the-art video processing techniques in traffic flow monitoring is presented in this paper. Firstly, vehicle detection is the first step of video processing and detection methods are classified into background modeling based methods and non-background modeling based methods. In particular, nighttime detection is more challenging due to bad illumination and sensitivity to light. Then tracking techniques, including 3D model-based, region-based, active contour-based and feature-based tracking, are presented. A variety of algorithms including MeanShift algorithm, Kalman Filter and Particle Filter are applied in tracking process. In addition, shadow detection and vehicles occlusion bring much trouble into vehicle detection, tracking and so on. Based on the aforementioned video processing techniques, discussion on behavior understanding including traffic incident detection is carried out. Finally, key challenges in traffic flow monitoring are discussed.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Citations
Cites
Kass, M., Witkin, A., & Terzopoulos, D. (1988) · International Journal of Computer Vision · doi:10.1007/bf00133570 · Cited by 17,070
Robust Real-Time Face Detection
Viola, P., & Jones, M. J. (2004) · International Journal of Computer Vision · doi:10.1023/b:visi.0000013087.49260.fb · Cited by 14,097
Adaptive background mixture models for real-time tracking
Stauffer, C., & Grimson, W. E. L. (2003) · Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149) · doi:10.1109/cvpr.1999.784637 · Cited by 6,923
Comaniciu, D., Ramesh, V., & Meer, P. (2003) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2003.1195991 · Cited by 4,560 · cited 1×
“appearance-based tracking method and performs well in tracking moving objects even in dense traffic [35][57].”
MethodBackground subtraction techniques: a review
Piccardi, M. (2005) · 2004 IEEE International Conference on Systems, Man and Cybernetics (IEEE Cat. No.04CH37583) · doi:10.1109/icsmc.2004.1400815 · Cited by 2,083
Real-time foreground–background segmentation using codebook model
Kim, K., Chalidabhongse, T. H., Harwood, D., & Davis, L. (2005) · Real-Time Imaging · doi:10.1016/j.rti.2004.12.004 · Cited by 1,422
Moving target classification and tracking from real-time video
Lipton, A. J., Fujiyoshi, H., & Patil, R. S. (2002) · Proceedings Fourth IEEE Workshop on Applications of Computer Vision. WACV'98 (Cat. No.98EX201) · doi:10.1109/acv.1998.732851 · Cited by 1,108 · cited 1×
“[54] extracted moving objects using two frame differencing method.”
MethodA Statistical Approach for Real-time Robust Background Subtraction and Shadow Detection
Horprasert, T. (1999) · IEEE/CVF International Conference on Computer Vision (ICCV) · Cited by 944
A Review of Computer Vision Techniques for the Analysis of Urban Traffic
Buch, N., Velastin, S. A., & Orwell, J. (2011) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2011.2119372 · Cited by 653 · cited 3×
“Vehicle tracking is to get trajectories of moving vehicles, enabling higher level tasks including traffic incident detection and behavior understanding [3][32].”
BackgroundTraffic monitoring and accident detection at intersections
Kamijo, S., Matsushita, Y., Ikeuchi, K., & Sakauchi, M. (2000) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/6979.880968 · Cited by 536
A real-time computer vision system for measuring traffic parameters
Beymer, D., McLauchlan, P., Coifman, B., & Malik, J. (2002) · Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.1997.609371 · Cited by 493 · cited 2×
“Corners and edges are usually used to represent objects in an image [37][38].”
BackgroundImproving shadow suppression in moving object detection with HSV color information
Cucchiara, R., Crana, C., Piccardi, M., Prati, A., & Sirotti, S. (2002) · ITSC 2001. 2001 IEEE Intelligent Transportation Systems. Proceedings (Cat. No.01TH8585) · doi:10.1109/itsc.2001.948679 · Cited by 436 · cited 1×
“Color space of shadow are within a certain range [18][23][24].”
BackgroundEvent detection and analysis from video streams
Medioni, G., Cohen, I., Bremond, F., Hongeng, S., & Nevatia, R. (2001) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/34.946990 · Cited by 405 · cited 2×
“[52] interpreted behaviors of mobile objects at checkpoint using object trajectories and contextual information.”
BackgroundImage analysis and rule-based reasoning for a traffic monitoring system
Cucchiara, R., Piccardi, M., & Mello, P. (2000) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/6979.880969 · Cited by 398
Tracking and Object Classification for Automated Surveillance
Javed, O., & Shah, M. (2002) · Lecture Notes in Computer Science · doi:10.1007/3-540-47979-1_23 · Cited by 337
Vehicle detection video through image processing: the Autoscope system
Michalopoulos, P. G. (1991) · IEEE Transactions on Vehicular Technology · doi:10.1109/25.69968 · Cited by 275 · cited 1×
“Some commercial companies, Autoscope (in America) [4][5], Traficon (in Italy) [6] and Citilog (in France) [7] collect parameters such as vehicle volume, average speed, queue length and so on.”
BackgroundFramework for Real-Time Behavior Interpretation From Traffic Video
Kumar, P., Ranganath, S., Weimin, H., & Sengupta, K. (2005) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2004.838219 · Cited by 168 · cited 3×
“[9] implemented real-time behavior interpretation at checkpost.”
BackgroundA shadow handler in a video-based real-time traffic monitoring system
Kilger, M. (2003) · [1992] Proceedings IEEE Workshop on Applications of Computer Vision · doi:10.1109/acv.1992.240332 · Cited by 156 · cited 3×
“(2) Vehicle’s shape and trajectory are inaccurate and tracking and recognition systems are confused [20][21].”
BackgroundA Vision-Based Approach to Collision Prediction at Traffic Intersections
Atev, S., Arumugam, H., Masoud, O., Janardan, R., & Papanikolopoulos, N. P. (2005) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2005.858786 · Cited by 144 · cited 2×
“[51][58] descript collision detection problem as follow: “Given the position, orientation, and size, at each time step, of n oriented rectangles in 2-D, find all possible pairs of rectangles that intersect in the current and future time steps.”
BackgroundShadow detection and removal for traffic images
Wang, J. M., Chung, Y.-C., Chang, C., & Chen, S. W. (2004) · IEEE International Conference on Networking, Sensing and Control (ICNSC) · doi:10.1109/icnsc.2004.1297516 · Cited by 109 · cited 1×
“[17] detected shadow based on shadow characters such as lower lightness and the lack of textures and edges.”
BackgroundVideo-based traffic monitoring
Kilger, M. (1992) · Cited by 99
Robert, K. (2009) · 2009 Sixth IEEE International Conference on Advanced Video and Signal Based Surveillance · doi:10.1109/avss.2009.98 · Cited by 89 · cited 4×
“In the first layer, headlights were detected using the same methods as [27].”
BackgroundMethodInfluentialVideo-based traffic monitoring at day and night vehicle features detection tracking
Robert, K. (2009) · 2009 12th International IEEE Conference on Intelligent Transportation Systems · doi:10.1109/itsc.2009.5309837 · Cited by 89 · cited 3×
“Vehicles headlights, taillights and dark windshields are chosen to be the most significant features to present vehicles [1][27][28][29].”
BackgroundA fast and accurate scoreboard algorithm for estimating stationary backgrounds in an image sequence
Lai, A. H. S., & Yung, N. H. C. (2002) · IEEE International Symposium on Circuits and Systems proceedings · doi:10.1109/iscas.1998.698804 · Cited by 85 · cited 1×
“In the simplest case, a period of image sequences are averaged to obtain a background model [12].”
BackgroundChen, S., Shyu, M., Peeta, S., & Zhang, C. (2003) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2003.821290 · Cited by 69 · cited 1×
“As improved, [42] considered the cases where a large object overlaps with a small one.”
BackgroundA Color Similarity Measure for Robust Shadow Removal in Real-Time
Grest, D., Frahm, J., & Koch, R. (2003) · Vision Modeling and Visualization · Cited by 62
A Survey of Visual Analysis of Human Motion
Liang, W. (2002) · Chinese Journal of Computers · Cited by 60
Distributed video networks for incident detection and management
Trivedi, M. M., Mikic, I., & Kogut, G. T. (2002) · IEEE International Conference on Intelligent Transportation Systems (ITSC) · doi:10.1109/itsc.2000.881042 · Cited by 54 · cited 1×
“In the 1990s, some research on traffic flow monitoring systems gave high-level description of both cars and their behaviors such as lane changing and braking [43].”
BackgroundImage-based vehicle tracking and classification on the highway
Lai, J.-C., Huang, S.-S., & Tseng, C. (2010) · International Conference on Green Circuits and Systems · doi:10.1109/icgcs.2010.5542980 · Cited by 46 · cited 2×
“based tracking processes were implemented in [13][33].”
MethodIDENTIFYING OVERLAPPED OBJECTS FOR VIDEO INDEXING AND MODELING IN MULTIMEDIA DATABASE SYSTEMS
Chen, S., Shyu, M., Zhang, C., & Kashyap, R. L. (2001) · International Journal of Artificial Intelligence Tools · doi:10.1142/s0218213001000738 · Cited by 46 · cited 1×
“[60] handled the case of two objects overlapping.”
BackgroundTakeuchi, A., Mita, S., & McAllester, D. (2010) · IEEE Intelligent Vehicles Symposium · doi:10.1109/ivs.2010.5548067 · Cited by 44 · cited 1×
“In [53], deformable object model which was composed of a root filter and six part filters was used to”
MethodReal-time vision-based multiple vehicle detection and tracking for nighttime traffic surveillance
Chen, Y.-L., Wu, B.-F., & Fan, C.-J. (2009) · 2009 IEEE International Conference on Systems, Man and Cybernetics · doi:10.1109/icsmc.2009.5346191 · Cited by 41 · cited 1×
“Vehicles headlights, taillights and dark windshields are chosen to be the most significant features to present vehicles [1][27][28][29].”
BackgroundTraffic accident prediction using vehicle tracking and trajectory analysis
Hu, W., Xiao, X., Xie, D., & Tan, T. (2004) · IEEE International Conference on Intelligent Transportation Systems (ITSC) · doi:10.1109/itsc.2003.1251952 · Cited by 36 · cited 1×
“[50] proposed a method of predicting traffic accidents.”
MethodVehicle Tracking by non-Drifting Mean-shift using Projective Kalman Filter
Bouttefroy, P. L. M., Bouzerdoum, A., Phung, S. L., & Beghdadi, A. (2008) · IEEE International Conference on Intelligent Transportation Systems (ITSC) · doi:10.1109/itsc.2008.4732659 · Cited by 34 · cited 5×
“With these attributes, tracking process can be performed using tracking algorithms including Meanshift [41] algorithms, Kalman Filter, projective Kalman Filter [41], Particle Filter.”
MethodInfluentialVehicle Tracking Using Projective Particle Filter
Bouttefroy, P. L. M., Bouzerdoum, A., Phung, S. L., & Beghdadi, A. (2009) · IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS) · doi:10.1109/avss.2009.60 · Cited by 30 · cited 2×
“Various filtering algorithms are used, such as Bayesian Filter, Kalman Filter and Particle Filter [25][32].”
BackgroundMethodAn adaptive, real-time, traffic monitoring system
Rodríguez, T., & Garcia, N. N. (2009) · Machine Vision and Applications · doi:10.1007/s00138-009-0185-z · Cited by 29 · cited 1×
“Video sensors can produce richer information without affecting the integrity of the road and with the possibility to transmit traffic images to Transportation Management Centre (TMC) [2].”
BackgroundLin, S.-P., Chen, Y.-H., & Bing-Fei, W. (2006) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr.2006.159 · Cited by 28 · cited 2×
“[14] resolved occluding problem with occlusion detection and queue detection.”
BackgroundVideo-based traffic accident analysis at intersections using partial vehicle trajectories
Aköz, Ö., & Karsligil, M. E. (2010) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2010.5653839 · Cited by 27 · cited 1×
“They matched new partial observation with normal vehicle behaviors to detect accidents, described in detail in [49].”
BackgroundSurveillance system based on spatio-temporal information
Nagai, A., Kuno, Y., & Shirai, Y. (2002) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.1996.560931 · Cited by 26 · cited 1×
“[56] developed a smart video-based surveillance system which was robust to light variation and moving background.”
BackgroundA Two-Layer Night-Time Vehicle Detector
Wang, W., Shen, C., Zhang, J., & Paisitkriangkrai, S. (2009) · International Conference on Digital Image Computing: Techniques and Applications (DICTA) · doi:10.1109/dicta.2009.33 · Cited by 26 · cited 2×
“Inspired by [27], [29] proposed a two-layer nighttime detection method.”
BackgroundMethodAköz, Ö., & Karsligil, M. E. (2010) · IEEE International Conference on Intelligent Transportation Systems (ITSC) · doi:10.1109/itsc.2010.5624990 · Cited by 23 · cited 1×
“[48] detected severity of traffic accidents at intersections.”
BackgroundMultimodal highway monitoring for robust incident detection
Pucher, M., Schabus, D., Schallauer, P., Lypetskyy, Y., Graf, F., Rainer, H., Stadtschnitzer, M., Sternig, S., Birchbauer, J., Schneider, W., et al. (2010) · IEEE International Conference on Intelligent Transportation Systems (ITSC) · doi:10.1109/itsc.2010.5625035 · Cited by 22 · cited 1×
“[47] used both video and audio sensors to detect incidents such as wrong-way drivers, still standing vehicles and traffic”
MethodRobust vehicle tracking based on Scale Invariant Feature Transform
Tu, Q., Xu, Y., & Zhou, M. (2008) · IEEE International Conference on Information and Automation (ICIA) · doi:10.1109/icinfa.2008.4607973 · Cited by 20 · cited 1×
“[39] combined region-based tracking with Scale Invariant Feature Transform (SIFT) features based tracking.”
MethodA survey of vision-based automatic incident detection technology
Wang, K.-F., Jia, X., & Tang, S. (2006) · IEEE International Conference on Vehicular Electronics and Safety (ICVES) · doi:10.1109/icves.2005.1563659 · Cited by 19 · cited 4×
“In previous subsection, tracking methods are classified into four categories based on vehicles’ attributes [34].”
BackgroundMethodInfluentialSelf-citationVideo-based traffic accident analysis at intersections using partial vehicle trajectories
Aköz, Ö., & Karsligil, M. E. (2010) · Signal Processing and Communications Applications Conference (SIU) · doi:10.1109/siu.2010.5651544 · Cited by 18
A collision prediction system for traffic intersections
Atev, S., Masoud, O., Janardan, R., & Papanikolopoulos, N. (2005) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2005.1545407 · Cited by 18 · cited 1×
“[51][58] descript collision detection problem as follow: “Given the position, orientation, and size, at each time step, of n oriented rectangles in 2-D, find all possible pairs of rectangles that intersect in the current and future time steps.”
BackgroundNight-time vehicle classification with an embedded, vision system
Gritsch, G., Donath, N., Kohn, B., & Litzenberger, M. (2009) · IEEE International Conference on Intelligent Transportation Systems (ITSC) · doi:10.1109/itsc.2009.5309875 · Cited by 17 · cited 1×
“[31] constructed a night-time classification system-smart eye TDS.”
BackgroundTraffic incident classification at intersections based on image sequences by HMM/SVM classifiers
Zou, Y., Shi, G., Shi, H., & Zhao, H. (2010) · Multimedia Tools and Applications · doi:10.1007/s11042-010-0466-6 · Cited by 16
An Accurate Shadow Removal Method for Vehicle Tracking
Zhou, Z., & Lu, X. (2010) · doi:10.1109/aici.2010.135 · Cited by 15 · cited 2×
“Color space of shadow are within a certain range [18][23][24].”
BackgroundMethodA shadow removal algorithm for vehicle detection based on reflectance ratio and edge density
Vargas, M., Toral, S. L., Milla, J. M., & Barrero, F. (2010) · IEEE International Conference on Intelligent Transportation Systems (ITSC) · doi:10.1109/itsc.2010.5625112 · Cited by 15 · cited 2×
“[22] detected vehicle’s shadow using the rule that a shadow does not affect the texture of the surface”
BackgroundMethodBragatto, T. A. C., Ruas, G. I. S., Benso, V. A. P., Lamar, M. V., Aldigueri, D. R., Teixeira, G. L., & Yamashita, Y. (2008) · IEEE Intelligent Vehicles Symposium · doi:10.1109/ivs.2008.4621293 · Cited by 13 · cited 1×
“Corners and edges are usually used to represent objects in an image [37][38].”
BackgroundVideo-based traffic accident analysis at intersection using partial vehicle trajectories
Aköz, Ö., & Karsligil, M. E. (2010) · doi:10.1145/1816041.1816090 · Cited by 12
Texture Analysis for Shadow Removing and Tracking of Vehicle in Traffic Monitoring System
Luo, D., & Huang, X. (2008) · Intelligent Information Technology Application · doi:10.1109/iita.workshops.2008.169 · Cited by 7 · cited 3×
“Various filtering algorithms are used, such as Bayesian Filter, Kalman Filter and Particle Filter [25][32].”
MethodA Detection and Tracing Algorithm of Moving Vehicles
Yang, Y., Yang, C., & Wang, X. (2007) · International Conference on Pervasive Computing and Applications (ICPCA) · doi:10.1109/icpca.2007.4365485 · Cited by 4 · cited 1×
“based tracking processes were implemented in [13][33].”
Method of removing moving shadow based on texture
Zhong, Q., & Junping, Z. (2008) · Chinese Control and Decision Conference (CCDC) · doi:10.1109/ccdc.2008.4597724 · Cited by 3 · cited 1×
“(2) Vehicle’s shape and trajectory are inaccurate and tracking and recognition systems are confused [20][21].”
Background
Research works printed but not linked: 3
- shen, 2008, The Research and Applications of Visual Tracking Based on Mean Shift
- ridder, 1995, Adaptive Background Estimation and Foreground Detection using Kalman-Filtering, Proc ICRA, 193
- huang, 2009, Automatic Detection of Vehicle Activities Based on Particle Filter Tracking, Proc IISCS, 381
Cited by
NoScope: optimizing neural network queries over video at scale
Kang, D., Emmons, J., Abuzaid, F., Bailis, P., & Zaharia, M. (2017) · Proceedings of the VLDB Endowment · doi:10.14778/3137628.3137664 · Cited by 367
“Video monitoring captures a variety of tasks [52], ranging from object detection [53] to vehicle tracking [87].”
BackgroundIntelligent Traffic Monitoring Systems for Vehicle Classification: A Survey
Won, M. (2020) · IEEE Access · doi:10.1109/access.2020.2987634 · Cited by 225
“Interestingly, we find that most survey works are focused on vision-based vehicle classification techniques [7] [8] [9] [10] [11] [12] overlooking numerous other emerging vehicle classification solutions.”
BackgroundVehicle Tracking and Speed Estimation From Roadside Lidar
Zhang, J., Xiao, W., Coifman, B., & Mills, J. P. (2020) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2020.3024921 · Cited by 182
“Video cameras can produce richer visual information than traditional devices without affecting the integrity of the road surface and the observed information can be processed intuitively with modern computer vision technologies [5].”
BackgroundAnomaly Detection in Road Traffic Using Visual Surveillance: A Survey
Santhosh, K. K., Dogra, D. P., & Roy, P. P. (2021) · ACM Computing Surveys · doi:10.1145/3417989 · Cited by 159
“The study presented in [14] covers vehicle detection, tracking, behavior”
BackgroundMethodHandcrafted and Deep Trackers: Recent Visual Object Tracking Approaches and Trends
Fiaz, M., Mahmood, A., Javed, S., & Jung, S. K. (2019) · ACM Computing Surveys · doi:10.1145/3309665 · Cited by 155
“It attained much reputation because of its widespread use in different applications; for instance, autonomous vehicles [92], traffic flow monitoring [147], surveillance and security [5], human machine interaction [138], medical diagnostic systems [150], and activity recognition [4].”
Background
Metadata
- Authors
- Tian, B., Yao, Q., Gu, Y., Wang, K., & Li, Y.
- Affiliations
- Chinese Academy of Sciences (CN)
- Venue
- 2011 14th International IEEE Conference on Intelligent Transportation Systems (ITSC)
- Publisher
- IEEE
- Published
- 2011-10
- Pages
- 1103-1108
- OpenAlex
- W2027843963
- Cited by
- 106
- References
- 55
- Citations by year
- 2025: 6 · 2024: 9 · 2023: 7 · 2022: 13 · 2021: 12 · 2020: 11 · 2019: 7 · 2018: 7 · 2017: 6 · 2016: 9 · 2015: 8 · 2014: 6 · 2013: 4 · 2012: 1
- FWCI
- 2.63
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- IEEE International Conference on Intelligent Transportation Systems (ITSC) (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Video Surveillance and Tracking Methods
- Physical Sciences › Engineering › Automotive Engineering › Autonomous Vehicle Technology and Safety
- Social Sciences › Transportation › Traffic Prediction and Management Techniques
- Keywords
- traffic flow monitoring, video-based traffic monitoring, vehicle detection, background modeling, nighttime vehicle detection, vehicle tracking, 3D model-based tracking, feature tracking, shadow detection, occlusion handling, traffic incident detection, behavior understanding, mean shift, Kalman filter, particle filter
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.