How close are we to solving the problem of automated visual surveillance?: A review of real-world surveillance, scientific progress and evaluative mechanisms
The DOI matches its Crossref record; 63 of the 63 references it cites were found in a registry or an index.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Nonparametric Statistics for the Behavioral Sciences
Guitton, H., & Siegel, S. (1958) · Revue économique · doi:10.2307/3498751 · Cited by 35,245
A New Approach to Linear Filtering and Prediction Problems
Kalman, R. E. (1960) · Journal of Basic Engineering · doi:10.1115/1.3662552 · Cited by 31,751
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 · cited 2×
“Stauffer and Grimson in [21,79] describe a multi-camera system which automatically calibrates to a world-coordinate system and produces ground plane coordinates, and it is this which enables the mapping of what they call obstacles (although in our terminology these are more like occlusions).”
BackgroundMethodLearning patterns of activity using real-time tracking
Stauffer, C., & Grimson, W. E. L. (2000) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/34.868677 · Cited by 3,248 · cited 2×
“This is acknowledged by the authors of [78], who stated they were working on methods of evaluating the unusual event detection aspect of their work.”
BackgroundMethodA Survey on Visual Surveillance of Object Motion and Behaviors
Hu, W., Tan, T., Wang, L., & Maybank, S. (2004) · IEEE Transactions on Systems, Man and Cybernetics, Part C (Applications and Reviews) · doi:10.1109/tsmcc.2004.829274 · Cited by 2,132 · cited 1×
“Due to the recent publication of several review papers on this topic, this section will provide a superficial overview and we direct the reader to the aforementioned Buxton paper [11] for a review of behaviour modelling techniques and [27] for a more surveillance specific overview.”
BackgroundDetecting Pedestrians Using Patterns of Motion and Appearance
Viola, P., Jones, M. J., & Snow, D. (2005) · International Journal of Computer Vision · doi:10.1007/s11263-005-6644-8 · Cited by 2,079
A Bayesian computer vision system for modeling human interactions
Oliver, N. M., Rosario, B., & Pentland, A. P. (2000) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/34.868684 · Cited by 1,578
Walsh, D., & Sudnow, D. (1972) · The British Journal of Sociology · doi:10.2307/588328 · Cited by 1,242
Coupled hidden Markov models for complex action recognition
Brand, M., Oliver, N., & Pentland, A. (2002) · Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.1997.609450 · Cited by 1,052
Detecting pedestrians using patterns of motion and appearance
Viola, Jones, & Snow (2003) · Proceedings Ninth IEEE International Conference on Computer Vision · doi:10.1109/iccv.2003.1238422 · Cited by 1,002
Recognition of visual activities and interactions by stochastic parsing
Ivanov, Y. A., & Bobick, A. F. (2000) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/34.868686 · Cited by 659 · cited 1×
“Ivanov and Bobick in [34] separate the problem”
BackgroundBraMBLe: a Bayesian multiple-blob tracker
Isard, M., & MacCormick, J. (2002) · Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001 · doi:10.1109/iccv.2001.937594 · Cited by 628 · cited 6×
“success, as have Bayesian [33] approaches.”
InfluentialUsing adaptive tracking to classify and monitor activities in a site
Grimson, W. E. L., Stauffer, C., Romano, R., & Lee, L. (2002) · Proceedings. 1998 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No.98CB36231) · doi:10.1109/cvpr.1998.698583 · Cited by 504 · cited 1×
“Stauffer and Grimson in [21,79] describe a multi-camera system which automatically calibrates to a world-coordinate system and produces ground plane coordinates, and it is this which enables the mapping of what they call obstacles (although in our terminology these are more like occlusions).”
BackgroundLearning the distribution of object trajectories for event recognition
Johnson, N., & Hogg, D. (1996) · Image and Vision Computing · doi:10.1016/0262-8856(96)01101-8 · Cited by 499
Detecting unusual activity in video
Zhong, H., Shi, J., & Visontai, M. (2004) · Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004. · doi:10.1109/cvpr.2004.1315249 · Cited by 495
Event 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 1×
“Similarly, Hongeng and others in [25] (expanded upon in [48]) describe a system based upon BNs which can recognise and categorise single agent (single “thread”) events.”
BackgroundComber, P. (2002) · Practical Web Traffic Analysis · doi:10.1007/978-1-4302-5366-2_5 · Cited by 338
A mixed-state condensation tracker with automatic model-switching
Isard, M., & Blake, A. (2002) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.1998.710707 · Cited by 338 · cited 1×
“DENSATION) [32] is used to identify foreground pixels”
MethodA Framework for Recognizing the Simultaneous Aspects of American Sign Language
Vogler, C., & Metaxas, D. (2001) · Computer Vision and Image Understanding · doi:10.1006/cviu.2000.0895 · Cited by 309 · cited 1×
“Parallel HMMs (PaHMMs) havebeenshowntobesuccessfulintherecognitionofrelated behaviours, such as the movement of both hands when using sign language [ 86 ].”
MethodDiscovery and segmentation of activities in video
Brand, M., & Kettnaker, V. (2000) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/34.868685 · Cited by 301 · cited 2×
“Brand and Kettnaker [8] use entropy minimisation to determine the structure of an HMM for the detection of events in video: typically, HMM transition topology is either handcrafted, learned by clustering, or discovered through some form of heuristic search.”
MethodLearning Semantic Scene Models From Observing Activity in Visual Surveillance
Makris, D., & Ellis, T. J. (2005) · IEEE Transactions on Systems Man and Cybernetics Part B (Cybernetics) · doi:10.1109/tsmcb.2005.846652 · Cited by 297 · cited 4×
“The most common technique for modelling entrances and exits is to fit a Gaussian mixture model (GMM) to the start and end points of trajectories using the Expectation Maximisation (EM) algorithm, as in McKenna and Nait-Charif [47], Stauffer [77], Makris and Ellis [43].”
BackgroundMethodInfluentialRecognition of group activities using dynamic probabilistic networks
Gong, S., & Xiang, T. (2003) · Proceedings Ninth IEEE International Conference on Computer Vision · doi:10.1109/iccv.2003.1238423 · Cited by 261 · cited 1×
“Gong and colleagues [18,19,29,68,69] also attempt to automatically summarise or categorise activities within video.”
BackgroundEmerging Topics in Computer Vision
Medioni, G., & Kang, S. B. (2004) · Cited by 241
Detecting irregularities in images and in video
Boiman, O., & Irani, M. (2005) · Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1 · doi:10.1109/iccv.2005.70 · Cited by 237
Norris, C., McCahill, M., & Wood, D. (2002) · Surveillance & Society · doi:10.24908/ss.v2i2/3.3369 · Cited by 210 · cited 1×
“[53] provide an overview of the introduction of CCTV cameras internationally, and show that the UK is a clear leader.”
BackgroundVERL: an ontology framework for representing and annotating video events
Francois, A. R. J., Nevatia, R., Hobbs, J., Bolles, R. C., & Smith, J. R. (2005) · IEEE MultiMedia · doi:10.1109/mmul.2005.87 · Cited by 200
Visual surveillance in a dynamic and uncertain world
Buxton, H., & Gong, S. (1995) · Artificial Intelligence · doi:10.1016/0004-3702(95)00041-0 · Cited by 184 · cited 1×
“Buxton and Gong, in [12] describe a BN-based system for”
BackgroundRecognizing Planned, Multiperson Action
Intille, S. S., & Bobick, A. F. (2001) · Computer Vision and Image Understanding · doi:10.1006/cviu.2000.0896 · Cited by 172 · cited 1×
“A similar approach to event detection is exemplified by Intille and Bobick in [31].”
MethodLearning and understanding dynamic scene activity: a review
Buxton, H. (2003) · Image and Vision Computing · doi:10.1016/s0262-8856(02)00127-0 · Cited by 171 · cited 2×
“Indeed, a recent review [11] describes the field almost entirely in terms of these techniques.”
BackgroundTracking many objects with many sensors
Pasula, H., Russell, S., Ostland, M., & Ritov, Y. (1999) · Cited by 165
Surveillance, Closed Circuit Television and Social Control
Norris, C., & Moran, J. (2016) · Routledge eBooks · doi:10.4324/9781315242019 · Cited by 160
Path detection in video surveillance
Makris, D., & Ellis, T. J. (2002) · Image and Vision Computing · doi:10.1016/s0262-8856(02)00098-7 · Cited by 152 · cited 3×
“The most common technique for modelling entrances and exits is to fit a Gaussian mixture model (GMM) to the start and end points of trajectories using the Expectation Maximisation (EM) algorithm, as in McKenna and Nait-Charif [47], Stauffer [77], Makris and Ellis [43].”
BackgroundTracking people with probabilistic appearance models
Senior, A. (2002) · Cited by 138
PRISMATICA: Toward Ambient Intelligence in Public Transport Environments
Velastín, S. A., Boghossian, B., Lo, B. P. L., Sun, J., & Vicencio-Silva, M. A. (2004) · IEEE Transactions on Systems Man and Cybernetics - Part A Systems and Humans · doi:10.1109/tsmca.2004.838461 · Cited by 127 · cited 1×
“CROMATICA, PRISMATICA and ADVISOR; funded by the European Union) have addressed the monitoring of people in public transport facilities such as metropolitan railways [70,84].”
BackgroundPETS Metrics: On-Line Performance Evaluation Service
Young, D. P., & Ferryman, J. M. (2006) · 2005 IEEE International Workshop on Visual Surveillance and Performance Evaluation of Tracking and Surveillance · doi:10.1109/vspets.2005.1570931 · Cited by 115 · cited 2×
“The PETS metrics site [91] provides automatic evaluation of motion detection algorithms using metrics from the AVITRACK project, detailed in [1].”
BackgroundMethodEstimating Tracking Sources and Sinks
Stauffer, C. (2003) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2003.10036 · Cited by 108 · cited 7×
“Stauffer has used a similar technique in lessconstrained single camera scenes using a conservative2 tracker, where tracking output can consist of numerous 2 A conservative tracker is one which only identifies an object or agent as present if there is a high probability of this being the case: very few false positives…”
BackgroundMethodInfluentialLearning spatio-temporal patterns for predicting object behaviour
Sumpter, N., & Bulpitt, A. J. (2000) · Image and Vision Computing · doi:10.1016/s0262-8856(99)00073-6 · Cited by 104 · cited 2×
“Sumpter and Bulpitt [80] present a related technique using neural networks to quantize over trajectories for behaviour modelling and prediction.”
MethodThe ADVISOR Visual Surveillance System
Siebel, N. T., & Maybank, S. J. (2004) · Cited by 101
The Maximum Surveillance Society
Norris, C., & Armstrong, G. (2020) · Routledge eBooks · doi:10.4324/9781003136439 · Cited by 95
Agent orientated annotation in model based visual surveillance
Remagnino, P., Tan, T. N., & Baker, K. D. (2002) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.1998.710817 · Cited by 86 · cited 1×
“In [58] the issue of interactions involving more than one agent is raised, and the authors suggest that a third level of BN would be required to handle such complicated interactions (a scene agent).”
BackgroundRobust statistics: a brief introduction and overview
Hampel, F. R. (2001) · Repository for Publications and Research Data (ETH Zurich) · doi:10.3929/ethz-a-004158597 · Cited by 85 · cited 1×
“the ability for a Gaussian-based model to handle non-Gaussian noise) [22].”
BackgroundWhat Happens Next? The Predictability of Natural Behaviour Viewed through CCTV Cameras
Trościanko, T., Holmes, A., Stillman, J. A., Mirmehdi, M., Wright, D. B., & Wilson, A. (2004) · Perception · doi:10.1068/p3402 · Cited by 84 · cited 1×
“the psychological literature [83] showing that when trying to”
BackgroundMulti-agent visual surveillance of dynamic scenes
Remagnino, P., Tan, T. N., & Baker, K. D. (1998) · Image and Vision Computing · doi:10.1016/s0262-8856(98)00099-7 · Cited by 76 · cited 1×
“Remagnino, Tan and Baker in [59] develop a model for the classification and annotation of multi-agent actions, using BNs on two levels.”
BackgroundVideo-understanding framework for automatic behavior recognition
Brémond, F., Thonnat, M., & Zuniga, M. D. (2006) · Behavior Research Methods · doi:10.3758/bf03192795 · Cited by 76 · cited 1×
“Progress has been made towards formalising this approach for example [10] through a hierarchical classification of primitive events (such as the presence of an object in an area given some a priori meaning) and scenarios (a spatio-temporal combination of events).”
BackgroundThe acquisition and use of interaction behaviour models
Johnson, N. J., Galata, A., & Hogg, D. (2002) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.1998.698706 · Cited by 76 · cited 4×
“Johnson and Hogg [36,37] have developed a method for behaviour modelling which enables prediction of future behaviour, trajectory classification and the detection of unusual or atypical behaviour patterns.”
MethodInfluentialConceptual descriptions from monitoring and watching image sequences
Howarth, R. J., & Buxton, H. (2000) · Image and Vision Computing · doi:10.1016/s0262-8856(99)00025-6 · Cited by 64 · cited 2×
“This was further developed by Buxton and Howarth [26] who enhanced the attentional use of Bayesian interaction agents to provide conceptual descriptions of behaviour.”
BackgroundMulti-camera spatio-temporal fusion and biased sequence-data learning for security surveillance
Wu, G., Wu, Y., Jiao, L., Wang, Y.-F., & Chang, E. Y. (2003) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/957013.957126 · Cited by 63 · cited 2×
“For example, in [35] interesting behaviour was defined as rapid head movements and video produced specifically featuring just that behaviour and in [89] the interesting behaviour detected was people driving in circles or zig-zags in a car-park.”
BackgroundMethodGenerating spatiotemporal models from examples
Baumberg, A., & Hogg, D. (1996) · Image and Vision Computing · doi:10.1016/0262-8856(96)01092-x · Cited by 61
Detecting lameness using ‘Re-sampling Condensation’ and ‘multi-stream cyclic hidden Markov models’
Magee, D., & Boyle, R. D. (2002) · Image and Vision Computing · doi:10.1016/s0262-8856(02)00047-1 · Cited by 54 · cited 8×
“They use HMMs for detecting primitive events (e.g. car-stop) and a stochastic context free grammar to recognise higher level events.”
MethodInfluentialStatistical Models of Object Interaction
Morris, R. J., & Hogg, D. (2000) · International Journal of Computer Vision · doi:10.1023/a:1008159822101 · Cited by 54 · cited 1×
“These people behave strangely in front of video cameras, and the system in question is evaluated on its ability to single out the sequences featuring these actors [37, 50].”
BackgroundSummarising contextual activity and detecting unusual inactivity in a supportive home environment
McKenna, S. J., & Nait‐Charif, H. (2004) · Pattern Analysis and Applications · doi:10.1007/s10044-004-0233-2 · Cited by 53 · cited 6×
“McKenna and Nait-Charif [47] use maximum penalised likelihood (MAP) estimation, which they claim results in Gaussian components that correspond to meaningful semantic regions.”
BackgroundMethodInfluentialGalata, A., Cohn, A. G., Magee, D., & Hogg, D. (2002) · Cited by 51
Performance Evaluating the Evaluator
List, T., Bins, J., Vazquez, J., & Fisher, R. B. (2006) · IEEE International Workshop on Visual Surveillance and Performance Evaluation of Tracking and Surveillance (VS-PETS) · doi:10.1109/vspets.2005.1570907 · Cited by 43 · cited 3×
“[41] in which three human annotators mark up the same sequence.”
BackgroundMethodInfluentialEvaluation of Motion Segmentation Quality for Aircraft Activity Surveillance
Aguilera, J., Wildenauer, H., Kampel, M., Borg, M., Thirde, D., & Ferryman, J. M. (2006) · IEEE International Workshop on Visual Surveillance and Performance Evaluation of Tracking and Surveillance (VS-PETS) · doi:10.1109/vspets.2005.1570928 · Cited by 37 · cited 1×
“The PETS metrics site [91] provides automatic evaluation of motion detection algorithms using metrics from the AVITRACK project, detailed in [1].”
MethodOcclusion analysis: Learning and utilising depth maps in object tracking
Greenhill, D. R., Renno, J.-P., Orwell, J., & Jones, G. A. (2006) · Image and Vision Computing · doi:10.1016/j.imavis.2006.12.007 · Cited by 36 · cited 1×
“In [20] Greenhill and others develop this approach, and create a depth map based upon the location in the image plane of the top of each moving person’s head.”
BackgroundPerformance evaluation of event detection solutions: the creds experience
Ziliani, F., Velastín, S. A., Porikli, F., Marcenaro, L., Kelliher, T. P., Cavallaro, A., & Bruneaut, P. (2006) · IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS) · doi:10.1109/avss.2005.1577267 · Cited by 35
A real time surveillance system for metropolitan railways
Black, J., Velastín, S. A., & Boghossian, B. (2006) · IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS) · doi:10.1109/avss.2005.1577265 · Cited by 33 · cited 2×
“Some of the systems submitted for the challenge were fully-fledged surveillance systems which were capable of detecting events not specified in the challenge (such as [6], which could detect graffiti and abandoned packages).”
BackgroundSherrah, J., & Gong, S. (2002) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2001.937596 · Cited by 30 · cited 3×
“In [68,69] the output of these filters is analysed using GMMs to detect events, and then these are”
BackgroundMethodSchödl, A., & Essa, I. A. (2005) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2001.990534 · Cited by 19 · cited 1×
“In [65] a method for learning a model of scene occlusions from the tracks of moving agents using minimum description length is described, which creates successively more detailed depth models by dividing the scene into “layers”.”
MethodMetro railway security algorithms with realworld experience adapted to the RATP dataset
Seyve, C. (2006) · IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS) · doi:10.1109/avss.2005.1577263 · Cited by 11 · cited 1×
“The systems demonstrated as part of the CREDS challenge [6,64,67,75] detected some activities with ease – often simply by defining areas of scene which were forbidden unless the moving object happened to be a train.”
BackgroundJoint spatial and temporal structure learning for task based control
Sage, K., & Buxton, H. (2004) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr.2004.1334032 · Cited by 7 · cited 1×
“Variable Length Markov Models (VLMMs) have been used [17,63] for the modelling of behaviours in a number of settings.”
MethodWavelet-based holistic sequence descriptor for generating video summaries
Graves, A., & Gong, S. (2004) · British Machine Vision Conference (BMVC) · doi:10.5244/c.18.19 · Cited by 3 · cited 3×
“up a can”, and in [19] events such as a car reversing are”
BackgroundMethod
Cited by
Visual privacy protection methods: A survey
Padilla-López, J. R., Chaaraoui, A. A., & Flórez-Revuelta, F. (2015) · Expert Systems with Applications · doi:10.1016/j.eswa.2015.01.041 · Cited by 226
Metadata
- Authors
- Dee, H. M., & Velastin, S. A.
- Venue
- Machine Vision and Applications
- Published
- 2007-05-05
- Volume
- 19
- Issue
- 5-6
- Pages
- 329-343
- ISSN
- 0932-8092 (ISSN-L)
- 1432-1769
- OpenAlex
- W1987517671
- Cited by
- 177
- References
- 63
- FWCI
- 18.33
- Type
- journal article
- Language
- en
- Open access
- closed
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.