A System for Video Surveillance and Monitoring

By Robert T. Collins, A. Lipton, Takeo Kanade, Hironobu Fujiyoshi, D. Duggins, Yanghai Tsin, David Tolliver, Nobuyoshi Enomoto, Osamu Hasegawa, P. Burt and 1 more. 2000

1,460 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

Soft-NMS — Improving Object Detection with One Line of Code (2017, background): “nerates bounding boxes for speciﬁed object categories and assigns them classiﬁcation scores. It has many practical applications in autonomous driving [5,8], video/image indexing [26,20], surveillance [2,10] etc. Hence, any new component proposed for the object detection pipeline should not create a ”
SensEye: a multi-tier camera sensor network (2005, background): “Another example of a single-tier video surveillance and monitoring system is VASM [17].”
Semantic event representation and recognition using syntactic attribute graph grammar (2009, methodology): “In the computer vision literature, there has been a significant amount of event understanding research in various application domains (Buxton and Gong, 1995; Haritaoglu et al., 2000; Medioni et al., 2001; Ivanov and Bobick, 2000; Bobick and Wilson, 1997; Collins et al., 2000; Xu and Chang, 2007).”
Multi-camera multi-person tracking for EasyLiving (2000, methodology): “CMU’s VSAM tracker[ 9 ] uses frame-to-frame matching of blobs based on the blob’s trajectory, image template, size, and histogram, all in image coordinate frames of each camera.”
A survey on activity recognition and behavior understanding in video surveillance (2013, background): “[29] shape single human, vehicles, human groups, clutter neural network image blob area, dispersedness, aspect ratio of blob bounding box classifier results kept in histogram”
Learning Patterns of Activity Using Real-Time Tracking (2000, background): “6.1 Previous Work in Classification There are countless examples of tracking systems that perform predetermined classification tasks on tracked data, e.g., human vs. vehicle or walking vs. running [ 2 ]; walking, marching, linewalking, and kicking [3]; etc.”
Adaptive Focus for Efficient Video Recognition (2021, background): “, on YouTube or TikTok) has fueled the demands for automatically recognizing human actions, events, or other contents within them, which benefits applications like recommendation [7, 8, 15], surveillance [6, 3] and content-based searching [22].”
A Self-Organizing Approach to Background Subtraction for Visual Surveillance Applications (2008, background): “The detection of moving objects in video streams is the first relevant step of information extraction in many computer vision applications.”
Performance evaluation of object detection algorithms for video surveillance (2006, methodology): “They rely on different assumptions , e.g., statistical models of the background [1]–[3], minimization of Gaussian differences [4], minimum and maximum values [5], adaptivity [6], [7] or a combination of frame differences and statistical background models [8].”
Learning and detecting activities from movement trajectories using the hierarchical hidden Markov model (2005, background): “Building intelligent systems in smart environments is the goal of much research [1, 6, 10, 11, 12, 13].”
Motion history image: its variants and applications (2012, methodology): “These temporal differencing methods employed among two [21,43, 88,146] or three consecutive frames [28,76] are adaptive to dynamic environments, though we can note poor extraction of the relevant feature pixels in general.”
A survey of active and passive indoor localisation systems (2012, methodology): “Carnegie Mellon University (CMU) developed a video-based monitoring system under the DARPA Video Surveillance and Monitoring (VSAM) project (1997–1999) [85].”
Video fire detection - Review (2013, methodology): “More complex systems use rule-based techniques such as Gaussian smoothed color histograms [7], statistically generated color models [15], and blending functions [20].”
A system for learning statistical motion patterns (2006, background): “For instance, Collins et al. [8] allocate detected objects to semantic categories such as human, human group, and vehicle.”
Computer vision based method for real-time fire and flame detection (2006, positive): “…[k, l] is assumed to be moving if the brightness values corresponding to it in image frame x n and image frame x nÀ1 satisfy the following inequality: jx n ½k; l À x nÀ1 ½k; lj > T n ½k; l; ð2Þ where T n [k, l] is a threshold that is adaptively determined as described in (Collins et al., 1999).”
A survey of appearance models in visual object tracking (2013, neutral): “58”
Recent developments in human motion analysis (2003, methodology): “For instance, VSAM [1] has successfully developed a hybrid algorithm for motion segmentation by combining an adaptive background subtraction algorithm with a three-frame diOerencing technique.”
Cyclops: in situ image sensing and interpretation in wireless sensor networks (2005, neutral): “actuation of the imagers [25] [26] [24].”
A survey on visual surveillance of object motion and behaviors (2004, methodology): “For example, the Defense Advanced Research Projection Agency (DARPA) supported the Visual Surveillance and Monitoring (VSAM) project [3] in 1997, whose purpose was to develop automatic video understanding technologies that enable a single human operator to monitor behaviors over complex areas such…”