Event Detection and Analysis from Video Streams

By Gérard G. Medioni, I. Cohen, Francois Bremond, Somboon Hongeng, Ramkant Nevatia. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2001

495 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/048ef48f58156ab9f8eb4c1126e090194459e699

How researchers see this paper

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

In Aerospace Engineering

In Computer Vision and Pattern Recognition

Citations in the corpus

Trajectory-Based Anomalous Event Detection (2008, methodology): “Other works are based on the integration of prior knowledge and low-level data acquired by video processing (change detection, object tracking, etc.) as in the works by Ayers and Shah [7] or Medioni et al. [8].”
Semi-supervised adapted HMMs for unusual event detection (2005, methodology): “Most works have been centered on the detection of predeﬁned events in particular conditions using supervised statistical learning methods, such as HMMs [12, 7, 18], and other graphical models [3, 11, 10, 9].”
Video-based event recognition: activity representation and probabilistic recognition methods (2004, methodology): “The event recognition methods described in [5] are based on a heuristic method and could not handle multiple-actor events.”
Understanding Video Events: A Survey of Methods for Automatic Interpretation of Semantic Occurrences in Video (2009, background): “Event domains for which FSM event models are utilized include hand gestures [45], single-actor actions [46], multiple person interaction [17], and aerial surveillance [47].”
Incremental Local Outlier Detection for Data Streams (2007, background): “Further, on-line detection of unusual behavior and events also plays a significant role in video and image analysis [14-16].”
Semantic event representation and recognition using syntactic attribute graph grammar (2009, background): “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).”
Detecting anomalous events in videos by learning deep representations of appearance and motion (2017, background): “Trajectories are widely used features for abnormal video event detection [26, 6], due to their ability of describing synthetically the dynamic information of foreground objects.”
Robust Real-Time Unusual Event Detection using Multiple Fixed-Location Monitors (2008, result): “In contrast with most previous works reported, our algorithm satisfies all of these requirements (having of course its own limitations which will be discussed).”
Unsupervised Activity Perception in Crowded and Complicated Scenes Using Hierarchical Bayesian Models (2008, unknown): “Then, object tracks are used to model activities [7], [8], [9], [10], [11], [12], [13], [14], [15], [16], [17], [18].”
Discriminative Latent Models for Recognizing Contextual Group Activities (2012, methodology): “Unlike their approach, which uses a nonparametric model for edge selection, we propose a latent structured model that captures group activity and individual person’s actions in a joint framework.”
Beyond Actions: Discriminative Models for Contextual Group Activities (2010, unknown): “Relatively few work attempts to model the high-level group activities [31, 22, 50, 29, 21, 27, 35].”
Leaving Some Stones Unturned: Dynamic Feature Prioritization for Activity Detection in Streaming Video (2016, background): “, [27]), they are limited to activities well-defined by a moving foreground subject.”
Detecting unusual activity in video (2004, background): “A common choice is to use Hidden Markov Models [1] [9] [10] or other graphical models [11] which quantize image features into a set of discrete states and model how states change in time.”
Tracking and Modeling of Human Activity Using Laser Rangefinders (2010, background): “The recognition of these low level actions is usually performed by defining a hidden Markov model (HMM) for each action (Medioni et al., 2001; Oliver et al., 2002).”
Machine Recognition of Human Activities: A Survey (2008, unknown): “[122] propose a hierarchical representation to”
Intelligent multi-camera video surveillance: A review (2013, background): “…surveillance systems (Johnson and Hogg, 1995; Stauffer and Grimson, 2000; Oliver et al., 2000; Haritaoglu et al., 2000; Brand and Kettnaker, 2000; Medioni et al., 2001; Honggeng and Nevatia, 2001; Hu et al., 2004; Wang et al., 2006; Morris and Trivedi, 2008; Wang et al., 2008, 2011), objects are…”
Weakly-supervised Video Anomaly Detection with Robust Temporal Feature Magnitude Learning (2021, background): “Traditional anomaly detection methods assume the availability of normal training data only and address the problem with one-class classification using handcrafted features [2, 32, 64, 75].”