Spatio-temporal context analysis within video volumes for anomalous-event detection and localization

Li, Nannan; Wang, Xinyu; Xu, Dan; Guo, Heng; Feng, Wei

doi:10.1016/j.neucom.2014.12.064

Cited by 64 publications

(45 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Leong et al 2003;Cristani et al 2013). There is also an increasing use of remote monitoring where researchers collect an impressive amount of data, which they have then to review to extract the target events (van Dam et al 2013;Li et al 2015). Computer-aided programs are thus instrumental in ensuring a manageable process that can lead to results (Visser 1993;Noldus et al 2000).…”

Section: Introductionmentioning

confidence: 99%

BORIS: a free, versatile open‐source event‐logging software for video/audio coding and live observations

2016

View full text Add to dashboard Cite

Summary1. Quantitative aspects of the study of animal and human behaviour are increasingly relevant to test hypotheses and find empirical support for them. At the same time, photo and video cameras can store a large number of video recordings and are often used to monitor the subjects remotely. Researchers frequently face the need to code considerable quantities of video recordings with relatively flexible software, often constrained by speciesspecific options or exact settings. 2. BORIS is a free, open-source and multiplatform standalone program that allows a user-specific coding environment to be set for a computer-based review of previously recorded videos or live observations. Being open to user-specific settings, the program allows a project-based ethogram to be defined that can then be shared with collaborators, or can be imported or modified. 3. Projects created in BORIS can include a list of observations, and each observation may include one or two videos (e.g. simultaneous screening of visual stimuli and the subject being tested; recordings from different sides of an aquarium). Once the user has set an ethogram, including state or point events or both, coding can be performed using previously assigned keys on the computer keyboard. BORIS allows definition of an unlimited number of events (states/point events) and subjects. 4. Once the coding process is completed, the program can extract a time-budget or single or grouped observations automatically and present an at-a-glance summary of the main behavioural features. The observation data and time-budget analysis can be exported in many common formats (TSV, CSV, ODF, XLS, SQL and JSON). The observed events can be plotted and exported in various graphic formats (SVG, PNG, JPG, TIFF, EPS and PDF).

show abstract

Section: Introductionmentioning

confidence: 99%

BORIS: a free, versatile open‐source event‐logging software for video/audio coding and live observations

2016

View full text Add to dashboard Cite

show abstract

“…Roshtkhari et al [5] modeled the spatio-temporal composition of small cuboids in a large volume using a probabilistic model and detected abnormal events with irregular compositions in real-time. Li et al [6] exploited the compositional context under a dictionary learning and sparse coding framework. Gupta et al [7] proposed a probabilistic model that exploits contextual information for visual action analysis to improve object recognition as well as activity recognition.…”

Section: Introductionmentioning

confidence: 99%

Abnormal event detection in crowded scenes using histogram of oriented contextual gradient descriptor

Duan

et al. 2018

EURASIP J. Adv. Signal Process.

View full text Add to dashboard Cite

Detecting abnormal events in crowded scenes is an important but challenging task in computer vision. Contextual information is useful for discovering salient events in scenes; however, it cannot be characterized well by commonly used pixel-based descriptors, such as the HOG descriptor. In this paper, we propose contextual gradients between two local regions and then construct a histogram of oriented contextual gradient (HOCG) descriptor for abnormal event detection based on the contextual gradients. The HOCG descriptor is a distribution of contextual gradients of sub-regions in different directions, which can effectively characterize the compositional context of events. We conduct extensive experiments on several public datasets and compare the experimental results using state-of-the-art approaches. Qualitative and quantitative analysis of experimental results demonstrate the effectiveness of the proposed HOCG descriptor.

show abstract

“…As abnormal situations are irregular, there is a need to understand properly the normal occurrences of scenes from input video. The approaches [5], [8] recently has developed a trend to first learn the normal situations based on context, since as the scene changes the same object or the same activity may become anomalous which is again a challenge for computer vision researchers while developing automated system for crowd behavior detection. The benchmark dataset [14,15] contain training videos with only normal behaviors and testing videos with abnormalities, which help to clearly distinguish between normal and abnormal situations so that an automated system can take a proper decision.…”

Section: Introductionmentioning

confidence: 99%

“…The benchmark dataset [14,15] contain training videos with only normal behaviors and testing videos with abnormalities, which help to clearly distinguish between normal and abnormal situations so that an automated system can take a proper decision. For learning normal behaviors, recent approaches are built on motion and appearance [2,3], spatiotemporal [6][7][8] and trajectories [9,10] as prime features. The input frame is subdivided into small blocks called cell and the features are computed on this small part so that detail analysis can be done.…”

Section: Introductionmentioning

confidence: 99%

“…Authors have introduced two normalcy models that jointly account for the appearance and dynamics of complex crowd scenes, temporal normalcy and spatial normalcy. Li et al [8], developed spatiotemporal video volume (STVV) based approach which computes spatial and temporal gradients in a fixed cell from a frame as raw features. These are clustered and represented within a large video cubes using BoW method.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Detection and Localization of Anomalies from Videos based on Optical flow Magnitude and Direction

Bansod¹,

Nandedkar²

2017

Proceedings of the International Conference on Communication and Signal Processing 2016 (ICCASP 2016)

View full text Add to dashboard Cite

Abstract. Anomalies in video scenes means unexpected or unusual activity which is usually not frequently observed. Such activities hence are rare and require sudden attention so that it can be detected as early as possible. There is a need to automatically identify and locate where such anomaly is present. Optical flow magnitude and direction based method is an automated system built on motion, position and statistical features of moving objects present in video. Moving objects are identified by means of optical flow and are represented using bounding box. The normal behaviors is learned beforehand for different objects. A generalization of normal behavior is captured by clustering different directional motions in the scene. Anomalous behavior of objects are detected and localized using motion and positions differing from normal behavior. The performance of proposed method is compared with existing methods by using standard benchmark datasets available online such as UCSD and UMN.

show abstract

Spatio-temporal context analysis within video volumes for anomalous-event detection and localization

Cited by 64 publications

References 49 publications

BORIS: a free, versatile open‐source event‐logging software for video/audio coding and live observations

BORIS: a free, versatile open‐source event‐logging software for video/audio coding and live observations

Abnormal event detection in crowded scenes using histogram of oriented contextual gradient descriptor

Detection and Localization of Anomalies from Videos based on Optical flow Magnitude and Direction

Contact Info

Product

Resources

About