Visual abnormal behavior detection based on trajectory sparse reconstruction analysis

Li, Ce; Han, Zhenjun; Ye, Qixiang; Jiao, J. B.

doi:10.1016/j.neucom.2012.03.040

Cited by 85 publications

(48 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Finally, the abnormal event is identified by measuring the deviation or probability of the testing trajectory with respect to the normal event models. Li et al [9] learned a dictionary using normal trajectories and then detected abnormal events according to the reconstruction error of their trajectory under the learned dictionary. Aköz et al [10] proposed a traffic event classification system that learned normal and common traffic flows by clustering vehicle trajectories.…”

Section: ) Trajectory-wise Descriptormentioning

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

Section: ) Trajectory-wise Descriptormentioning

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

show abstract

“…Other works are able to detect anomalies locally in videos and without an explicit definition of what the abnormality is. Among these, two main classes are found: trajectory-based (Stauffer and Grimson, 2000;Piciarelli et al, 2008;Wu et al, 2010;Jiang et al, 2011;Zen et al, 2012;Li et al, 2013) and feature-based ones (Adam et al, 2008;Kim and Grauman, 2009;Kratz and Nishino, 2009;Antic and Ommer, 2011;Bertini et al, 2012;Cong et al, 2013;Hu et al, 2013;Li et al, 2014;Cheng et al, 2015;Zhang et al, 2016).…”

Section: Related Workmentioning

confidence: 99%

“…Sparse representations have been increasingly adopted for anomaly detection, as the problem can be elegantly modeled with sparse linear combinations of representations in a training dataset (Zhao et al, 2011;Cong et al, 2013;Li et al, 2013;Zhu et al, 2014). Explicit image space subdivision can also benefit anomaly localization performance in sparse representation-based methods (Biswas and Babu, 2014).…”

Section: Related Workmentioning

confidence: 99%

Detection and Localization of Anomalous Motion in Video Sequences from Local Histograms of Labeled Affine Flows

2017

View full text Add to dashboard Cite

“…Many pioneering algorithms [1,16,4,14,15] have been developed during this period. According to Ce Li et al [12], all of them can be coarsely classified into two categories, namely trajectory analysis and features based analysis such as optical flow, etc. In trajectory analysis [12,16,21,18], usual behavior is learned through tracking of normal objects/persons and their interaction.…”

Section: Related Workmentioning

confidence: 99%

“…According to Ce Li et al [12], all of them can be coarsely classified into two categories, namely trajectory analysis and features based analysis such as optical flow, etc. In trajectory analysis [12,16,21,18], usual behavior is learned through tracking of normal objects/persons and their interaction. On the other side, video feature based analysis [4,15,2,3] involves abnormality detection based on the feature of a space-time cube.…”

Section: Related Workmentioning

confidence: 99%

Short Local Trajectory based moving anomaly detection

Biswas

Babu

2014

Proceedings of the 2014 Indian Conference on Computer Vision Graphics and Image Processing

View full text Add to dashboard Cite

A high level abstraction of the behavior a moving object can be obtained by analyzing its trajectory. However, traditional trajectories or tracklets are bound by the limitations of the underlying tracking algorithm used. In this paper, we propose a novel idea of detecting anomalous objects amid other moving objects in a video based on its short history. This history is defined as short local trajectory (SLT). The unique approach of generating SLTs from super-pixels belonging to a foreground object that incorporates both spatial and temporal information is the key in detection of anomaly. Additionally, the proposed trajectory extraction is robust across videos having different crowd density, occlusions, etc. Generally the trajectories of persons/objects moving at a particular region under usual conditions has certain fixed characteristics, thus we use Hidden Markov Model (HMM) for capturing the usual trajectory patterns during training. Whereas during detection, the proposed algorithm takes SLTs as observations for each super-pixel and measures its likelihood of being anomaly using the learned HMMs. Furthermore, we compute the spatial consistency measure for each SLT based on the neighboring trajectories. Thus, anomaly detected by the proposed approach is highly localized as demonstrated from the experiments conducted on two widely used anomaly datasets, namely UCSD Ped1 and UCSD Ped2.

show abstract

Visual abnormal behavior detection based on trajectory sparse reconstruction analysis

Cited by 85 publications

References 27 publications

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

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

Detection and Localization of Anomalous Motion in Video Sequences from Local Histograms of Labeled Affine Flows

Short Local Trajectory based moving anomaly detection

Contact Info

Product

Resources

About