Violence detection in crowded scenes using substantial derivative

Mohammadi, Sadegh; Kiani, Hamed; Perina, Alessandro; Murino, Vittorio

doi:10.1109/avss.2015.7301787

Cited by 60 publications

(41 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Hockey Dataset Movies Dataset Violent-Flows Dataset MoSIFT+HIK [21] 90.9% 89.5% -ViF [15] 82.9±0.14% -81.3±0.21% MoSIFT+KDE+Sparse Coding [32] 94.3±1.68% -89.05±3.26% Deniz et al [8] 90.1±0% 98.0±0.22% -Gracia et al [13] 82.4±0.4% 97.8±0.4% -Substantial Derivative [20] -96.89±0.21% 85.43±0.21% Bilinski et al [2] 93.4 99 96.4 MoIWLD [34] 96.8±1.04% -93.19±0.12% ViF+OViF [11] 87.5±1.7% -88±2.45% Three streams + LSTM [10] 93.9 --Proposed 97.1±0.55% 100±0% 94.57±2.34%…”

Section: Methodsmentioning

confidence: 99%

“…Inter-frame changes: Frames containing violence undergo massive variations because of fast motion due to fights [28,5,4,8] 2. Local motion in videos: The motion change patterns taking place in the video is analyzed [6,3,7,21,15,32,20,24,13,2,11,34] Vasconcelos and Lippman [28] used the tangent distance between adjacent frames for detecting the inter-frame variations. Clarin et al improves this method in [5] by finding the regions with skin and blood and analyzing these regions for fast motion.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Learning to detect violent videos using convolutional long short-term memory

Sudhakaran

Lanz

2017

2017 14th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS)

249

123

View full text Add to dashboard Cite

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Learning to detect violent videos using convolutional long short-term memory

Sudhakaran

Lanz

2017

2017 14th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS)

249

123

View full text Add to dashboard Cite

show abstract

“…Accuracy Speed (FPS) SD [8] 85.43±0.21% N/A HOT [7] 82.3% N/A ViF [3] 81.3±0.18% 30 CM [9] 81.5% 5 Our Method (SVM) 85.53±0.17% 40 Our Method (GMM) 65.8±0.15% 40 Table 5. The contribution of each feature towards mean detection accuracy on the violent-flows dataset using our SVMbased detection.…”

Section: Methodsmentioning

confidence: 99%

“…Techniques based on optical flow/tracklets include the Social Force Model [6], HOT (Histogram of Oriented Tracklets) [7], Substantial Derivative [8], Commotion Measure [9] and ViF (violent-flows descriptor) [3]. These approaches collate local motion vectors before applying a physics inspired model to generate a representation of crowd behaviour which can be used to classify crowd behaviour.…”

Section: Introductionmentioning

confidence: 99%

Holistic features for real-time crowd behaviour anomaly detection

Marsden

McGuinness

Little

et al. 2016

2016 IEEE International Conference on Image Processing (ICIP)

View full text Add to dashboard Cite

This paper presents a new approach to crowd behaviour anomaly detection that uses a set of efficiently computed, easily interpretable, scene-level holistic features. This lowdimensional descriptor combines two features from the literature: crowd collectiveness [1] and crowd conflict [2], with two newly developed crowd features: mean motion speed and a new formulation of crowd density. Two different anomaly detection approaches are investigated using these features. When only normal training data is available we use a Gaussian Mixture Model (GMM) for outlier detection. When both normal and abnormal training data is available we use a Support Vector Machine (SVM) for binary classification. We evaluate on two crowd behaviour anomaly detection datasets, achieving both state-of-the-art classification performance on the violentflows dataset [3] as well as better than real-time processing performance (40 frames per second).

show abstract

“…Only few of them, though, are concerned with dangerous behaviors. These methods can be further divided into those detecting dangerous crowd behaviors, in which the individual motion is superseded by large flows as in [68,69,70,71], and those detecting closer dangerous human behaviors.…”

Section: Related Work and Datasets On Abnormal Behaviorsmentioning

confidence: 99%

Discovery and recognition of motion primitives in human activities

2019

View full text Add to dashboard Cite

We present a novel framework for the automatic discovery and recognition of motion primitives in videos of human activities. Given the 3D pose of a human in a video, human motion primitives are discovered by optimizing the ‘motion flux’, a quantity which captures the motion variation of a group of skeletal joints. A normalization of the primitives is proposed in order to make them invariant with respect to a subject anatomical variations and data sampling rate. The discovered primitives are unknown and unlabeled and are unsupervisedly collected into classes via a hierarchical non-parametric Bayes mixture model. Once classes are determined and labeled they are further analyzed for establishing models for recognizing discovered primitives. Each primitive model is defined by a set of learned parameters. Given new video data and given the estimated pose of the subject appearing on the video, the motion is segmented into primitives, which are recognized with a probability given according to the parameters of the learned models. Using our framework we build a publicly available dataset of human motion primitives, using sequences taken from well-known motion capture datasets. We expect that our framework, by providing an objective way for discovering and categorizing human motion, will be a useful tool in numerous research fields including video analysis, human inspired motion generation, learning by demonstration, intuitive human-robot interaction, and human behavior analysis.

show abstract

Violence detection in crowded scenes using substantial derivative

Cited by 60 publications

References 15 publications

Learning to detect violent videos using convolutional long short-term memory

Learning to detect violent videos using convolutional long short-term memory

Holistic features for real-time crowd behaviour anomaly detection

Discovery and recognition of motion primitives in human activities

Contact Info

Product

Resources

About