In this paper, a new efficient method based on mixed statistic feature is proposed for video anomaly detection in densely crowded scenes. The proposed mixed statistic feature is a hand-designed feature considering both magnitude and phase information of the optical flow block after the preprocessing step which based on the latent consistency information of moving objects in the block. Gaussian ...

This paper proposes a novel vision based multi-pedestrian tracking scheme in crowded scenes, which are very common in real-world applications. The major challenge of the multi-pedestrian tracking problem comes from complicated occlusions, cluttered or even changing background. We address these issues by creatively combining state-of-the-art pedestrian detectors and clustering algorithms. The co...

This paper presents a novel framework for detecting abnormal pedestrian and vehicle behaviour by modelling cross-correlation among different co-occurring objects both locally and globally in a given scene. We address this problem by first segmenting a scene into semantic regions according to how object events occur globally in the scene, and second modelling concurrent correlations among region...

Abstract. This master thesis discribes a new dense spatio-temporal motion segmentation algorithm with application to tracking of people in crowded environments. The algorithm is based on state-of-the-art motion and image segmentation algorithms. We specifically make use of a mean shift image segmentation algorithm and two graph based motion segmentation algorithms. The resulting motion segmenta...

Generic person detection is an ill-posed problem as context is widely ignored. Local context can be used to split the generic detection task into easier sub-problems, which was recently explored by classifier grids. The detection problem gets simplified spatially by training separate classifiers for each possible location in the image. So far, adaptive grid based approaches only focused on expl...

This paper presents an investigation into event detection in crowded scenes, where the event of interest co-occurs with other activities and only binary labels at the clip level are available. The proposed approach incorporates a fast feature descriptor from the MPEG domain, and a novel multiple instance learning (MIL) algorithm using sparse approximation and random sensing. MPEG motion vectors...

Detecting activities which involve a sequence of complex pose and motion changes in unsegmented videos is a challenging task, and common approaches use sequential graphical models to infer the human pose-state in every frame. We propose an alternative model based on detecting the key-poses in a video, where only the temporal positions of a few key-poses are inferred. We also introduce a novel p...

We present an approach to non-rigid object tracking designed to handle textured objects in crowded scenes captured by non-static cameras. For this purpose, groups of low-level features are combined into a model describing both the shape and the appearance of the object. This results in remarkable robustness to severe partial occlusions, since overlapping objects are unlikely to be indistinguish...

In this paper we present a novel method for dominant motion analysis in crowded scenes, based on corner features. Corner features identify characteristic regions in the crowd. In our method, we initialize corner features on the scene, and advect them through optical flow. Approximating the moving corner features to individuals, their interaction forces, represented as endothermic reactions in a...

Video surveillance is widely used to monitor the place which needs constant security such as Banks, Shopping Malls, Highways, crowded public places, country borders etc. The major disputes include the complex motion behaviours of different human objects, complex scenes with numerous targets, detection of change in human motion. The objective of this paper is to develop a visual detection and tr...