In this paper, we present a novel approach for video-anomaly detection in crowded and complicated scenes. The proposed approach detects anomalies based on a hierarchical activity-pattern discovery framework, comprehensively considering both global and local spatio-temporal contexts. The discovery is a coarse-to-fine learning process with unsupervised methods for automatically constructing norma...

In this paper, we present a real-time pedestrian detection system that uses a pair of moving cameras to detect both stationary and moving pedestrians in crowded environments. This is achieved through stereo-based segmentation and neural network-based recognition. Stereo-based segmentation allows us to extract objects from a changing background; neural network-based recognition allows us to iden...

There are a number of solutions to automate the monotonous task of looking at a monitor to find suspicious behaviors in video surveillance scenarios. Detecting strange objects and intruders, or tracking people and objects, is essential for surveillance and safety in crowded environments. The present work deals with the idea of jointly modeling simple and complex behaviors to report local and gl...

In this paper, we address the challenging task of pedestrian detection. The topic keyword Real-World should be noted as a synonym for a realistic detection environment (e.g. real-time, robustness, occlusions). We present some basic approaches for urban human detection and refine them to a suitable solution. We then discuss problems of detectors with common scene conditions and introduce an dete...

We present a planning framework for producing socially competent robot behaviors in pedestrian environments. The framework is designed according to conclusions of recent psychology studies on action interpretation and sociology studies on human pedestrian behavior. The core of the approach is a novel topological representation of the pedestrian scene, based on braid groups. Thanks to this repre...

This paper, addresses the problem of detecting heads in crowded real world scenes, by combining a human head, an upper-body and a body detector to create a robust head detector. The idea is not to rely on a single detector. Instead, a head, an upper-body and a body detector, are used for decision making by combining their individual opinions to derive a consensus decision. The combined classifi...

This work presents an approach for generating video evidence of dangerous situations in crowded scenes. The scenarios of interest are those with high safety risk such as blocked exit, collapse of a person in the crowd, and escape panic. Real visual evidence for these scenarios is rare or unsafe to reproduce in a controllable way. Thus there is a need for simulation to allow training and validat...

In this paper, we present a real-time pedestrian detection system that uses a pair of moving cameras to detect both stationary and moving pedestrians in crowded environments. This is achieved through stereo-based segmentation and neural network-based recognition. Stereo-based segmentation allows us to extract objects from a changing background; neural network-based recognition allows us to iden...

State-of-the-art multi-object tracking~(MOT) methods follow the tracking-by-detection paradigm, where object trajectories are obtained by associating per-frame outputs of detectors. In crowded scenes, however, detectors often fail to obtain accurate detections due heavy occlusions and high crowd density. this paper, we propose a new MOT tracking-by-counting, tailored for scenes. Using density m...

How are complex visual entities such as scenes represented in the human brain? More concretely, along what visual and semantic dimensions are scenes encoded in memory? One hypothesis is that global spatial properties provide a basis for categorizing the neural response patterns arising from scenes. In contrast, non-spatial properties, such as single objects, also account for variance in neural ...