The main challenge of online multi-object tracking is to reliably associate object trajectories with detections in each video frame based on their tracking history. In this work, we propose the Recurrent Autoregressive Network (RAN), a temporal generative modeling framework to characterize the appearance and motion dynamics of multiple objects over time. The RAN couples an external memory and a...

In this paper, we present a video based smoke detection algorithm based on TVL1 optical flow estimation. The main part of the algorithm is an accumulating system for motion angles and upward motion speed of the flow field. We optimized the usage of TVL1 flow estimation for the detection of smoke with very low smoke density. Therefore, we use adapted flow parameters and estimate the flow field o...

We present a system to determine ground-plane parameters in densely crowded scenes where use of geometric features such as parallel lines or reliable estimates of agent dimensions are not possible. Using feature points tracked over short intervals, together with some plausible scene assumptions, we can estimate the parameters of the ground-plane to a sufficient degree of accuracy to correct use...

Detecting static objects in video sequences has a high relevance in many surveillance applications, such as the detection of abandoned objects in public areas. In this paper, we present a system for the detection of static objects in crowded scenes. Based on the detection of two background models learning at different rates, pixels are classified with the help of a finite-state machine. The bac...

Motion is a fundamental cue for scene analysis and human activity understanding in videos. It can be encoded in trajectories for tracking objects and for action recognition, or in form of flow to address behaviour analysis in crowded scenes. Each approach can only be applied on limited scenarios. We propose a motion-based system that represents the spatial and temporal features of the flow in t...

In this paper, we present a cooperative perception system between wall mounted cameras and sensors on-board a mobile robot to : (i) track and follow a given target person wearing a Radio Frequency Identification (RFID) tag, and (ii) facilitate navigation in the presence of passers-by during the execution of this mission. We employ a "trackingby-detection" approach within a Particle Filtering st...

Recent investigations have shown the advantages of keeping multiple hypotheses during visual tracking. In this paper we explore an alternative method that keeps just a single hypothesis per tracked object for computational e ciency, but displays robust performance and recovery from error by employing continuous detection during tracking. The method is implemented in the domain of people-trackin...

Whole genome amplification (WGA) has been touted as a possible technique to augment fragment analysis of STRs in amplifying low-levels of DNA recovered from crime scenes or items. Only LCN DNA analysis is routinely used as an additional amplification step; but this is not without problems, such as the increased incidents of stochastic variations. A review of the literature was carried out in or...

Camera systems have a very important place as they are widely used in providing security crowded environments. The video images recorded by cameras examined to check whether there is dangerous or unusual behavior. It tried develop appropriate measures according the result of this control. Modeling human behaviors for definition and detection abnormal behavior has become popular research area re...

In this book chapter, we will introduce approaches of using topic models for action recognition. Topic models were originally developed in language processing. In recent years, they were applied to action recognition and other computer vision problems, and achieved great success. Topic models are unsupervised. The models of actions are learned through exploring the co-occurrence of visual featu...