Object tracking using adaptive covariance descriptor and clustering-based model updating for visual surveillance.

Lei Qin,Hichem Snoussi,Fahed Abdallah

doi:10.3390/s140609380

Abstract

We propose a novel approach for tracking an arbitrary object in video sequences for visual surveillance. The first contribution of this work is an automatic feature extraction method that is able to extract compact discriminative features from a feature pool before computing the region covariance descriptor. As the feature extraction method is adaptive to a specific object of interest, we refer to the region covariance descriptor computed using the extracted features as the adaptive covariance descriptor. The second contribution is to propose a weakly supervised method for updating the object appearance model during tracking. The method performs a mean-shift clustering procedure among the tracking result samples accumulated during a period of time and selects a group of reliable samples for updating the object appearance model. As such, the object appearance model is kept up-to-date and is prevented from contamination even in case of tracking mistakes. We conducted comparing experiments on real-world video sequences, which confirmed the effectiveness of the proposed approaches. The tracking system that integrates the adaptive covariance descriptor and the clustering-based model updating method accomplished stable object tracking on challenging video sequences.

Highlights

Visual tracking is an important and challenging task for building visual surveillance systems
Our goal is to develop an efficient and robust way to keep tracking the object throughout long-term video sequences in the presence of significant appearance variations and severe occlusions
Our idea for approaching robust visual tracking is of two folds: (1) build an object appearance model using descriptors or feature representations that have are discriminative and robust to extrinsic variations; (2) update the appearance model in a punctual and careful manner to keep the model adaptive to the intrinsic variations of the target

Summary

Introduction

Visual tracking is an important and challenging task for building visual surveillance systems. In [2], both deterministic and probabilistic patch-based approaches are tested for observation detection for single object tracking. We focus on the problem of tracking an arbitrary object with no prior knowledge other than an annotation in the first frame. Our goal is to develop an efficient and robust way to keep tracking the object throughout long-term video sequences in the presence of significant appearance variations and severe occlusions. Our idea for approaching robust visual tracking is of two folds: (1) build an object appearance model using descriptors or feature representations that have are discriminative and robust to extrinsic variations; (2) update the appearance model in a punctual and careful manner to keep the model adaptive to the intrinsic variations of the target

Objectives

Methods

Results

Discussion

Conclusion