Unified Target Detection and Tracking Using Motion Coherence

This paper details the construction of three-dimensional separable steerable filters. The approach presented is an extension of the construction of two-dimensional separable steerable filters outlined in [1]. Additionally, three-dimensional separable steerable filters, both continuous and discrete versions, for the second derivative of the Gaussian and its Hilbert transform are reported. Experimental evaluation demonstrates that the errors in the constructed separable filters are negligible.

show abstract

“…Early delineation of coherently moving structures can provide a strong cue to target detection and tracking [17]. Correspondingly, Fig.…”

Section: Experimental Evaluationmentioning

confidence: 98%

Three-dimensional nth derivative of Gaussian separable steerable filters

Derpanis

Gryn

2005

IEEE International Conference on Image Processing 2005

View full text Add to dashboard Cite

show abstract

“…Wildes [16,15] proposed measures of motion saliency and some primitive classes of spatiotemporal structures based on SOE features. Enzweiler et al [10] used a measure of "Coherent Motion Energy" based on SOE features for target detection and tracking. However the fundamental feature set utilised for motion estimation in this work is intensity.…”

Section: Introductionmentioning

confidence: 99%

Role of Spatiotemporal Oriented Energy Features for Robust Visual Tracking in Video Surveillance

Emami

Dadgostar

Bigdeli

et al. 2012

2012 IEEE Ninth International Conference on Advanced Video and Signal-Based Surveillance

View full text Add to dashboard Cite

We propose an effective approach to take advantage of the rich description provided by Spatiotemporal Oriented Energy features for the purpose of robust tracking. There are two core components in our system. The first one is a compound measure of 'Coherent Motion' and 'Identity Motion Signature' which is introduced based on motion dynamics of the targets. This measure is used for robust optimisation in occluded situations as well as an adaptive template updating scheme. The second component is a state machine which detects various states of the targets based on statistical analysis of their 'Motion Signature'. Empirical evaluations demonstrate improvement in performance of the tracking system along with the role of each component.

show abstract

“…(1) is mostly a bottom-up process which has to cope with changes in the appearance of the target, like for example Mean-Shift [5], [3], Particle filtering [10], [12] or iterative errorminimising [9], [11], [8] approaches. Those kinds of approaches typically keep the position of the object of interest in an image sequence.…”

Section: Introductionmentioning

confidence: 99%

Probabilistic shape vision for embedded systems

Olufs

Vincze

Plöger

2011

2011 8th International Conference on Ubiquitous Robots and Ambient Intelligence (URAI)

View full text Add to dashboard Cite

This paper presents a robust object tracking method using a sparse shape-based object model for embedded systems with limited computational capabilities. Our approach consists of three ingredients namely shapes, a motion model and a sparse (non-binary) subsampling of colours in background and foreground parts based on the shape assumption. The tracking itself is inspired by the idea of having a short-term and a longterm memory. A lost object is "missed" by the long-term memory when it is no longer recognized by the shortterm memory. Moreover, the long-term memory allows to re-detect vanished objects and using their new position as a new initial position for object tracking. The short-term memory is implemented with a new Monte Carlo variant which provides a heuristic to cope with the loss-of-diversity problem. It enables simultaneous tracking of multiple (visually) identical objects. The long-term memory is implemented with a Bayesian Multiple Hypothesis filter. We demonstrate the robustness of our approach with respect to object occlusions and non-Gaussian/non-linear movements of the tracked object. Our approach is very scalable since one can tune the parameters for a trade-off between precision and computational time.

show abstract

Unified Target Detection and Tracking Using Motion Coherence

Abstract: Abstract

Cited by 7 publications

References 32 publications

Three-dimensional nth derivative of Gaussian separable steerable filters

Three-dimensional nth derivative of Gaussian separable steerable filters

Role of Spatiotemporal Oriented Energy Features for Robust Visual Tracking in Video Surveillance

Probabilistic shape vision for embedded systems

Contact Info

Product

Resources

About