Online Feature Selection Using Mutual Information for Real-Time Multi-view Object Tracking

Leung, Chu Lun Alex; Gong, Shaogang

doi:10.1007/11564386_15

Cited by 9 publications

(3 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Usually, a set of candidate features, such as the linear combinations of the basic R, G, B pixel values [22], and other multiple cues [23], [26], are chosen initially. Features can be evaluated and ranked in different ways, such as the variance ratios [22], principal component analysis [24], variance of mutual information [25], and Kullback-Leibler distance [27]. Then the best ones which make foreground most discriminative against surrounding background are selected for tracking.…”

Section: A Discriminative Feature Selection For Trackingmentioning

confidence: 99%

Online Appearance Model Learning and Generation for Adaptive Visual Tracking

Wang

Qiao

2011

IEEE Trans. Circuits Syst. Video Technol.

View full text Add to dashboard Cite

Several adaptive visual tracking algorithms have been recently proposed to capture the varying appearance of target. However, adaptability may also result in the problem of gradual drift, especially when the target appearance changes drastically. This paper gives some theoretical principles for online learning of target model, and then presents a novel adaptive tracking algorithm which is able to effectively cope with drastic variations in target appearance and resist gradual drift. Once target is localized in each frame, the patches sampled from target observation are first classified into foreground and background using an effective classifier. Then the adaptive, pure and timecontinuous target model is extracted online through two processes: absorption process and rejection process, through which only the reliable features with high separability are absorbed in the new target model, while the "dangerous" features which may cause interfusion of background patterns are rejected. To minimize the influence of background and keep the temporal continuity of target model, two collaborative models dominant model and continuous model are designed. The proposed learning and generation mechanisms of target model are finally embedded in an adaptive tracking system. Experimental results demonstrate the robust performance of the proposed algorithm under challenging conditions.

show abstract

Section: A Discriminative Feature Selection For Trackingmentioning

confidence: 99%

Online Appearance Model Learning and Generation for Adaptive Visual Tracking

Wang

Qiao

2011

IEEE Trans. Circuits Syst. Video Technol.

View full text Add to dashboard Cite

show abstract

“…[5] combine saliency information with color features to make tracking more robust to changing illumination. [6] use mutual information to track multi-view objects in real time. They use the variance of mutual information to acquire reliable features for tracking by making use of the images of the tracked object in previous frames to refine the target model.…”

Section: Introductionmentioning

confidence: 99%

Adaptive Feature Selection for Object Tracking with Particle Filter

Venkatrayappa

Sidibé

Mériaudeau

et al. 2014

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. Object tracking is an important topic in the field of computer vision. Commonly used color-based trackers are based on a fixed set of color features such as RGB or HSV and, as a result, fail to adapt to changing illumination conditions and background clutter. These drawbacks can be overcome to an extent by using an adaptive framework which selects for each frame of a sequence the features that best discriminate the object from the background. In this paper, we use such an adaptive feature selection method embedded into a particle filter mechanism and show that our tracking method is robust to lighting changes and background distractions. Different experiments also show that the proposed method outperform other approaches.

show abstract

“…A comparison of some of the most important algorithms with the method proposed here is given in Tab. 1 Juengling et al [13] Leung et al [14] Wang et al [26] Farenzena et al [5] …”

Section: State-of-the-artmentioning

confidence: 99%

View Invariant Appearance-Based Person Reidentification Using Fast Online Feature Selection and Score Level Fusion

Eisenbach

Kolarow

Schenk

et al. 2012

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

View full text Add to dashboard Cite

Fast and robust person reidentification is an important task in multi-camera surveillance and automated access control. We present an efficient appearance-based algorithm, able to reidentify a person regardless of occlusions, distance to the camera, and changes in view and lighting. The use of fast online feature selection techniques enables us to perform reidentification in hyper-real-time for a multicamera system, by taking only 10 seconds for evaluating 100 minutes of HD-video data. We demonstrate, that our approach surpasses current appearance-based state-of-theart in reidentification quality and computational speed and sets a new reference in non-biometric reidentification.

show abstract

Online Feature Selection Using Mutual Information for Real-Time Multi-view Object Tracking

Cited by 9 publications

References 20 publications

Online Appearance Model Learning and Generation for Adaptive Visual Tracking

Online Appearance Model Learning and Generation for Adaptive Visual Tracking

Adaptive Feature Selection for Object Tracking with Particle Filter

View Invariant Appearance-Based Person Reidentification Using Fast Online Feature Selection and Score Level Fusion

Contact Info

Product

Resources

About