Robust Online Appearance Models for Visual Tracking_OldClassical.pdf

Robust Online Appearance Models for Visual Tracking_OldClassical.pdf

Info icon This preview shows pages 1–2. Sign up to view the full content.

View Full Document Right Arrow Icon
Robust Online Appearance Models for Visual Tracking Allan D. Jepson, Member , IEEE Computer Society , David J. Fleet, Member , IEEE Computer Society , and Thomas F. El-Maraghi, Member , IEEE Computer Society Abstract —We propose a framework for learning robust, adaptive, appearance models to be used for motion-based tracking of natural objects. The model adapts to slowly changing appearance, and it maintains a natural measure of the stability of the observed image structure during tracking. By identifying stable properties of appearance, we can weight them more heavily for motion estimation, while less stable properties can be proportionately downweighted. The appearance model involves a mixture of stable image structure, learned over long time courses, along with two-frame motion information and an outlier process. An online EM-algorithm is used to adapt the appearance model parameters over time. An implementation of this approach is developed for an appearance model based on the filter responses from a steerable pyramid. This model is used in a motion-based tracking algorithm to provide robustness in the face of image outliers, such as those caused by occlusions, while adapting to natural changes in appearance such as those due to facial expressions or variations in 3D pose. Index Terms —Motion, optical flow, tracking, occlusion, EM algorithm, adaptive appearance models. æ 1 I NTRODUCTION O NE of the main factors that limits the performance of visual tracking algorithms is the lack of suitable appearance models. This is true of template-matching methods that do not adapt to appearance changes, and it is true of motion-based tracking where the appearance model can change rapidly, allowing models to drift away from targets. This paper proposes a robust, adaptive appearance model for motion-based tracking of complex natural objects. The model adapts to slowly changing appearance, and it maintains a natural measure of the stability of the observed image structure during tracking. By identifying stable properties of appearance, we can weight them more heavily for motion estimation, while less stable properties can be proportionately downweighted. The generative model for appearance is formulated as a mixture of three components, namely, a stable component that is learned with a relatively long time-course, a two- frame transient component, and an outlier process. The stable component adapts to slowly varying properties of image appearance, thereby encoding properties that remain reasonably stable over long time frames. This allows the stable model to identify the most reliable structure for motion estimation, while the two-frame constraints provide additional information when the appearance model is being initialized or when appearance is changing too quickly compared to the slow adaptation of the stable component.
Image of page 1

Info icon This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document Right Arrow Icon
Image of page 2
This is the end of the preview. Sign up to access the rest of the document.

{[ snackBarMessage ]}

What students are saying

  • Left Quote Icon

    As a current student on this bumpy collegiate pathway, I stumbled upon Course Hero, where I can find study resources for nearly all my courses, get online help from tutors 24/7, and even share my old projects, papers, and lecture notes with other students.

    Student Picture

    Kiran Temple University Fox School of Business ‘17, Course Hero Intern

  • Left Quote Icon

    I cannot even describe how much Course Hero helped me this summer. It’s truly become something I can always rely on and help me. In the end, I was not only able to survive summer classes, but I was able to thrive thanks to Course Hero.

    Student Picture

    Dana University of Pennsylvania ‘17, Course Hero Intern

  • Left Quote Icon

    The ability to access any university’s resources through Course Hero proved invaluable in my case. I was behind on Tulane coursework and actually used UCLA’s materials to help me move forward and get everything together on time.

    Student Picture

    Jill Tulane University ‘16, Course Hero Intern