Online object tracking with proposal selection

Yang Hua, Karteek Alahari, Cordelia Schmid

Research output: Chapter in Book/Report/Conference proceedingConference contribution

78 Citations (Scopus)
132 Downloads (Pure)

Abstract

Tracking-by-detection approaches are some of the most successful object trackers in recent years. Their success is largely determined by the detector model they learn initially and then update over time. However, under challenging conditions where an object can undergo transformations, e.g., severe rotation, these methods are found to be lacking. In this paper, we address this problem by formulating it as a proposal selection task and making two contributions. The first one is introducing novel proposals estimated from the geometric transformations undergone by the object, and building a rich candidate set for predicting the object location. The second one is devising a novel selection strategy using multiple cues, i.e., detection score and edgeness score computed from state-of-the-art object edges and motion boundaries. We extensively evaluate our approach on the visual object tracking 2014 challenge and online tracking benchmark datasets, and show the best performance.
Original languageEnglish
Title of host publicationProceedings of the IEEE International Conference on Computer Vision
Publisher IEEE
Pages3092-3100
Number of pages9
Publication statusPublished - 2015

Fingerprint

Dive into the research topics of 'Online object tracking with proposal selection'. Together they form a unique fingerprint.

Cite this