Tracking the Untrackable: How to Track When Your Object Is Featureless
Lebeda, Karel, Matas, Jiri and Bowden, Richard (2013) Tracking the Untrackable: How to Track When Your Object Is Featureless In: ACCV workshop on Detection and Tracking in Challenging Environments, 5-9 November 2012, Daejeon, South Korea.
Download (1MB) | Preview
We propose a novel approach to tracking objects by low-level line correspondences. In our implementation we show that this approach is usable even when tracking objects with lack of texture, exploiting situations, when feature-based trackers fails due to the aperture problem. Furthermore, we suggest an approach to failure detection and recovery to maintain long-term stability. This is achieved by remembering configurations which lead to good pose estimations and using them later for tracking corrections. We carried out experiments on several sequences of different types. The proposed tracker proves itself as competitive or superior to state-of-the-art trackers in both standard and low-textured scenes.
|Item Type:||Conference or Workshop Item (Conference Paper)|
|Divisions :||Faculty of Engineering and Physical Sciences > Electronic Engineering > Centre for Vision Speech and Signal Processing|
|Identification Number :||https://doi.org/10.1007/978-3-642-37484-5_29|
|Projects :||SGS11/125/OHK3/2T/13, GACR P103/12/2310, EPSRC EP/I011811/1|
|Uncontrolled Keywords :||computer vision, tracking, featureless object, low texture, edge, line correspondences|
|Additional Information :||The original publication is available at http://www.springerlink.com|
|Depositing User :||Karel Lebeda|
|Date Deposited :||11 Feb 2015 14:07|
|Last Modified :||11 Feb 2015 14:07|
Actions (login required)
Downloads per month over past year