Depth Masked Discriminative Correlation Filter
U\u{g}ur Kart, Joni-Kristian K\"am\"ar\"ainen, Ji\v{r}\'i Matas, Lixin, Fan, Francesco Cricri

TL;DR
This paper introduces DM-DCF, a depth-aware object tracking method that uses depth segmentation for occlusion detection and adaptive masking, achieving state-of-the-art accuracy and high speed on RGBD benchmarks.
Contribution
The paper presents a novel depth masked discriminative correlation filter that incorporates depth segmentation for occlusion handling and adaptive spatial support adjustment.
Findings
Achieves top overall ranking on Princeton RGBD Tracking Benchmark.
Outperforms competitors in multiple categories.
Runs an order of magnitude faster than existing methods.
Abstract
Depth information provides a strong cue for occlusion detection and handling, but has been largely omitted in generic object tracking until recently due to lack of suitable benchmark datasets and applications. In this work, we propose a Depth Masked Discriminative Correlation Filter (DM-DCF) which adopts novel depth segmentation based occlusion detection that stops correlation filter updating and depth masking which adaptively adjusts the spatial support for correlation filter. In Princeton RGBD Tracking Benchmark, our DM-DCF is among the state-of-the-art in overall ranking and the winner on multiple categories. Moreover, since it is based on DCF, ``DM-DCF`` runs an order of magnitude faster than its competitors making it suitable for time constrained applications.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
