The Benefits of Evaluating Tracker Performance Using Pixel-Wise Segmentations
Tobias Bottger, Patrick Follmann; Proceedings of the IEEE International Conference on Computer Vision (ICCV), 2017, pp. 1983-1991
Abstract
For years, the ground truth data for evaluating object trackers consists of axis-aligned or oriented boxes. This greatly reduces the workload of labeling the datasets in the common benchmarks. Nevertheless, boxes are a very coarse approximation of an object and the approximation by a box has a large degree of ambiguity. Furthermore, tracking approaches that are not restricted to boxes cannot be evaluated within the benchmarks without adding a penalty to them. We present a simple extension to the VOT evaluation procedure that enables to include these approaches. Furthermore, we present upper bounds for trackers restricted to boxes. Moreover, we present a new measure that captures how well an approach can cope with scale changes without the need of frame-wise labels. We present a learning-based approach which helps to identify frames with heavy occlusion automatically. The framework is tested on the segmentations of the VOT2016 dataset.
Related Material
[pdf]
[
bibtex]
@InProceedings{Bottger_2017_ICCV,
author = {Bottger, Tobias and Follmann, Patrick},
title = {The Benefits of Evaluating Tracker Performance Using Pixel-Wise Segmentations},
booktitle = {Proceedings of the IEEE International Conference on Computer Vision (ICCV) Workshops},
month = {Oct},
year = {2017}
}