Beyond Standard Benchmarks: Parameterizing Performance Evaluation in Visual Object Tracking

Object-to-camera motion produces a variety of apparent motion patterns that significantly affect performance of short-term visual trackers. Despite being crucial for designing robust trackers, their influence is poorly explored in standard benchmarks due to weakly defined, biased and overlapping att...

Full description

Saved in:
Bibliographic Details
Main Authors: Zajc, Luka Cehovin, Lukezic, Alan, Leonardis, Ales, Kristan, Matej
Format: Conference Proceeding
Language:English
Subjects:
Benchmark testing
Cameras
Target tracking
Videos
Visualization
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Object-to-camera motion produces a variety of apparent motion patterns that significantly affect performance of short-term visual trackers. Despite being crucial for designing robust trackers, their influence is poorly explored in standard benchmarks due to weakly defined, biased and overlapping attribute annotations. In this paper we propose to go beyond pre-recorded benchmarks with post-hoc annotations by presenting an approach that utilizes omnidirectional videos to generate realistic, consistently annotated, short-term tracking scenarios with exactly parameterized motion patterns. We have created an evaluation system, constructed a fully annotated dataset of omnidirectional videos and generators for typical motion patterns. We provide an in-depth analysis of major tracking paradigms which is complementary to the standard benchmarks and confirms the expressiveness of our evaluation approach.
ISSN:2380-7504
DOI:10.1109/ICCV.2017.360