Long-term object tracking with a moving event camera

Bharath Ramesh, Shihao Zhang, Zhi Wei Lee, Zhi Gao, Garrick Orchard, Cheng Xiang

Research output: Chapter in Book / Conference PaperConference Paperpeer-review

Abstract

![CDATA[This paper presents a long-term object tracking algorithm for event cameras. A first of its kind for these revolutionary cameras, the tracking framework uses a discriminative representation for the object with online learning, and detects and re-tracks the object when it comes back into the field-of-view. One of the key novelties is the use of an event-based local sliding window technique that performs reliably in scenes with cluttered and textured background. In addition, Bayesian bootstrapping is used to assist real-time processing and boost the discriminative power of the object representation. Extensive experiments on a publicly available event camera dataset demonstrates the ability to track and detect arbitrary objects of various shapes and sizes. This is a significant improvement compared to earlier works that simply track objects as long as they are visible under simpler background settings. In other words, when the object re-enters the field-of-view of the camera, a data-driven, global sliding window based detector locates the object under different view-point conditions for subsequent tracking.]]
Original languageEnglish
Title of host publicationProceedings of the 29th British Machine Vision Conference, 3-6 September 2018, Newcastle, UK
PublisherNorthumbria University
Number of pages12
Publication statusPublished - 2018
EventBritish Machine Vision Conference -
Duration: 3 Sept 2018 → …

Conference

ConferenceBritish Machine Vision Conference
Period3/09/18 → …

Keywords

  • cameras
  • algorithms
  • neural networks (computer science)
  • image processing

Fingerprint

Dive into the research topics of 'Long-term object tracking with a moving event camera'. Together they form a unique fingerprint.

Cite this