Event Retrieval Using Motion Barcodes
Gil Ben-Artzi, Michael Werman, Shmuel Peleg

TL;DR
This paper presents a novel motion barcode feature for video event retrieval that is invariant to viewpoint changes, enabling effective matching of videos captured from different angles despite appearance variations.
Contribution
The paper introduces a simple pixel-based motion barcode feature and a new similarity measure for robust event retrieval across diverse viewpoints.
Findings
Motion barcode is viewpoint invariant and robust to occlusions.
The method outperforms appearance-based approaches in challenging viewpoint scenarios.
Efficient computation enables practical application in real-world videos.
Abstract
We introduce a simple and effective method for retrieval of videos showing a specific event, even when the videos of that event were captured from significantly different viewpoints. Appearance-based methods fail in such cases, as appearances change with large changes of viewpoints. Our method is based on a pixel-based feature, "motion barcode", which records the existence/non-existence of motion as a function of time. While appearance, motion magnitude, and motion direction can vary greatly between disparate viewpoints, the existence of motion is viewpoint invariant. Based on the motion barcode, a similarity measure is developed for videos of the same event taken from very different viewpoints. This measure is robust to occlusions common under different viewpoints, and can be computed efficiently. Event retrieval is demonstrated using challenging videos from stationary and hand…
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.
Taxonomy
TopicsAdvanced Image and Video Retrieval Techniques · Video Analysis and Summarization · Video Surveillance and Tracking Methods
