Semi-Automatic Video Annotation For Object Detection
Year: 2021
Type: preprint
Abstract: In this study, a semi-automatic video annotation method is proposed which utilizes temporal information to eliminate false-positives with a tracking-by-detection approach by employing multiple hypothesis tracking (MHT). MHT method automatically forms tracklets which are confirmed by human operators to enlarge the training set. A novel incremental learning approach helps to annotate videos in an iterative way. The experiments performed on AUTH Multidrone Dataset reveals that the annotation workload can be reduced up to 96% by the proposed approach.
Source: arXiv (Cornell University)
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W3124810097