Analysis and a solution of momentarily missed detection for anchor-based object detectors

研究成果: Conference contribution

1 被引用数 (Scopus)

抄録

The employment of convolutional neural networks has led to significant performance improvement on the task of object detection. However, when applying existing detectors to continuous frames in a video, we often encounter momentary miss-detection of objects, that is, objects are undetected exceptionally at a few frames, although they are correctly detected at all other frames. In this paper, we analyze the mechanism of how such miss-detection occurs. For the most popular class of detectors that are based on anchor boxes, we show the followings: i) besides apparent causes such as motion blur, occlusions, background clutters, etc., the majority of remaining miss-detection can be explained by an improper behavior of the detectors at boundaries of the anchor boxes; and ii) this can be rectified by improving the way of choosing positive samples from candidate anchor boxes when training the detectors.

本文言語English
ホスト出版物のタイトルProceedings - 2020 IEEE Winter Conference on Applications of Computer Vision, WACV 2020
出版社Institute of Electrical and Electronics Engineers Inc.
ページ1399-1407
ページ数9
ISBN(電子版)9781728165530
DOI
出版ステータスPublished - 2020 3
イベント2020 IEEE/CVF Winter Conference on Applications of Computer Vision, WACV 2020 - Snowmass Village, United States
継続期間: 2020 3 12020 3 5

出版物シリーズ

名前Proceedings - 2020 IEEE Winter Conference on Applications of Computer Vision, WACV 2020

Conference

Conference2020 IEEE/CVF Winter Conference on Applications of Computer Vision, WACV 2020
国/地域United States
CitySnowmass Village
Period20/3/120/3/5

ASJC Scopus subject areas

  • コンピュータ サイエンスの応用
  • コンピュータ ビジョンおよびパターン認識

フィンガープリント

「Analysis and a solution of momentarily missed detection for anchor-based object detectors」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル