arrow
返回

Video object detection with a convolutional regression tracker

delete2021-06-01
delete14
delete
OA
AI
L
Lyu, Ye
M
Michael Ying Yang *
G
George Vosselman
G
Gui-Song Xia *
DOI:10.1016/j.isprsjprs.2021.04.004delete
delete原文链接
delete原文求助
delete分享
delete收藏
摘要

摘要

En 中文
Video object detection is a fundamental research task for scene understanding. Compared with object detection in images, object detection in videos has been less researched due to shortage of labelled video datasets. As frames in a video clip are highly correlated, a larger quantity of video labels are needed to have good data variation, which are not always available as the labels are much more expensive to attain. Regarding the above-mentioned problem, it is easy to train an image object detector, but not always possible to train a video object detector if there are insufficient video labels for certain classes. In order to deal with this problem and improve the performance of an image object detector for the classes without video labels, we propose to augment a well-trained image object detector with an efficient and effective class-agnostic convolutional regression tracker for the video object detection task. The tracker learns to track objects by reusing the features from the image object detector, which is a light-weighted increment to the detector, with only a slight speed drop for the video object detection task. The performance of our model is evaluated on the large-scale ImageNet VID dataset. Our strategy improves the mean average precision (mAP) score for the image object detector by around 5% and around 3% for the image object detector plus Seq-NMS post-processing.
Keyword:
Video object detection
Plug & Play
Convolutional regression tracker
Deep learning
Tracking

期刊

ISPRS Journal of Photogrammetry and Remote Sensing 封面图
ISPRS Journal of Photogrammetry and Remote Sensing
IF:
12.2
论文数:
4.4K
被引数:
3.2W

机构

U
university of twente
学者数:
1.5W
论文数: 1.4W
被引数: 9
W
wuhan university
学者数:
8.1W
论文数: 5.8W
被引数: 70
引用论文

引用论文

Conductivity Enhancement in Thin Silicon-on-Insulator Layer Embedding Artificial Dislocation Network
err2011-02-01
err0
PREAI
errYasuhiko Ishikawa; Kazuaki Yamauchi; Chihiro Yamamoto; Michiharu Tabe
err分享
err收藏
err分享
err收藏
Particle size, morphology and phase transitions in hydrothermally produced VO2(D)
err2017-01-01
err0
errOAAI
errDiana Teixeira; Raul Quesada-Cabrera; Michael J. Powell; G. K. L. Goh; G. Sankar; I. P. Parkin; R. G. Palgrave
err分享
err收藏
Synthesis of n-type semiconducting diamond film using diphosphorus pentaoxide as the doping source以五氧化二磷为掺杂源合成n型半导体金刚石膜
err1990-10-01
err0
PREAI
errKen Okano; Hideo Kiyota; Tatsuya Iwasaki; Yoshitaka Nakamura; Yukio Akiba; Tateki Kurosu; Masamori Iida; Terutaro Nakamura
err分享
err收藏
err分享
err收藏
学者 查看更多内容