著者
Guan PANG Guijin WANG Xinggang LIN
出版者
The Institute of Electronics, Information and Communication Engineers
雑誌
IEICE TRANSACTIONS on Information and Systems (ISSN:09168532)
巻号頁・発行日
vol.E93-D, no.3, pp.658-661, 2010-03-01

Human detection has witnessed significant development in recent years. The introduction of cascade structure and integral histogram has greatly improved detection speed. But real-time detection is still only possible for sparse scan of 320 240 sized images. In this work, we propose a matrix-based structure to reorganize the computation structure of window-scanning detection algorithms, as well as a new pre-processing method called Hierarchical HOG Matrices (HHM) in place of integral histogram. Our speed-up scheme can process 320 240 sized images by dense scan (≈ 12000 windows per image) at the speed of about 30 fps, while maintaining accuracy comparable to the original HOG + cascade method.

言及状況

Twitter (1 users, 1 posts, 0 favorites)

Real-Time Human Detection Using Hierarchical HOG Matrices. 某氏がやってたのとは少し違う気がするが http://search.ieice.org/bin/summary.php?id=e93-d_3_658

収集済み URL リスト