Share Email Print

Proceedings Paper

Multi-scale HOG feature used in object detection
Author(s): Jin Li; Hong Zhang; Lei Zhang; Yawei Li; Qiaochu Kang; Yujie Wu
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Object detection is one of the most popular and difficult field in computer vision. Although deep learning methods have great performance on object detection. For specific application, algorithms which use hand-crafted features are still widely used. One main problem in object detection is the scale problem. Algorithms usually use image pyramid to cover as many scales as possible. But gaps still exist between scale levels in image pyramid. Our work extends some sub scale level to fill the gaps between image pyramids. To this end, we use Gaussian Scales Pyramid to generate sub-scale image and extract HOG feature on the sub-scale. We use framework offered by DPM algorithm and make modification on it. We compare the result of our method with DPM baseline on Pascal VOC database. Our work has great performance on some categories and makes an improvement on the overall performance. This work can be used in other object detection frameworks. We apply multi-scale HOG feature on pre-process procedure of our own detection framework and test it on our own dataset. Then the framework gains performance improvement on precision and recall rate of the pre-process procedure comparing to the original HOG feature architecture.

Paper Details

Date Published: 6 May 2019
PDF: 7 pages
Proc. SPIE 11069, Tenth International Conference on Graphics and Image Processing (ICGIP 2018), 110693U (6 May 2019); doi: 10.1117/12.2524169
Show Author Affiliations
Jin Li, Beihang Univ. (China)
Hong Zhang, Beihang Univ. (China)
Lei Zhang, Beihang Univ. (China)
Yawei Li, Beihang Univ. (China)
Qiaochu Kang, Univ. of Massachusetts Amherst (United States)
Yujie Wu, Beihang Univ. (China)

Published in SPIE Proceedings Vol. 11069:
Tenth International Conference on Graphics and Image Processing (ICGIP 2018)
Chunming Li; Hui Yu; Zhigeng Pan; Yifei Pu, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?