Share Email Print
cover

Proceedings Paper

Object direction estimation by Constrained Convolutional Neural Network
Author(s): Jin Liu; Chuxuan Luo; Fang Gao
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

We propose Constrained Convolutional Neural Network, a novel approach to estimate the direction of numerous target objects. Considering adding a constrained layer at the output of existing object detection networks, by which CCNN performs better in both accuracy and speed than previous neural networks as it works with filtered data, and obtains a more precise result. In object direction estimation, by means of constraint structures, forward and backward propagation algorithms redesigned for the quaternions which describe the 3D pose of the object, CCNN can be further applied to 3D pose estimation. Experiments show that CCNN is feasible for object direction detection and 3D pose estimation, and outperforms conventional neural networks without unitized constrained layer.

Paper Details

Date Published: 14 February 2020
PDF: 11 pages
Proc. SPIE 11430, MIPPR 2019: Pattern Recognition and Computer Vision, 1143024 (14 February 2020); doi: 10.1117/12.2541936
Show Author Affiliations
Jin Liu, Wuhan Univ. (China)
Chuxuan Luo, Wuhan Univ. (China)
Fang Gao, Wuhan Univ. (China)


Published in SPIE Proceedings Vol. 11430:
MIPPR 2019: Pattern Recognition and Computer Vision
Nong Sang; Jayaram K. Udupa; Yuehuan Wang; Zhenbing Liu, Editor(s)

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