Sorry, you need to enable JavaScript to visit this website.

facebooktwittermailshare

KPSNET: KEYPOINT DETECTION AND FEATURE EXTRACTION FOR POINT CLOUD REGISTRATION

Abstract: 

This paper presents the KPSNet, a KeyPoint Siamese Network to simultaneously learn task-desirable keypoint detector and feature extractor. The keypoint detector is optimized to predict a score vector, which signifies the probability of each candidate being a keypoint. The feature extractor is optimized to learn robust features of keypoints by exploiting the correspondence between the keypoints generated from two inputs, respectively. For training, the KPSNet does not require to manually annotate keypoints and local patches pairwise. Instead, we design an alignment module to establish the correspondence between the two inputs and generate positive and negative samples on-the-fly. Therefore, our method can be easily extended to new scenes. We test the proposed method on the open-source benchmark and experiments show the validity of our method.

up
0 users have voted:

Paper Details

Authors:
Xiaoshui Huang, Jian Zhang, Lingxiang Yao, Qiang Wu
Submitted On:
16 September 2019 - 9:58pm
Short Link:
Type:
Poster
Event:
Presenter's Name:
Anan DU
Paper Code:
3546
Document Year:
2019
Cite

Document Files

ICIP.pdf

(13)

Subscribe

[1] Xiaoshui Huang, Jian Zhang, Lingxiang Yao, Qiang Wu, "KPSNET: KEYPOINT DETECTION AND FEATURE EXTRACTION FOR POINT CLOUD REGISTRATION", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4648. Accessed: Oct. 20, 2019.
@article{4648-19,
url = {http://sigport.org/4648},
author = {Xiaoshui Huang; Jian Zhang; Lingxiang Yao; Qiang Wu },
publisher = {IEEE SigPort},
title = {KPSNET: KEYPOINT DETECTION AND FEATURE EXTRACTION FOR POINT CLOUD REGISTRATION},
year = {2019} }
TY - EJOUR
T1 - KPSNET: KEYPOINT DETECTION AND FEATURE EXTRACTION FOR POINT CLOUD REGISTRATION
AU - Xiaoshui Huang; Jian Zhang; Lingxiang Yao; Qiang Wu
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4648
ER -
Xiaoshui Huang, Jian Zhang, Lingxiang Yao, Qiang Wu. (2019). KPSNET: KEYPOINT DETECTION AND FEATURE EXTRACTION FOR POINT CLOUD REGISTRATION. IEEE SigPort. http://sigport.org/4648
Xiaoshui Huang, Jian Zhang, Lingxiang Yao, Qiang Wu, 2019. KPSNET: KEYPOINT DETECTION AND FEATURE EXTRACTION FOR POINT CLOUD REGISTRATION. Available at: http://sigport.org/4648.
Xiaoshui Huang, Jian Zhang, Lingxiang Yao, Qiang Wu. (2019). "KPSNET: KEYPOINT DETECTION AND FEATURE EXTRACTION FOR POINT CLOUD REGISTRATION." Web.
1. Xiaoshui Huang, Jian Zhang, Lingxiang Yao, Qiang Wu. KPSNET: KEYPOINT DETECTION AND FEATURE EXTRACTION FOR POINT CLOUD REGISTRATION [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4648