A new accurate and fast homography computation algorithm for sports and traffic video analysis
Homography has wide applications in aerial photographic surveys, camera calibration, traffic scene analysis, and sports science, such as player and team performance evaluation. Unlike the mainstream homography that utilizes points as matching features, homography estimation for sports and traffic vi...
Saved in:
Main Authors: | , , , |
---|---|
Other Authors: | |
Format: | Article |
Language: | English |
Published: |
2020
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/142928 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
id |
sg-ntu-dr.10356-142928 |
---|---|
record_format |
dspace |
spelling |
sg-ntu-dr.10356-1429282020-07-14T01:36:10Z A new accurate and fast homography computation algorithm for sports and traffic video analysis Liu, Shumin Chen, Jiajia Chang, Chip-Hong Ai, Ye School of Electrical and Electronic Engineering Engineering::Electrical and electronic engineering Homography Video Processing Homography has wide applications in aerial photographic surveys, camera calibration, traffic scene analysis, and sports science, such as player and team performance evaluation. Unlike the mainstream homography that utilizes points as matching features, homography estimation for sports and traffic video can achieve higher accuracy and speed by utilizing straight lines in the scenes, which convey more information than points. Owing to the more stringent requirement of accuracy and computational speed for advanced video analysis, this paper presents a novel homography computational algorithm. Three major novelties are proposed and validated, which are multiple points Hough transform for straight line extraction, correspondence initialization by angle to estimate a set of quasi-optimal solutions, and the feature correspondences optimization to achieve a minimized error using genetic algorithm. With these contributions, the experiments have shown that the proposed algorithm can improve the homography computational accuracy by up to 130% and reduce the processing time by up to 96% over the state-of-the-art algorithms for the same purposes. 2020-07-14T01:36:10Z 2020-07-14T01:36:10Z 2017 Journal Article Liu, S., Chen, J., Chang, C.-H., & Ai, Y. (2018). A new accurate and fast homography computation algorithm for sports and traffic video analysis. IEEE Transactions on Circuits and Systems for Video Technology, 28(10), 2993-3006. doi:10.1109/TCSVT.2017.2731781 1051-8215 https://hdl.handle.net/10356/142928 10.1109/TCSVT.2017.2731781 2-s2.0-85029891040 10 28 2993 3006 en IEEE Transactions on Circuits and Systems for Video Technology © 2017 IEEE. All rights reserved. |
institution |
Nanyang Technological University |
building |
NTU Library |
country |
Singapore |
collection |
DR-NTU |
language |
English |
topic |
Engineering::Electrical and electronic engineering Homography Video Processing |
spellingShingle |
Engineering::Electrical and electronic engineering Homography Video Processing Liu, Shumin Chen, Jiajia Chang, Chip-Hong Ai, Ye A new accurate and fast homography computation algorithm for sports and traffic video analysis |
description |
Homography has wide applications in aerial photographic surveys, camera calibration, traffic scene analysis, and sports science, such as player and team performance evaluation. Unlike the mainstream homography that utilizes points as matching features, homography estimation for sports and traffic video can achieve higher accuracy and speed by utilizing straight lines in the scenes, which convey more information than points. Owing to the more stringent requirement of accuracy and computational speed for advanced video analysis, this paper presents a novel homography computational algorithm. Three major novelties are proposed and validated, which are multiple points Hough transform for straight line extraction, correspondence initialization by angle to estimate a set of quasi-optimal solutions, and the feature correspondences optimization to achieve a minimized error using genetic algorithm. With these contributions, the experiments have shown that the proposed algorithm can improve the homography computational accuracy by up to 130% and reduce the processing time by up to 96% over the state-of-the-art algorithms for the same purposes. |
author2 |
School of Electrical and Electronic Engineering |
author_facet |
School of Electrical and Electronic Engineering Liu, Shumin Chen, Jiajia Chang, Chip-Hong Ai, Ye |
format |
Article |
author |
Liu, Shumin Chen, Jiajia Chang, Chip-Hong Ai, Ye |
author_sort |
Liu, Shumin |
title |
A new accurate and fast homography computation algorithm for sports and traffic video analysis |
title_short |
A new accurate and fast homography computation algorithm for sports and traffic video analysis |
title_full |
A new accurate and fast homography computation algorithm for sports and traffic video analysis |
title_fullStr |
A new accurate and fast homography computation algorithm for sports and traffic video analysis |
title_full_unstemmed |
A new accurate and fast homography computation algorithm for sports and traffic video analysis |
title_sort |
new accurate and fast homography computation algorithm for sports and traffic video analysis |
publishDate |
2020 |
url |
https://hdl.handle.net/10356/142928 |
_version_ |
1681056614815105024 |