LV-FeatEx: Large Viewpoint-Image Feature Extraction

Maintaining stable image feature extraction under viewpoint changes is challenging, particularly when the angle between the camera’s reverse direction and the object’s surface normal exceeds 40 degrees. Such conditions can result in unreliable feature detection. Consequently, this hinders the perfor...

Full description

Saved in:
Bibliographic Details
Main Authors: Yukai Wang, Yinghui Wang, Wenzhuo Li, Yanxing Liang, Liangyi Huang, Xiaojuan Ning
Format: Article
Language:English
Published: MDPI AG 2025-03-01
Series:Mathematics
Subjects:
Online Access:https://www.mdpi.com/2227-7390/13/7/1111
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849730320607215616
author Yukai Wang
Yinghui Wang
Wenzhuo Li
Yanxing Liang
Liangyi Huang
Xiaojuan Ning
author_facet Yukai Wang
Yinghui Wang
Wenzhuo Li
Yanxing Liang
Liangyi Huang
Xiaojuan Ning
author_sort Yukai Wang
collection DOAJ
description Maintaining stable image feature extraction under viewpoint changes is challenging, particularly when the angle between the camera’s reverse direction and the object’s surface normal exceeds 40 degrees. Such conditions can result in unreliable feature detection. Consequently, this hinders the performance of vision-based systems. To address this, we propose a feature point extraction method named Large Viewpoint Feature Extraction (LV-FeatEx). Firstly, the method uses a dual-threshold approach based on image grayscale histograms and Kapur’s maximum entropy to constrain the AGAST (Adaptive and Generic Accelerated Segment Test) feature detector. Combined with the FREAK (Fast Retina Keypoint) descriptor, the method enables more effective estimation of camera motion parameters. Next, we design a longitude sampling strategy to create a sparser affine simulation model. Meanwhile, images undergo perspective transformation based on the camera motion parameters. This improves operational efficiency and aligns perspective distortions between two images, enhancing feature point extraction accuracy under large viewpoints. Finally, we verify the stability of the extracted feature points through feature point matching. Comprehensive experimental results show that, under large viewpoint changes, our method outperforms popular classical and deep learning feature extraction methods. The correct rate of feature point matching improves by an average of 40.1 percent, and speed increases by an average of 6.67 times simultaneously.
format Article
id doaj-art-5ad25e1faef3471585995d92b15fab3a
institution DOAJ
issn 2227-7390
language English
publishDate 2025-03-01
publisher MDPI AG
record_format Article
series Mathematics
spelling doaj-art-5ad25e1faef3471585995d92b15fab3a2025-08-20T03:08:55ZengMDPI AGMathematics2227-73902025-03-01137111110.3390/math13071111LV-FeatEx: Large Viewpoint-Image Feature ExtractionYukai Wang0Yinghui Wang1Wenzhuo Li2Yanxing Liang3Liangyi Huang4Xiaojuan Ning5School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi 214122, ChinaSchool of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi 214122, ChinaSchool of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi 214122, ChinaSchool of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi 214122, ChinaSchool of Computing and Augmented Intelligence, Arizona State University, Tempe, AZ 85281, USADepartment of Computer Science & Engineering, Xi’an University of Technology, Xi’an 710048, ChinaMaintaining stable image feature extraction under viewpoint changes is challenging, particularly when the angle between the camera’s reverse direction and the object’s surface normal exceeds 40 degrees. Such conditions can result in unreliable feature detection. Consequently, this hinders the performance of vision-based systems. To address this, we propose a feature point extraction method named Large Viewpoint Feature Extraction (LV-FeatEx). Firstly, the method uses a dual-threshold approach based on image grayscale histograms and Kapur’s maximum entropy to constrain the AGAST (Adaptive and Generic Accelerated Segment Test) feature detector. Combined with the FREAK (Fast Retina Keypoint) descriptor, the method enables more effective estimation of camera motion parameters. Next, we design a longitude sampling strategy to create a sparser affine simulation model. Meanwhile, images undergo perspective transformation based on the camera motion parameters. This improves operational efficiency and aligns perspective distortions between two images, enhancing feature point extraction accuracy under large viewpoints. Finally, we verify the stability of the extracted feature points through feature point matching. Comprehensive experimental results show that, under large viewpoint changes, our method outperforms popular classical and deep learning feature extraction methods. The correct rate of feature point matching improves by an average of 40.1 percent, and speed increases by an average of 6.67 times simultaneously.https://www.mdpi.com/2227-7390/13/7/1111feature pointslarge viewpointASIFTAGASTFREAK
spellingShingle Yukai Wang
Yinghui Wang
Wenzhuo Li
Yanxing Liang
Liangyi Huang
Xiaojuan Ning
LV-FeatEx: Large Viewpoint-Image Feature Extraction
Mathematics
feature points
large viewpoint
ASIFT
AGAST
FREAK
title LV-FeatEx: Large Viewpoint-Image Feature Extraction
title_full LV-FeatEx: Large Viewpoint-Image Feature Extraction
title_fullStr LV-FeatEx: Large Viewpoint-Image Feature Extraction
title_full_unstemmed LV-FeatEx: Large Viewpoint-Image Feature Extraction
title_short LV-FeatEx: Large Viewpoint-Image Feature Extraction
title_sort lv featex large viewpoint image feature extraction
topic feature points
large viewpoint
ASIFT
AGAST
FREAK
url https://www.mdpi.com/2227-7390/13/7/1111
work_keys_str_mv AT yukaiwang lvfeatexlargeviewpointimagefeatureextraction
AT yinghuiwang lvfeatexlargeviewpointimagefeatureextraction
AT wenzhuoli lvfeatexlargeviewpointimagefeatureextraction
AT yanxingliang lvfeatexlargeviewpointimagefeatureextraction
AT liangyihuang lvfeatexlargeviewpointimagefeatureextraction
AT xiaojuanning lvfeatexlargeviewpointimagefeatureextraction