Feature Point Extraction and Matching Method Based on Akaze in Illumination Invariant Color Space

Xue, Yongyuan

doi:10.1109/icivc50857.2020.9177459

Cited by 6 publications

(4 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Aiming at the impact of illumination changes on feature tracking, ref. [21] used the AKAZE detector to extract feature points after they constructed a color space with constant illumination based on adaptive histogram equalization and dark channel prior theory. This technique increases the accuracy of extracting and matching image feature points in the event of significant changes in illumination.…”

Section: Image Feature Pointmentioning

confidence: 99%

An Improved Visual SLAM Method with Adaptive Feature Extraction

Guo,

Lyu,

Xia

et al. 2023

Applied Sciences

View full text Add to dashboard Cite

The feature point method is the mainstream method to accomplish inter-frame estimation in visual Simultaneous Localization and Mapping (SLAM) methods, among which the Oriented FAST and Rotated BRIEF (ORB) feature-based method provides an equilibrium of accuracy as well as efficiency. However, the ORB algorithm is prone to clustering phenomena, and its unequal distribution of extracted feature points is not conducive to the subsequent camera tracking. To solve the above problems, this paper suggests an adaptive feature extraction algorithm that first constructs multiple-scale images using an adaptive Gaussian pyramid algorithm, calculates adaptive thresholds, and uses an adaptive meshing method for regional feature point detection to adapt to different scenes. The method uses Adaptive and Generic Accelerated Segment Test (AGAST) to speed up feature detection and the non-maximum suppression method to filter feature points. The feature points are then divided equally by a quadtree technique, and the orientation of those points is determined by an intensity centroid approach. Experiments were conducted on publicly available datasets, and the outcomes demonstrate the algorithm has good adaptivity and solves the problem of a large number of corner point clusters that may result from using manually set detection thresholds. The RMSE of the absolute trajectory error of SLAM applying this method on four sequences of TUM RGB-D datasets is decreased by 13.88% when compared with ORB-SLAM3. It is demonstrated that the algorithm provides high-quality feature points for subsequent image alignment, and the application to SLAM improves the reliability and accuracy of SLAM.

show abstract

Section: Image Feature Pointmentioning

confidence: 99%

An Improved Visual SLAM Method with Adaptive Feature Extraction

Guo,

Lyu,

Xia

et al. 2023

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…Song et al constructed a pyramid model with the help of a nonlinear filter, used the fast display diffusion algorithm to obtain a numerical solution, and solved the image coordinates, which gave good robustness in image scale, brightness and rotation [ 36 ]. Y. Xue et al combined histogram equalization and dark channel prior theory to construct a color space with constant illumination, which ensured the amount of feature extraction, matching accuracy and efficiency [ 37 ]. However, due to the characteristics of the FAST algorithm, the corners it extracts have the characteristics of large quantity but low quality.…”

Section: Related Work and System Overviewmentioning

confidence: 99%

An Improved FAST Algorithm Based on Image Edges for Complex Environment

Ding

2022

Sensors

View full text Add to dashboard Cite

In complex environments such as those with low textures or obvious brightness changes, point features extracted from a traditional FAST algorithm cannot perform well in pose estimation. Simultaneously, the number of point features extracted from FAST is too large, which increases the complexity of the build map. To solve these problems, we propose an L-FAST algorithm based on FAST, in order to reduce the number of extracted points and increase their quality. L-FAST pays more attention to the intersection of line elements in the image, which can be extracted directly from the related edge image. Hence, we improved the Canny edge extraction algorithm, including denoising, gradient calculation and adaptive threshold. These improvements aimed to enhance the sharpness of image edges and effectively extract the edges of strong light or dark areas in the images as brightness changed. Experiments on digital standard images showed that our improved Canny algorithm was smoother and more continuous for the edges extracted from images with brightness changes. Experiments on KITTI datasets showed that L-FAST extracted fewer point features and increased the robustness of SLAM.

show abstract

“…By incorporating deep learning methods into traditional SLAM modules, this paper proposes a dense 3D reconstruction algorithm based on optimized accelerated-KAZE (AKAZE) and multi-view loop detection networks. The optimized algorithm uses the optimized AKAZE [21] algorithm to improve the efficiency, accuracy and robustness of feature point extraction. Then the optimized algorithm uses the K-nearest neighbor (KNN) method [22] to optimize the Fast Library for approximate nearest neighbors (FLANN) [23] algorithm for feature matching optimization.…”

Section: Introductionmentioning

confidence: 99%

Realtime 3D reconstruction algorithm based on improved AKAZE and multi-layer feature detection network

Pan,

Hou,

et al. 2024

Meas. Sci. Technol.

View full text Add to dashboard Cite

Simultaneous localization and mapping(SLAM) technology aims to solve the problem of how to determine the trajectory of robots by observing the environment and construct sparse spatial models. And the 3D reconstruction technology can further build dense spatial models based on the pose information. This paper proposes a dense 3D reconstruction algorithm based on improved accelerated-KAZE(AKAZE) features and a multi-layer feature detection network. A multi-layer feature detection neural network is constructed to replace the BoW model and optimize the loopback results, which improves the effect of pose estimation. The optimized algorithm improves the mapping effect and construct clear and robust indoor complex models. The pose estimation results show that the optimized algorithm improves the accuracy by 30% compared with ORB-SLAM2. Compared with the mapping effect of Kintinuous, ElasticFusion, ORB-SLAM2 and BundleFusion, the optimized models own the advantages of clearer details, richer information and no split layer.

show abstract

Feature Point Extraction and Matching Method Based on Akaze in Illumination Invariant Color Space

Cited by 6 publications

References 8 publications

An Improved Visual SLAM Method with Adaptive Feature Extraction

An Improved Visual SLAM Method with Adaptive Feature Extraction

An Improved FAST Algorithm Based on Image Edges for Complex Environment

Realtime 3D reconstruction algorithm based on improved AKAZE and multi-layer feature detection network

Contact Info

Product

Resources

About