Fast Line Description for Line-based SLAM

Hirose, Keikichi; Saitō, Hideo

doi:10.5244/c.26.83

Cited by 43 publications

(24 citation statements)

References 22 publications

(24 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Figure 4-(a, c, e, g, i, k) are obtained by our method, meanwhile Fig. 4-(b, d, f, h, j, l) are by LEHF [13]. It is clear that our method can not detect many corresponding line segments, but it achieves higher matching accuracy than that of LEHF.…”

Section: The Matching Resultsmentioning

confidence: 97%

See 1 more Smart Citation

Line-Based SLAM Using Non-Overlapping Cameras in an Urban Environment

Kawasaki

Hara

Saitō

2018

IEICE Trans. Inf. & Syst.

Self Cite

View full text Add to dashboard Cite

SUMMARYWe propose a method of line-based Simultaneous Localization and Mapping (SLAM) using non-overlapping multiple cameras for vehicles running in an urban environment. It uses corresponding line segments between images taken by different frames and different cameras. The contribution is a novel line segment matching algorithm by warping processing based on urban structures. This idea significantly improves the accuracy of line segment matching when viewing direction are very different, so that a number of correspondences between front-view and rear-view cameras can be found and the accuracy of SLAM can be improved. Additionally, to enhance the accuracy of SLAM we apply a geometrical constraint of urban area for initial estimation of 3D mapping of line segments and optimization by bundle adjustment. We can further improve the accuracy of SLAM by combining points and lines. The position error is stable within 1.5m for the entire image dataset evaluated in this paper. The estimation accuracy of our method is as high as that of ground truth captured by RTK-GPS. Our high accuracy SLAM algorithm can be apply for generating a road map represented by line segments. According to an evaluation of our generating map, true positive rate around the vehicle exceeding 70% is achieved.

show abstract

Section: The Matching Resultsmentioning

confidence: 97%

“…They detected lines by checking if Sobeldetected edges exist between two corners or not. Hirose et al [13] proposed a novel descriptor of line segment features for line-based SLAM. Many other researches on SLAM combine lines and other features.…”

Section: Related Workmentioning

confidence: 99%

Line-Based SLAM Using Non-Overlapping Cameras in an Urban Environment

Kawasaki

Hara

Saitō

2018

IEICE Trans. Inf. & Syst.

Self Cite

View full text Add to dashboard Cite

show abstract

“…SLAM approaches are designed to perform pose estimation and sparse 3D reconstruction simultaneously in previously unknown environments. While traditional SLAM methods are based on interest point features, it has been shown that incorporating line segments produces more accurate results for urban environments [3,4,9]. Even though these approaches are in a way related to the proposed method, they focus more on fast localisation than on generating accurate and complete 3D line models of the scene.…”

Section: Related Workmentioning

confidence: 99%

“…To match two line segments from different views, an appearance-based similarity measure has to be applied (e.g. normalized-cross-correlation) or line descriptors such as MSLD [15,16] or LEHF [4] have to be used. Since the resulting matching scores are based c 2013.…”

Section: Introductionmentioning

confidence: 99%

Incremental Line-based 3D Reconstruction using Geometric Constraints

Höfer¹,

Wendel²,

Bischof³

2013

Procedings of the British Machine Vision Conference 2013

View full text Add to dashboard Cite

Generating accurate 3D models for man-made environments can be a challenging task due to the presence of texture-less objects or wiry structures. Since traditional point-based 3D reconstruction approaches may fail to integrate these structures into the resulting point cloud, a different feature representation is necessary. We present a novel approach which uses point features for camera estimation and additional line segments for 3D reconstruction. To avoid appearance-based line matching, we use purely geometric constraints for hypothesis generation and verification. Therefore, the proposed method is able to reconstruct both wiry structures as well as solid objects. The algorithm is designed to generate incremental results using online Structure-from-Motion and linebased 3D modelling in parallel. We show that the proposed method outperforms previous descriptor-less line matching approaches in terms of run-time while delivering accurate results.

show abstract

“…Therefore, some existing methods [4][5][6] do not rely on appearance-based line segment matching. However, recently, researches about line segment feature descriptor such as the mean standard-deviation line descriptor (MSLD) [7] or the Line-based Eight-directional Histogram Feature(LEHF) [8] have been reported. With these line segment feature descriptors, line segment based 3D model can be generated in man-made environment.…”

Section: Introductionmentioning

confidence: 99%

3D Line Segment Based Model Generation by RGB-D Camera for Camera Pose Estimation

Nakayama

Saitō

Shimizu

et al. 2015

Computer Vision - ACCV 2014 Workshops

Self Cite

View full text Add to dashboard Cite

Abstract. In this paper, we propose a novel method for generating 3D line segment based model from an image sequence taken with a RGB-D camera. Constructing 3D geometrical representation by 3D model is essential for model based camera pose estimation that can be performed by corresponding 2D features in images with 3D features of the captured scene. While point features are mostly used as such features for conventional camera pose estimation, we aim to use line segment features for improving the performance of the camera pose estimation. In this method, using RGB images and depth images of two continuous frames, 2D line segments from the current frame and 3D line segments from the previous frame are corresponded. The 2D-3D line segment correspondences provide camera pose of the current frame. All of 2D line segments are finally back-projected to the world coordinate based on the estimated camera pose for generating 3D line segment based model of the target scene. In experiments, we confirmed that the proposed method can successfully generate line segment based models, while 3D models based on the point features often fail to successfully represent the target scene.

show abstract

Fast Line Description for Line-based SLAM

Cited by 43 publications

References 22 publications

Line-Based SLAM Using Non-Overlapping Cameras in an Urban Environment

Line-Based SLAM Using Non-Overlapping Cameras in an Urban Environment

Incremental Line-based 3D Reconstruction using Geometric Constraints

3D Line Segment Based Model Generation by RGB-D Camera for Camera Pose Estimation

Contact Info

Product

Resources

About