Line-Based Global Localization of a Spherical Camera in Manhattan Worlds

Goto, Tsubasa; Pathak, Sarthak; Ji, Yonghoon; Fujii, Hiromitsu; Yamashita, Atsushi; Asama, Hajime

doi:10.1109/icra.2018.8460920

Cited by 14 publications

(8 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Both data are structured environments including 3D parallel lines, which is the prerequisite for the vanishing direction matching. It should be noticed that the proposed method works with the assumption of a large overlap between point clouds and images, which is consistent with the condition of previous methods [4], [8], [16].…”

Section: Methodssupporting

confidence: 86%

See 1 more Smart Citation

Line-based Camera Pose Estimation in Point Cloud of Structured Environments

Yu¹,

Zhen²,

Wen³

et al. 2019

Preprint

View full text Add to dashboard Cite

Accurate registration of 2D imagery with point clouds is a key technology for image-LiDAR point cloud fusion, camera to laser scanner calibration and camera localization. Despite continuous improvements, automatic registration of 2D and 3D data without using additional textured information still faces great challenges. In this paper, we propose a new 2D-3D registration method to estimate 2D-3D line feature correspondences and the camera pose in untextured point clouds of structured environments. Specifically, we first use geometric constraints between vanishing points and 3D parallel lines to compute all feasible camera rotations. Then, we utilize a hypothesis testing strategy to estimate the 2D-3D line correspondences and the translation vector. By checking the consistency with computed correspondences, the best rotation matrix can be found. Finally, the camera pose is further refined using nonlinear optimization with all the 2D-3D line correspondences. The experimental results demonstrate the effectiveness of the proposed method on the synthetic and real dataset (outdoors and indoors) with repeated structures and rapid depth changes.

show abstract

Section: Methodssupporting

confidence: 86%

“…The modality differences and description gaps make the common image registration methods fail to get correspondences. Fortunately, 2D images share some geometric consistent features with point clouds, such as line segments and planes [8]. Thus we can use geometric cooccurrence to find these feature correspondences.…”

Section: Introductionmentioning

confidence: 99%

Line-based Camera Pose Estimation in Point Cloud of Structured Environments

Yu¹,

Zhen²,

Wen³

et al. 2019

Preprint

View full text Add to dashboard Cite

show abstract

“…Additionally, nowadays cameras are essential parts of smartphones, which further corroborates the feasibility of vision based localization technologies [7]. Therefore, VLP and computer vision based localization have been gained increasing attentions in recent years [7], [8].…”

Section: Introductionmentioning

confidence: 85%

“…However, PnL methods need 3D-2D correspondences which are difficult to obtain. In existing PnL studies, the 3D-2D correspondences assumed to be perfectly known in advance [22], [25], which is impractical in practice [8]. To circumvent this challenge, the work in [8] proposed a method to find the 3D-2D correspondences for the scenario where the number of the vertical lines are more than that of horizontal lines.…”

Section: Introductionmentioning

confidence: 99%

Novel Visible Light Communication Assisted Perspective-Four-Line Algorithm for Indoor Localization

Bai

2020

Preprint

View full text Add to dashboard Cite

In this paper, we propose a novel visible light communication (VLC) assisted Perspective-four-Line algorithm (V-P4L) for practical indoor localization. The basic idea of V-P4L is to joint VLC and computer vision to achieve high accuracy regardless of LED height differences. In particular, we first exploit the space-domain information to estimate the orientation and coordinate of a single rectangular LED luminaire in the camera coordinate system based on the plane and solid geometry. Then, based on the time-domain information transmitted by VLC and the estimated luminaire information, V-P4L can estimate the position and pose of the camera by the single-view geometry theory and the linear least square (LLS) method. To further mitigate the effect of height differences among LEDs on localization accuracy, we then propose a correction algorithm of V-P4L based on the LLS method and a simple optimization method. Due to the combination of time-and space-domain information, V-P4L only requires a single luminaire for localization without limitation on the correspondences between the features and their projections. Simulation results show that for V-P4L the position error is always less than 15 cm and the orientation error is always less than 3 • using popular indoor luminaires.

show abstract

“…Furthermore, vision-based systems might fail in cases in which feature points cannot be computed due to a blocked view caused by the system facing a wall, corner or an object. To solve the blocked view problem, cameras with a large field of view (FOV) have been used for indoor localization using different techniques, such as matching 2D lines extracted from a spherical image to a line descriptor map under the Manhattan world assumption [10] and matching scale-invariant feature transform (SIFT) features to a built image database [11]. Although these approaches are highly accurate and can manage possible view blockages, the amount of computation and storage required for matching large amounts of 3D point clouds or feature points can be too demanding for a small mobile or portable system with limited resources.…”

Section: Introductionmentioning

confidence: 99%

Robust and Efficient Indoor Localization Using Sparse Semantic Information from a Spherical Camera

Uygur

Miyagusuku

Pathak

et al. 2020

Sensors

Self Cite

View full text Add to dashboard Cite

Self-localization enables a system to navigate and interact with its environment. In this study, we propose a novel sparse semantic self-localization approach for robust and efficient indoor localization. “Sparse semantic” refers to the detection of sparsely distributed objects such as doors and windows. We use sparse semantic information to self-localize on a human-readable 2D annotated map in the sensor model. Thus, compared to previous works using point clouds or other dense and large data structures, our work uses a small amount of sparse semantic information, which efficiently reduces uncertainty in real-time localization. Unlike complex 3D constructions, the annotated map required by our method can be easily prepared by marking the approximate centers of the annotated objects on a 2D map. Our approach is robust to the partial obstruction of views and geometrical errors on the map. The localization is performed using low-cost lightweight sensors, an inertial measurement unit and a spherical camera. We conducted experiments to show the feasibility and robustness of our approach.

show abstract

Line-Based Global Localization of a Spherical Camera in Manhattan Worlds

Cited by 14 publications

References 15 publications

Line-based Camera Pose Estimation in Point Cloud of Structured Environments

Line-based Camera Pose Estimation in Point Cloud of Structured Environments

Novel Visible Light Communication Assisted Perspective-Four-Line Algorithm for Indoor Localization

Robust and Efficient Indoor Localization Using Sparse Semantic Information from a Spherical Camera

Contact Info

Product

Resources

About