Search Results - "Li, Haoang"

Combining points and lines for camera pose estimation and optimization in monocular visual odometry by Haoang Li, Jian Yao, Xiaohu Lu, Junlin Wu

“…In this paper, we propose a unified model for camera pose estimation and a novel strategy for pose optimization by combining points and lines in monocular…”
Get full text

LPD-Net: 3D Point Cloud Learning for Large-Scale Place Recognition and Environment Analysis by Liu, Zhe, Zhou, Shunbo, Suo, Chuanzhe, Yin, Peng, Chen, Wen, Wang, Hesheng, Li, Haoang, Liu, Yunhui

“…Point cloud based place recognition is still an open issue due to the difficulty in extracting local features from the raw 3D point cloud and generating the…”
Get full text

Efficient and Robust Point Cloud Registration via Heuristics-Guided Parameter Search by Huang, Tianyu, Li, Haoang, Peng, Liangzu, Liu, Yinlong, Liu, Yun-Hui

“…Estimating the rigid transformation with 6 degrees of freedom based on a putative 3D correspondence set is a crucial procedure in point cloud registration…”
Get full text

Integrated Task Allocation and Path Coordination for Large-Scale Robot Networks With Uncertainties by Liu, Zhe, Wei, Huanshu, Wang, Hongye, Li, Haoang, Wang, Hesheng

“…Artificial intelligence-enhanced autonomous unmanned systems, such as large-scale autonomous robot networks, are widely used in logistic and industrial…”
Get full text

Quasi-Globally Optimal and Real-Time Visual Compass in Manhattan Structured Environments by Kim, Pyojin, Li, Haoang, Joo, Kyungdon

“…We present a drift-free visual compass for estimating the three degrees of freedom (DoF) rotational motion of a camera by recognizing structural regularities…”
Get full text

Hong Kong World: Leveraging Structural Regularity for Line-based SLAM by Li, Haoang, Zhao, Ji, Bazin, Jean-Charles, Kim, Pyojin, Joo, Kyungdon, Zhao, Zhenjun, Liu, Yun-Hui

“…Manhattan and Atlanta worlds hold for the structured scenes with only vertical and horizontal dominant directions (DDs). To describe the scenes with additional…”
Get full text

Leveraging Geometric and Semantic Information for Visual Simultaneous Localization and Mapping by Li, Haoang

“…Simultaneous localization and mapping (SLAM) is a crucial technology for robot navigation, 3Dreconstruction, and virtual/augmented reality. While it has been…”
Get full text

Quasi-Globally Optimal and Near/True Real-Time Vanishing Point Estimation in Manhattan World by Li, Haoang, Zhao, Ji, Bazin, Jean-Charles, Liu, Yun-Hui

“…Image lines projected from parallel 3D lines intersect at a common point called the vanishing point (VP). Manhattan world holds for the scenes with three…”
Get full text

Task-Space Trajectory Tracking Control for Coordinated Manipulation Using Sampled Coupling Data by Liu, Zhe, Chen, Wei, Jin, Kefan, Li, Haoang

“…This letter studies the task-space synchronization control problem of networked manipulators which are commanded to track the desired task-space trajectories…”
Get full text

Optimal seamline detection in dynamic scenes via graph cuts for image mosaicking by Li, Li, Yao, Jian, Li, Haoang, Xia, Menghan, Zhang, Wei

“…In this paper, we present a novel method for creating a seamless mosaic from a set of geometrically aligned images captured from the scene with dynamic objects…”
Get full text

Deterministic Point Cloud Registration via Novel Transformation Decomposition by Chen, Wen, Li, Haoang, Nie, Qiang, Liu, Yun-Hui

“…Given a set of putative 3D-3D point correspondences, we aim to remove outliers and estimate rigid transformation with 6 degrees of freedom (DOF)…”
Get full text

Robust Estimation of Absolute Camera Pose via Intersection Constraint and Flow Consensus by Li, Haoang, Zhao, Ji, Bazin, Jean-Charles, Liu, Yun-Hui

“…Estimating the absolute camera pose requires 3D-to-2D correspondences of points and/or lines. However, in practice, these correspondences are inevitably…”
Get full text

End-to-End 3D Point Cloud Learning for Registration Task Using Virtual Correspondences by Wei, Huanshu, Qiao, Zhijian, Liu, Zhe, Suo, Chuanzhe, Yin, Peng, Shen, Yueling, Li, Haoang, Wang, Hesheng

“…3D Point cloud registration is still a very challenging topic due to the difficulty in finding the rigid transformation between two point clouds with partial…”
Get full text

Deep Learning-Based Localization and Perception Systems: Approaches for Autonomous Cargo Transportation Vehicles in Large-Scale, Semiclosed Environments by Liu, Zhe, Suo, Chuanzhe, Liu, Yingtian, Shen, Yueling, Qiao, Zhijian, Wei, Huanshu, Zhou, Shunbo, Li, Haoang, Liang, Xinwu, Wang, Hesheng, Liu, Yun-Hui

“…Vehicles capable of delivering heavy cargoes are a major means for the promotion of social productivity and are widely applied in industry. Even though…”
Get full text

Learning Accurate 3D Shape Based on Stereo Polarimetric Imaging by Huang, Tianyu, Li, Haoang, He, Kejing, Sui, Congying, Li, Bin, Liu, Yun-Hui

“…Shape from Polarization (SfP) aims to recover surface normal using the polarization cues of light. The accuracy of existing SfP methods is affected by two main…”
Get full text

Learning Icosahedral Spherical Probability Map Based on Bingham Mixture Model for Vanishing Point Estimation by Li, Haoang, Chen, Kai, Kim, Pyojin, Yoon, Kuk-Jin, Liu, Zhe, Joo, Kyungdon, Liu, Yun-Hui

“…Existing vanishing point (VP) estimation methods rely on pre-extracted image lines and/or prior knowledge of the number of VPs. However, in practice, this…”
Get full text

Quasi-Globally Optimal and Efficient Vanishing Point Estimation in Manhattan World by Li, Haoang, Zhao, Ji, Bazin, Jean-Charles, Chen, Wen, Liu, Zhe, Liu, Yunhui

“…The image lines projected from parallel 3D lines intersect at a common point called the vanishing point (VP). Manhattan world holds for the scenes with three…”
Get full text

CUHK-AHU Dataset: Promoting Practical Self-Driving Applications in the Complex Airport Logistics, Hill and Urban Environments by Chen, Wen, Liu, Zhe, Zhao, Hongchao, Zhou, Shunbo, Li, Haoang, Liu, Yun-Hui

“…This paper presents a novel dataset targeting three types of challenging environments for autonomous driving, i.e., the industrial logistics environment, the…”
Get full text

Learning to Identify Correct 2D-2D Line Correspondences on Sphere by Li, Haoang, Chen, Kai, Zhao, Ji, Wang, Jiangliu, Kim, Pyojin, Liu, Zhe, Liu, Yun-Hui

“…Given a set of putative 2D-2D line correspondences, we aim to identify correct matches. Existing methods exploit the geometric constraints. They are only…”
Get full text

Line-based Absolute and Relative Camera Pose Estimation in Structured Environments by Li, Haoang, Zhao, Ji, Bazin, Jean-Charles, Chen, Wen, Chen, Kai, Liu, Yun-Hui

“…3D lines in structured environments encode particular regularity like parallelism and orthogonality. We leverage this structural regularity to estimate the…”
Get full text