Hongpei Yin

Hongpei Yin

Auto-generated profile, based on publicly available information

Hongpei Yin

School of Mechanical, Electronic and Control Engineering, Beijing Jiaotong University, Beijing, China

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
27 February 2024 in IEEE Transactions on Instrumentation and Measurement
Verified
Journal Article
Closed access
XZXiongwei Zhao
Xiongwei Zhao
CWCongcong Wen
Congcong Wen
SPSAI MANOJ PRAKHYA
SAI MANOJ PRAKHYA
HYHongpei Yin
Hongpei Yin
RZRundong Zhou
Rundong Zhou
YWYang Wang
Yang Wang
Lidar-Visual-Inertial SLAM (LVINS) provides a compelling solution for accurate and robust state estimation and mapping, integrating complementary information from multi-sensor data. However, in the front-end processing of existing LVINS systems, methods based on visual line feature matching typically suffer from low accuracy and are time-consuming. Additionally, the back-end optimization of current multi-sensor fusion SLAM systems is adversely affected by feature association outliers, which constrains further enhancements in localization precision. In the loop closure process, existing lidar loop closure descriptors, relying primarily on 2D information from point clouds, often fall short in complex environments. To effectively tackle these challenges, we introduce the Multi-Modal Feature-based Lidar-Visual-Inertial SLAM framework, abbreviated as MMF-LVINS. Our framework consists of three major innovations. Firstly, we propose a novel coarse-to-fine visual line matching method that utilizes geometric descriptor similarity and optical flow verification, substantially improving both efficiency and accuracy of line feature matching. Secondly, we present a robust iterative optimization approach featuring a newly proposed adaptive loss function. This function is tailored based on the quality of feature association and incorporates graduated non-convexity, thereby reducing the impact of outliers on system accuracy. Thirdly, to augment the precision of lidar-based loop closure detection, we introduce an innovative 3D lidar descriptor that captures spatial, height, and intensity information from the point cloud. We also propose a two-stage place recognition module that synergistically combines both visual and this new lidar descriptor, significantly diminishing cumulative drift. Extensive experimental evaluations on six real-world datasets, including EuRoc, KITTI, NCLT, M2DGR, UrbanNav and UrbanLoco, demonstrate that our MMF-LVINS system achieves superior state estimation accuracy compared to existing state-of-the-art methods. These experiments also validate the effectiveness of our advanced techniques in visual line matching, robust iterative optimization, and enhanced lidar loop closure detection.

21 November 2022 in IEEE Transactions on Instrumentation and Measurement
Verified
Journal Article
Closed access
HYHongpei Yin
Hongpei Yin
PLPeter Xiaoping Liu
Peter Xiaoping Liu
MZMinhua Zheng
Minhua Zheng
Vision-based localization and mapping can be easily affected by unstable feature tracking and illumination variations. To address these problems, we propose a point-based stereo Visual Odometry (VO) system with image brightness adjustment and feature tracking prediction. The system incorporates two threads that run in parallel: front-end and back-end. The front-end thread performs brightness adjustment, feature tracking, and motion estimation between frames. When the brightness of image changes significantly, a cumulative gray-scale histogram is used to estimate the exposure of the camera and adjust the brightness of the image. Additionally, a constant acceleration motion model and stereo geometric constraint are used to predict the location of feature points in the target image, providing a reliable initial guess for the LK optical flow tracker. In order to improve the accuracy and reduce computational complexity, the back-end performs a sliding window bundle adjustment to achieve optimal camera poses and landmark positions. Experiments on publicly available datasets indicate that the proposed scheme has better performance than state-of-the-art stereo VO.

5 June 2023 in IEEE Transactions on Instrumentation and Measurement
Verified
Journal Article
Closed access
HYHongpei Yin
Hongpei Yin
PLPeter Xiaoping Liu
Peter Xiaoping Liu
MZMinhua Zheng
Minhua Zheng
Reliable extrinsic calibration is critical to fuse camera and inertial measurement unit (IMU), which are usually used in stereo visual-inertial odometry (VIO), however, it is difficult to obtain extrinsic parameters in practice. This paper proposes a stereo VIO with the capability of calibrating the unknown extrinsic parameters online. The initial values of IMU-camera and camera-camera transformations are estimated during the initial process, which fully leverages commonly observed features between stereo cameras. The pose and velocity are estimated and the extrinsic parameters are jointly refined. Additionally, the accelerometer and gyroscope biases, and gravity direction are taken into account. The proposed VIO scheme have been demonstrated to be effective without prior knowledge of extrinsic parameters.

16 August 2022 in IEEE Transactions on Instrumentation and Measurement
Verified
Journal Article
Closed access
HYHongpei Yin
Hongpei Yin
PLPeter Xiaoping Liu
Peter Xiaoping Liu
MZMinhua Zheng
Minhua Zheng
This article presents a new edge-based ego-motion estimation method for stereo cameras using 3D–2D edge alignment. To filter out prominent edgelets from Canny edge extractor, a region growing algorithm is developed to remove cluttered edges out of raw edgelets. Edge matching between stereo image pairs is guided by sparse feature correspondence using optical flow. The disparity is then refined using an inverse compositional algorithm, which is far more computationally efficient than searching along the epipolar line. The relative camera motion is solved by 3D–2D edge alignment based on an iterative closest point (ICP) algorithm, minimizing the point-to-tangent distance. A gradient-orientation-based similarity measurement is proposed, and the optimal correspondence is searched between the 3-D edge point projected onto the current image and the extracted edge pixels in the current frame with 1-nearest neighbor. In addition, the inverse depth of edge points in the reference frame is optimized. Experiments show that the proposed method can provide centimeter-level relative pose error (RPE), which has a better performance than the point-based approach efficient perspective-n-point (EPnP) and the edge-based approach direct edge-alignment (DE-A).