Alert button
Picture for Jianzhu Huai

Jianzhu Huai

Alert button

3D-SeqMOS: A Novel Sequential 3D Moving Object Segmentation in Autonomous Driving

Jul 18, 2023
Qipeng Li, Yuan Zhuang, Yiwen Chen, Jianzhu Huai, Miao Li, Tianbing Ma, Yufei Tang, Xinlian Liang

Figure 1 for 3D-SeqMOS: A Novel Sequential 3D Moving Object Segmentation in Autonomous Driving
Figure 2 for 3D-SeqMOS: A Novel Sequential 3D Moving Object Segmentation in Autonomous Driving
Figure 3 for 3D-SeqMOS: A Novel Sequential 3D Moving Object Segmentation in Autonomous Driving
Figure 4 for 3D-SeqMOS: A Novel Sequential 3D Moving Object Segmentation in Autonomous Driving

For the SLAM system in robotics and autonomous driving, the accuracy of front-end odometry and back-end loop-closure detection determine the whole intelligent system performance. But the LiDAR-SLAM could be disturbed by current scene moving objects, resulting in drift errors and even loop-closure failure. Thus, the ability to detect and segment moving objects is essential for high-precision positioning and building a consistent map. In this paper, we address the problem of moving object segmentation from 3D LiDAR scans to improve the odometry and loop-closure accuracy of SLAM. We propose a novel 3D Sequential Moving-Object-Segmentation (3D-SeqMOS) method that can accurately segment the scene into moving and static objects, such as moving and static cars. Different from the existing projected-image method, we process the raw 3D point cloud and build a 3D convolution neural network for MOS task. In addition, to make full use of the spatio-temporal information of point cloud, we propose a point cloud residual mechanism using the spatial features of current scan and the temporal features of previous residual scans. Besides, we build a complete SLAM framework to verify the effectiveness and accuracy of 3D-SeqMOS. Experiments on SemanticKITTI dataset show that our proposed 3D-SeqMOS method can effectively detect moving objects and improve the accuracy of LiDAR odometry and loop-closure detection. The test results show our 3D-SeqMOS outperforms the state-of-the-art method by 12.4%. We extend the proposed method to the SemanticKITTI: Moving Object Segmentation competition and achieve the 2nd in the leaderboard, showing its effectiveness.

Viaarxiv icon

A Review and Comparative Study of Close-Range Geometric Camera Calibration Tools

Jun 15, 2023
Jianzhu Huai, Yuan Zhuang, Yuxin Shao, Grzegorz Jozkow, Binliang Wang, Junhui Liu, Yijia He, Alper Yilmaz

Figure 1 for A Review and Comparative Study of Close-Range Geometric Camera Calibration Tools
Figure 2 for A Review and Comparative Study of Close-Range Geometric Camera Calibration Tools
Figure 3 for A Review and Comparative Study of Close-Range Geometric Camera Calibration Tools
Figure 4 for A Review and Comparative Study of Close-Range Geometric Camera Calibration Tools

In many camera-based applications, it is necessary to find the geometric relationship between incoming rays and image pixels, i.e., the projection model, through the geometric camera calibration (GCC). Aiming to provide practical calibration guidelines, this work surveys and evaluates the existing GCC tools. The survey covers camera models, calibration targets, and algorithms used in these tools, highlighting their properties and the trends in GCC development. The evaluation compares six target-based GCC tools, namely, BabelCalib, Basalt, Camodocal, Kalibr, the MATLAB calibrator, and the OpenCV-based ROS calibrator, with simulated and real data for cameras of wide-angle and fisheye lenses described by three traditional projection models. These tests reveal the strengths and weaknesses of these camera models, as well as the repeatability of these GCC tools. In view of the survey and evaluation, future research directions of GCC are also discussed.

* 17 pages, 13 figures 
Viaarxiv icon

4D iRIOM: 4D Imaging Radar Inertial Odometry and Mapping

Apr 03, 2023
Yuan Zhuang, Binliang Wang, Jianzhu Huai, Miao Li

Figure 1 for 4D iRIOM: 4D Imaging Radar Inertial Odometry and Mapping
Figure 2 for 4D iRIOM: 4D Imaging Radar Inertial Odometry and Mapping
Figure 3 for 4D iRIOM: 4D Imaging Radar Inertial Odometry and Mapping
Figure 4 for 4D iRIOM: 4D Imaging Radar Inertial Odometry and Mapping

Millimeter wave radar can measure distances, directions, and Doppler velocity for objects in harsh conditions such as fog. The 4D imaging radar with both vertical and horizontal data resembling an image can also measure objects' height. Previous studies have used 3D radars for ego-motion estimation. But few methods leveraged the rich data of imaging radars, and they usually omitted the mapping aspect, thus leading to inferior odometry accuracy. This paper presents a real-time imaging radar inertial odometry and mapping method, iRIOM, based on the submap concept. To deal with moving objects and multipath reflections, we use the graduated non-convexity method to robustly and efficiently estimate ego-velocity from a single scan. To measure the agreement between sparse non-repetitive radar scan points and submap points, the distribution-to-multi-distribution distance for matches is adopted. The ego-velocity, scan-to-submap matches are fused with the 6D inertial data by an iterative extended Kalman filter to get the platform's 3D position and orientation. A loop closure module is also developed to curb the odometry module's drift. To our knowledge, iRIOM based on the two modules is the first 4D radar inertial SLAM system. On our and third-party data, we show iRIOM's favorable odometry accuracy and mapping consistency against the FastLIO-SLAM and the EKFRIO. Also, the ablation study reveal the benefit of inertial data versus the constant velocity model, and scan-to-submap matching versus scan-to-scan matching.

* 8 pages, 8 figures, 4 tables, the proofread version will appear on RA-L soon 
Viaarxiv icon

Observability Analysis and Keyframe-Based Filtering for Visual Inertial Odometry with Full Self-Calibration

Jan 13, 2022
Jianzhu Huai, Yukai Lin, Yuan Zhuang, Charles Toth, Dong Chen

Figure 1 for Observability Analysis and Keyframe-Based Filtering for Visual Inertial Odometry with Full Self-Calibration
Figure 2 for Observability Analysis and Keyframe-Based Filtering for Visual Inertial Odometry with Full Self-Calibration
Figure 3 for Observability Analysis and Keyframe-Based Filtering for Visual Inertial Odometry with Full Self-Calibration
Figure 4 for Observability Analysis and Keyframe-Based Filtering for Visual Inertial Odometry with Full Self-Calibration

Camera-IMU (Inertial Measurement Unit) sensor fusion has been extensively studied in recent decades. Numerous observability analysis and fusion schemes for motion estimation with self-calibration have been presented. However, it has been uncertain whether both camera and IMU intrinsic parameters are observable under general motion. To answer this question, we first prove that for a global shutter camera-IMU system, all intrinsic and extrinsic parameters are observable with an unknown landmark. Given this, time offset and readout time of a rolling shutter (RS) camera also prove to be observable. Next, to validate this analysis and to solve the drift issue of a structureless filter during standstills, we develop a Keyframe-based Sliding Window Filter (KSWF) for odometry and self-calibration, which works with a monocular RS camera or stereo RS cameras. Though the keyframe concept is widely used in vision-based sensor fusion, to our knowledge, KSWF is the first of its kind to support self-calibration. Our simulation and real data tests validated that it is possible to fully calibrate the camera-IMU system using observations of opportunistic landmarks under diverse motion. Real data tests confirmed previous allusions that keeping landmarks in the state vector can remedy the drift in standstill, and showed that the keyframe-based scheme is an alternative cure.

* 16 pages, 9 figures 
Viaarxiv icon

Continuous-Time Spatiotemporal Calibration of a Rolling Shutter Camera---IMU System

Aug 16, 2021
Jianzhu Huai, Yuan Zhuang, Qicheng Yuan, Yukai Lin

Figure 1 for Continuous-Time Spatiotemporal Calibration of a Rolling Shutter Camera---IMU System
Figure 2 for Continuous-Time Spatiotemporal Calibration of a Rolling Shutter Camera---IMU System
Figure 3 for Continuous-Time Spatiotemporal Calibration of a Rolling Shutter Camera---IMU System
Figure 4 for Continuous-Time Spatiotemporal Calibration of a Rolling Shutter Camera---IMU System

The rolling shutter (RS) mechanism is widely used by consumer-grade cameras, which are essential parts in smartphones and autonomous vehicles. The RS effect leads to image distortion upon relative motion between a camera and the scene. This effect needs to be considered in video stabilization, structure from motion, and vision-aided odometry, for which recent studies have improved earlier global shutter (GS) methods by accounting for the RS effect. However, it is still unclear how the RS affects spatiotemporal calibration of the camera in a sensor assembly, which is crucial to good performance in aforementioned applications. This work takes the camera-IMU system as an example and looks into the RS effect on its spatiotemporal calibration. To this end, we develop a calibration method for a RS-camera-IMU system with continuous-time B-splines by using a calibration target. Unlike in calibrating GS cameras, every observation of a landmark on the target has a unique camera pose fitted by continuous-time B-splines. With simulated data generated from four sets of public calibration data, we show that RS can noticeably affect the extrinsic parameters, causing errors about 1$^\circ$ in orientation and 2 $cm$ in translation with a RS setting as in common smartphone cameras. With real data collected by two industrial camera-IMU systems, we find that considering the RS effect gives more accurate and consistent spatiotemporal calibration. Moreover, our method also accurately calibrates the inter-line delay of the RS. The code for simulation and calibration is publicly available.

* 11 pages, 9 figures 
Viaarxiv icon

Consistent Right-Invariant Fixed-Lag Smoother with Application to Visual Inertial SLAM

Feb 17, 2021
Jianzhu Huai, Yukai Lin, Yuan Zhuang, Min Shi

Figure 1 for Consistent Right-Invariant Fixed-Lag Smoother with Application to Visual Inertial SLAM
Figure 2 for Consistent Right-Invariant Fixed-Lag Smoother with Application to Visual Inertial SLAM
Figure 3 for Consistent Right-Invariant Fixed-Lag Smoother with Application to Visual Inertial SLAM
Figure 4 for Consistent Right-Invariant Fixed-Lag Smoother with Application to Visual Inertial SLAM

State estimation problems that use relative observations routinely arise in navigation of unmanned aerial vehicles, autonomous ground vehicles, \etc whose proper operation relies on accurate state estimates and reliable covariances. These problems have immanent unobservable directions. Traditional causal estimators, however, usually gain spurious information on the unobservable directions, leading to over confident covariance inconsistent with the actual estimator errors. The consistency problem of fixed-lag smoothers (FLSs) has only been attacked by the first estimate Jacobian (FEJ) technique because of the complexity to analyze their observability property. But the FEJ has several drawbacks hampering its wide adoption. To ensure the consistency of a FLS, this paper introduces the right invariant error formulation into the FLS framework. To our knowledge, we are the first to analyze the observability of a FLS with the right invariant error. Our main contributions are twofold. As the first novelty, to bypass the complexity of analysis with the classic observability matrix, we show that observability analysis of FLSs can be done equivalently on the linearized system. Second, we prove that the inconsistency issue in the traditional FLS can be elegantly solved by the right invariant error formulation without artificially correcting Jacobians. By applying the proposed FLS to the monocular visual inertial simultaneous localization and mapping (SLAM) problem, we confirm that the method consistently estimates covariance similarly to a batch smoother in simulation and that our method achieved comparable accuracy as traditional FLSs on real data.

* 13 pages, 4 figures, AAAI 2021 Conference 
Viaarxiv icon

A Versatile Keyframe-Based Structureless Filter for Visual Inertial Odometry

Jan 02, 2021
Jianzhu Huai, Yukai Lin, Charles Toth, Yuan Zhuang, Dong Chen

Figure 1 for A Versatile Keyframe-Based Structureless Filter for Visual Inertial Odometry
Figure 2 for A Versatile Keyframe-Based Structureless Filter for Visual Inertial Odometry
Figure 3 for A Versatile Keyframe-Based Structureless Filter for Visual Inertial Odometry
Figure 4 for A Versatile Keyframe-Based Structureless Filter for Visual Inertial Odometry

Motion estimation by fusing data from at least a camera and an Inertial Measurement Unit (IMU) enables many applications in robotics. However, among the multitude of Visual Inertial Odometry (VIO) methods, few efficiently estimate device motion with consistent covariance, and calibrate sensor parameters online for handling data from consumer sensors. This paper addresses the gap with a Keyframe-based Structureless Filter (KSF). For efficiency, landmarks are not included in the filter's state vector. For robustness, KSF associates feature observations and manages state variables using the concept of keyframes. For flexibility, KSF supports anytime calibration of IMU systematic errors, as well as extrinsic, intrinsic, and temporal parameters of each camera. Estimator consistency and observability of sensor parameters were analyzed by simulation. Sensitivity to design options, e.g., feature matching method and camera count was studied with the EuRoC benchmark. Sensor parameter estimation was evaluated on raw TUM VI sequences and smartphone data. Moreover, pose estimation accuracy was evaluated on EuRoC and TUM VI sequences versus recent VIO methods. These tests confirm that KSF reliably calibrates sensor parameters when the data contain adequate motion, and consistently estimate motion with accuracy rivaling recent VIO methods. Our implementation runs at 42 Hz with stereo camera images on a consumer laptop.

* 18 pages, 5 figures, 13 tables 
Viaarxiv icon

Segway DRIVE Benchmark: Place Recognition and SLAM Data Collected by A Fleet of Delivery Robots

Jul 08, 2019
Jianzhu Huai, Yusen Qin, Fumin Pang, Zichong Chen

Figure 1 for Segway DRIVE Benchmark: Place Recognition and SLAM Data Collected by A Fleet of Delivery Robots
Figure 2 for Segway DRIVE Benchmark: Place Recognition and SLAM Data Collected by A Fleet of Delivery Robots
Figure 3 for Segway DRIVE Benchmark: Place Recognition and SLAM Data Collected by A Fleet of Delivery Robots
Figure 4 for Segway DRIVE Benchmark: Place Recognition and SLAM Data Collected by A Fleet of Delivery Robots

Visual place recognition and simultaneous localization and mapping (SLAM) have recently begun to be used in real-world autonomous navigation tasks like food delivery. Existing datasets for SLAM research are often not representative of in situ operations, leaving a gap between academic research and real-world deployment. In response, this paper presents the Segway DRIVE benchmark, a novel and challenging dataset suite collected by a fleet of Segway delivery robots. Each robot is equipped with a global-shutter fisheye camera, a consumer-grade IMU synced to the camera on chip, two low-cost wheel encoders, and a removable high-precision lidar for generating reference solutions. As they routinely carry out tasks in office buildings and shopping malls while collecting data, the dataset spanning a year is characterized by planar motions, moving pedestrians in scenes, and changing environment and lighting. Such factors typically pose severe challenges and may lead to failures for SLAM algorithms. Moreover, several metrics are proposed to evaluate metric place recognition algorithms. With these metrics, sample SLAM and metric place recognition methods were evaluated on this benchmark. The first release of our benchmark has hundreds of sequences, covering more than 50 km of indoor floors. More data will be added as the robot fleet continues to operate in real life. The benchmark is available at http://drive.segwayrobotics.com/#/dataset/download.

* 8 pages, 4 figures, 4 tables, conference 
Viaarxiv icon