Dynamic Multi-LiDAR Based Multiple Object Detection and Tracking

Abstract

Environmental perception plays an essential role in autonomous driving tasks and demands robustness in cluttered dynamic environments such as complex urban scenarios. In this paper, a robust Multiple Object Detection and Tracking (MODT) algorithm for a non-stationary base is presented, using multiple 3D LiDARs for perception. The merged LiDAR data is treated with an efficient MODT framework, considering the limitations of the vehicle-embedded computing environment. The ground classification is obtained through a grid-based method while considering a non-planar ground. Furthermore, unlike prior works, 3D grid-based clustering technique is developed to detect objects under elevated structures. The centroid measurements obtained from the object detection are tracked using Interactive Multiple Model-Unscented Kalman Filter-Joint Probabilistic Data Association Filter (IMM-UKF-JPDAF). IMM captures different motion patterns, UKF handles the nonlinearities of motion models, and JPDAF associates the measurements in the presence of clutter. The proposed algorithm is implemented on two slightly dissimilar platforms, giving real-time performance on embedded computers. The performance evaluation metrics by MOT16 and ground truths provided by KITTI Datasets are used for evaluations and comparison with the state-of-the-art. The experimentation on platforms and comparisons with state-of-the-art techniques suggest that the proposed framework is a feasible solution for MODT tasks.

Vehicle Tracking and Speed Estimation From Roadside Lidar

“…After the vehicle detection stage, the resulting set of identified trackable vehicles are processed for pose and centroid estimation, accompanied by known model fitting [24]. This generates a valid measurement of a vehicle for which the attributes further evolve over time.…”

Clothoid: An Integrated Hierarchical Framework for Autonomous Driving in a Dynamic Urban Environment

“…Thus, first of all, ground extraction is performed by separation of LiDAR point cloud measurements into the ground and non-ground point clouds. The technique deployed in this work follows a cylindrical grid-based approach with the non-planner ground assumption, as used in [ 35 ]. The point cloud related to ground measurements is used for lane detection in GPS-denied regions.…”

“…The clustering component makes the clusters of the LiDAR point cloud by following the connected component method [ 35 ]. The object clusters formed in the specified regions of the LiDAR point cloud are filtered through a dimension filter to further reduce the outliers.…”

Application of Wireless Accelerometer Mounted on Wheel Rim for Parked Car Monitoring

“…The classic sensing systems increasing the safety of car operation include: tire-pressure monitoring system (TPMS), adaptive cruise control (ACC), blind-spot detection (BSD), lane-departure warning (LDW), traction control (TC) sometimes called rollover prevention, antilock braking system (ABS), emergency brake assist (EBA), adaptive headlights and rearview camera. All these systems are well developed, but the progress in technology and system performances are under continuous improvements [6][7][8][9][10][11].…”