Enhanced ground segmentation method for Lidar point clouds in human-centric autonomous robot systems

A Survey on Ground Segmentation Methods for Automotive LiDAR Sensors

In the near future, autonomous vehicles with full self-driving features will populate our public roads. However, fully autonomous cars will require robust perception systems to safely navigate the environment, which includes cameras, RADAR devices, and Light Detection and Ranging (LiDAR) sensors. LiDAR is currently a key sensor for the future of autonomous driving since it can read the vehicle's vicinity and provide a real-time 3D visualization of the surroundings through a point cloud representation. These features can assist the autonomous vehicle in several tasks, such as object identification and obstacle avoidance, accurate speed and distance measurements, road navigation, and more. However, it is crucial to detect the ground plane and road limits to safely navigate the environment, which requires extracting information from the point cloud to accurately detect common road boundaries. This article presents a survey of existing methods used to detect and extract ground points from LiDAR point clouds. It summarizes the already extensive literature and proposes a comprehensive taxonomy to help understand the current ground segmentation methods that can be used in automotive LiDAR sensors.

A Robust Gaussian Process-Based LiDAR Ground Segmentation Algorithm for Autonomous Driving

Robust and precise vehicle detection is the prerequisite for decision-making and motion planning in autonomous driving. Vehicle detection algorithms follow three steps: ground segmentation, obstacle clustering and bounding box fitting. The ground segmentation result directly affects the input of the subsequent obstacle clustering algorithms. Aiming at the problems of over-segmentation and under-segmentation in traditional ground segmentation algorithms, a ground segmentation algorithm based on Gaussian process is proposed in this paper. To ensure accurate search of real ground candidate points as training data for Gaussian process, the proposed algorithm introduces the height and slope criteria, which is more reasonable than the use of fixed height threshold for searching. After that, a sparse covariance function is introduced as the kernel function for calculation in Gaussian process. This function is more suitable for ground segmentation situation the radial basis function (RBF). The proposed algorithm is tested on our autonomous driving experimental platform and the public autonomous driving dataset KITTI, compared with the most used RANSAC algorithm and ray ground filter algorithm. Experiment results show that the proposed algorithm can avoid obvious over-segmentation and under-segmentation. In addition, compared with the RBF, the introduction of the sparse covariance function also reduces the computation time by 37.26%.

Fast Ground Segmentation for 3D LiDAR Point Cloud Based on Jump-Convolution-Process

LiDAR occupies a vital position in self-driving as the advanced detection technology enables autonomous vehicles (AVs) to obtain much environmental information. Ground segmentation for LiDAR point cloud is a crucial procedure to ensure AVs’ driving safety. However, some current algorithms suffer from embarrassments such as unavailability on complex terrains, excessive time and memory usage, and additional pre-training requirements. The Jump-Convolution-Process (JCP) is proposed to solve these issues. JCP converts the segmentation problem of the 3D point cloud into the smoothing problem of the 2D image and takes little time to improve the segmentation effect significantly. First, the point cloud marked by an improved local feature extraction algorithm is projected onto an RGB image. Then, the pixel value is initialized with the points’ label and continuously updated according to image convolution. Finally, a jump operation is introduced in the convolution process to perform calculations only on the low-confidence points filtered by the credibility propagation algorithm, reducing the time cost. Experiments on three datasets show that our approach has a better segmentation accuracy and terrain adaptability than those of the three existing methods. Meanwhile, the average time for the proposed method to deal with one scan data of 64-beam and 128-beam LiDAR is only 8.61 ms and 15.62 ms, which fully meets the AVs’ requirement for real-time performance.

VB-Net: Voxel-Based Broad Learning Network for 3D Object Classification

Point clouds have been widely used in three-dimensional (3D) object classification tasks, i.e., people recognition in unmanned ground vehicles. However, the irregular data format of point clouds and the large number of parameters in deep learning networks affect the performance of object classification. This paper develops a 3D object classification system using a broad learning system (BLS) with a feature extractor called VB-Net. First, raw point clouds are voxelized into voxels. Through this step, irregular point clouds are converted into regular voxels which are easily processed by the feature extractor. Then, a pre-trained VoxNet is employed as a feature extractor to extract features from voxels. Finally, those features are used for object classification by the applied BLS. The proposed system is tested on the ModelNet40 dataset and ModelNet10 dataset. The average recognition accuracy was 83.99% and 90.08%, respectively. Compared to deep learning networks, the time consumption of the proposed system is significantly decreased.

Cyclist detection and tracking based on multi-layer laser scanner

The technology of Artificial Intelligence (AI) brings tremendous possibilities for autonomous vehicle applications. One of the essential tasks of autonomous vehicle is environment perception using machine learning algorithms. Since the cyclists are the vulnerable road users, cyclist detection and tracking are important perception sub-tasks for autonomous vehicles to avoid vehicle-cyclist collision. In this paper, a robust method for cyclist detection and tracking is presented based on multi-layer laser scanner, i.e., IBEO LUX 4L, which obtains four-layer point cloud from local environment. First, the laser points are partitioned into individual clusters using Density-Based Spatial Clustering of Applications with Noise (DBSCAN) method based on subarea. Then, 37-dimensional feature set is optimized by Relief algorithm and Principal Component Analysis (PCA) to produce two new feature sets. Support Vector Machine (SVM) and Decision Tree (DT) classifiers are further combined with three feature sets, respectively. Moreover, Multiple Hypothesis Tracking (MHT) algorithm and Kalman filter based on Current Statistical (CS) model are applied to track moving cyclists and estimate the motion state. The performance of the proposed cyclist detection and tracking method is validated in real road environment.

End-To-End Controls Using K-Means Algorithm for 360-Degree Video Control Method on Omnidirectional Camera-Equipped Autonomous Micro Unmanned Aircraft Systems

Micro unmanned aircraft systems (micro UAS)-related technical research is important because micro UAS has the advantage of being able to perform missions remotely. When an omnidirectional camera is mounted, it captures all surrounding areas of the micro UAS. Normal field of view (NFoV) refers to a view presented as an image to a user in a 360-degree video. The 360-degree video is controlled using an end-to-end controls method to automatically provide the user with NFoVs without the user controlling the 360-degree video. When using the end-to-end controls method that controls 360-degree video, if there are various signals that control the 360-degree video, the training of the deep learning model requires a considerable amount of training data. Therefore, there is a need for a method of autonomously determining the signals to reduce the number of signals for controlling the 360-degree video. This paper proposes a method to autonomously determine the output to be used for end-to-end control-based deep learning model to control 360-degree video for micro UAS controllers. The output of the deep learning model to control 360-degree video is automatically determined using the K-means algorithm. Using a trained deep learning model, the user is presented with NFoVs in a 360-degree video. The proposed method was experimentally verified by providing NFoVs wherein the signals that control the 360-degree video were set by the proposed method and by user definition. The results of training the convolution neural network (CNN) model using the signals to provide NFoVs were compared, and the proposed method provided NFoVs similar to NFoVs of existing user with 24.4% more similarity compared to a user-defined approach.