RT3D: Real-Time 3-D Vehicle Detection in LiDAR Point Cloud for Autonomous Driving

Vehicle detection is one of the most important environment perception tasks for autonomous vehicles. The traditional vision-based vehicle detection methods are not accurate enough especially for small and occluded targets, while the light detection and ranging- (lidar-) based methods are good in detecting obstacles but they are time-consuming and have a low classification rate for different target types. Focusing on these shortcomings to make the full use of the advantages of the depth information of lidar and the obstacle classification ability of vision, this work proposes a real-time vehicle detection algorithm which fuses vision and lidar point cloud information. Firstly, the obstacles are detected by the grid projection method using the lidar point cloud information. Then, the obstacles are mapped to the image to get several separated regions of interest (ROIs). After that, the ROIs are expanded based on the dynamic threshold and merged to generate the final ROI. Finally, a deep learning method named You Only Look Once (YOLO) is applied on the ROI to detect vehicles. The experimental results on the KITTI dataset demonstrate that the proposed algorithm has high detection accuracy and good real-time performance. Compared with the detection method based only on the YOLO deep learning, the mean average precision (mAP) is increased by 17%.

Download Full-text

Vehicle Detection and Ranging Using Two Different Focal Length Cameras

Journal of Sensors ◽

10.1155/2020/4372847 ◽

2020 ◽

Vol 2020 ◽

pp. 1-14 ◽

Cited By ~ 5

Author(s):

Jun Liu ◽

Rui Zhang

Keyword(s):

Real Time ◽

Focal Length ◽

Vehicle Detection ◽

Autonomous Driving ◽

License Plate ◽

The Road ◽

Detection Model ◽

Automatic Driving ◽

Convolution Structure ◽

Model Size

Vehicle detection is a crucial task for autonomous driving and demands high accuracy and real-time speed. Considering that the current deep learning object detection model size is too large to be deployed on the vehicle, this paper introduces the lightweight network to modify the feature extraction layer of YOLOv3 and improve the remaining convolution structure, and the improved Lightweight YOLO network reduces the number of network parameters to a quarter. Then, the license plate is detected to calculate the actual vehicle width and the distance between the vehicles is estimated by the width. This paper proposes a detection and ranging fusion method based on two different focal length cameras to solve the problem of difficult detection and low accuracy caused by a small license plate when the distance is far away. The experimental results show that the average precision and recall of the Lightweight YOLO trained on the self-built dataset is 4.43% and 3.54% lower than YOLOv3, respectively, but the computing speed of the network decreases 49 ms per frame. The road experiments in different scenes also show that the long and short focal length camera fusion ranging method dramatically improves the accuracy and stability of ranging. The mean error of ranging results is less than 4%, and the range of stable ranging can reach 100 m. The proposed method can realize real-time vehicle detection and ranging on the on-board embedded platform Jetson Xavier, which satisfies the requirements of automatic driving environment perception.

Download Full-text

Real-Time LiDAR Point Cloud Semantic Segmentation for Autonomous Driving

Electronics ◽

10.3390/electronics11010011 ◽

2021 ◽

Vol 11 (1) ◽

pp. 11

Author(s):

Xing Xie ◽

Lin Bai ◽

Xinming Huang

Keyword(s):

Real Time ◽

Power Efficiency ◽

Point Cloud ◽

Processing Time ◽

State Of The Art ◽

Semantic Segmentation ◽

Autonomous Driving ◽

Geometric Information ◽

Embedded Platform ◽

Gpu Implementation

LiDAR has been widely used in autonomous driving systems to provide high-precision 3D geometric information about the vehicle’s surroundings for perception, localization, and path planning. LiDAR-based point cloud semantic segmentation is an important task with a critical real-time requirement. However, most of the existing convolutional neural network (CNN) models for 3D point cloud semantic segmentation are very complex and can hardly be processed at real-time on an embedded platform. In this study, a lightweight CNN structure was proposed for projection-based LiDAR point cloud semantic segmentation with only 1.9 M parameters that gave an 87% reduction comparing to the state-of-the-art networks. When evaluated on a GPU, the processing time was 38.5 ms per frame, and it achieved a 47.9% mIoU score on Semantic-KITTI dataset. In addition, the proposed CNN is targeted on an FPGA using an NVDLA architecture, which results in a 2.74x speedup over the GPU implementation with a 46 times improvement in terms of power efficiency.

Download Full-text

LiDAR Data Enrichment by Fusing Spatial and Temporal Adjacent Frames

Remote Sensing ◽

10.3390/rs13183640 ◽

2021 ◽

Vol 13 (18) ◽

pp. 3640

Author(s):

Hao Fu ◽

Hanzhang Xue ◽

Xiaochang Hu ◽

Bokai Liu

Keyword(s):

Sparse Representation ◽

Real Time ◽

Point Cloud ◽

Moving Objects ◽

Autonomous Driving ◽

Experimental Results ◽

Lidar Data ◽

Identification Algorithm ◽

Data Enrichment ◽

A New Technique

In autonomous driving scenarios, the point cloud generated by LiDAR is usually considered as an accurate but sparse representation. In order to enrich the LiDAR point cloud, this paper proposes a new technique that combines spatial adjacent frames and temporal adjacent frames. To eliminate the “ghost” artifacts caused by moving objects, a moving point identification algorithm is introduced that employs the comparison between range images. Experiments are performed on the publicly available Semantic KITTI dataset. Experimental results show that the proposed method outperforms most of the previous approaches. Compared with these previous works, the proposed method is the only method that can run in real-time for online usage.

Download Full-text

Point Cloud Semantic Segmentation with Cross-Correction Features

10.21203/rs.3.rs-1218117/v1 ◽

2022 ◽

Author(s):

Yuehua Zhao ◽

Ma Jie ◽

Chong Nannan ◽

Wen Junjie

Keyword(s):

Real Time ◽

Point Cloud ◽

Large Scale ◽

Spatial Information ◽

Semantic Segmentation ◽

Autonomous Driving ◽

Basic Unit ◽

Semantic Features ◽

Point Cloud Segmentation ◽

Scale Point

Abstract Real time large scale point cloud segmentation is an important but challenging task for practical application like autonomous driving. Existing real time methods have achieved acceptance performance by aggregating local information. However, most of them only exploit local spatial information or local semantic information dependently, few considering the complementarity of both. In this paper, we propose a model named Spatial-Semantic Incorporation Network (SSI-Net) for real time large scale point cloud segmentation. A Spatial-Semantic Cross-correction (SSC) module is introduced in SSI-Net as a basic unit. High quality contextual features can be learned through SSC by correct and update semantic features using spatial cues, and vice verse. Adopting the plug-and-play SSC module, we design SSI-Net as an encoder-decoder architecture. To ensure efficiency, it also adopts a random sample based hierarchical network structure. Extensive experiments on several prevalent datasets demonstrate that our method can achieve state-of-the-art performance.

Download Full-text

Adaptive Vehicle Detection for Real-time Autonomous Driving System

2019 Design, Automation & Test in Europe Conference & Exhibition (DATE) ◽

10.23919/date.2019.8714818 ◽

2019 ◽

Cited By ~ 1

Author(s):

Maryam Hemmati ◽

Morteza Biglari-Abhari ◽

Smail Niar

Keyword(s):

Real Time ◽

Vehicle Detection ◽

Autonomous Driving ◽

Driving System ◽

Time Autonomous ◽

Autonomous Driving System

Download Full-text

Research on NDT-based Positioning for Autonomous Driving

E3S Web of Conferences ◽

10.1051/e3sconf/202125702055 ◽

2021 ◽

Vol 257 ◽

pp. 02055

Author(s):

Sijia Liu ◽

Jie Luo ◽

Jinmin Hu ◽

Haoru Luo ◽

Yu Liang

Keyword(s):

Real Time ◽

Electromagnetic Interference ◽

Autonomous Vehicles ◽

Autonomous Navigation ◽

Point Cloud ◽

Autonomous Driving ◽

Mapping Method ◽

Signal Loss ◽

Positioning Accuracy ◽

Localization And Mapping

Autonomous driving technology is one of the currently popular technologies, while positioning is the basic problem of autonomous navigation of autonomous vehicles. GPS is widely used as a relatively mature solution in the outdoor open road environment. However, GPS signals will be greatly affected in a complex environment with obstruction and electromagnetic interference, even signal loss may occur if serious, which has a great impact on the accuracy, stability and reliability of positioning. For the time being, L4 and most L3 autonomous driving modules still provide registration and positioning based on the high-precision map constructed. Based on this, this paper elaborates on the reconstruction of the experimental scene environment, using the SLAM (simultaneous localization and mapping) method to construct a highprecision point cloud map. On the constructed prior map, the 3D laser point cloud NDT matching method is used for real-time positioning, which is tested and verified on the “JAC Electric Vehicle” platform. The experimental results show that this algorithm has high positioning accuracy and its real-time performance meets the requirements, which can replace GPS signals to complete the positioning of autonomous vehicles when there is no GPS signal or the GPS signal is weak, and provide positioning accuracy meeting the requirements.

Download Full-text