Fusion of 3D LIDAR and Camera Data for Object Detection in Autonomous Vehicle Applications
TL;DR: A novel object detection and identification method that fuses the complementary information obtained by two types of sensors, 3D LIDAR and vision cameras, that meets the real-time demand of autonomous vehicles.
read more
Abstract: It is vital that autonomous vehicles acquire accurate and real-time information about objects in their vicinity, which fully guarantees the safety of the passengers and vehicle in various environments. Three-dimensional light detection and ranging (3D LIDAR) sensors can directly obtain the position and geometric structure of an object within its detection range, whereas the use of vision cameras is most suitable for object recognition. Accordingly, in this paper, we present a novel object detection and identification method that fuses the complementary information obtained by two types of sensors. First, we utilise 3D LIDAR data to generate accurate object-region proposals. Then, these candidates are mapped onto the image space from which regions of interest (ROI) of the proposals are selected and input to a convolutional neural network (CNN) for further object recognition. To precisely identify the sizes of all the objects, we combine the features of the last three layers of the CNN to extract multi-scale features from the ROIs. The evaluation results obtained on the KITTI dataset demonstrate that: (1) unlike sliding windows that produce thousands of candidate object-region proposals, 3D LIDAR provides an average of 86 real candidates per frame and the minimal recall rate is better than 95%, which greatly decreases the extraction time; (2) The average processing time for each frame of the proposed method is only 66.79 ms, which meets the real-time demand of autonomous vehicles; (3) The average identification accuracies of our method for cars and pedestrians at a moderate level of difficulty are 89.04% and 78.18%, respectively, which is better than those of most previous methods.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Evaluation of Benchmarking Pre-Trained CNN Model for Autonomous Vehicles Object Detection in Mixed Traffic
10 Aug 2022
TL;DR: In this paper , the authors evaluated the performance of five pre-trained CNN models for object detection in a mixed traffic environment, including Faster RCNN, SSD, YOLOv3 and EfficientDet.
3
Developing a Self-Driving Autonomous Car using Artificial Intelligence Algorithm
Ahsan Kabir Nuhel,Mir Mohibullah Sazid,Md. Nafim Mahmud Bhuiyan,Ariful Islam Arif,Priyadarshini Hriddhi Roy,Md Riazul Islam +5 more
- 01 Dec 2022
TL;DR: Using deep learning, machine learning, computer vision, and conventional neural networks, a self-driving automobile was developed in this article by modeling the design of a car body and the implementation of various sensors on the car chassis in order to automatically run the cars.
3
HP3D-V2V: High-Precision 3D Object Detection Vehicle-to-Vehicle Cooperative Perception Algorithm
Hongmei Chen,Haifeng Wang,Zilong Liu,Dongbing Gu,Wen-Wei Ye +4 more
- 28 Mar 2024
TL;DR: A high-precision 3D object detection V2V cooperative perception algorithm that achieves lightweighting with a higher average precision (AP) than other existing models and solves the spatial feature interaction problem lacking in the PointPillars approach.
3
Low-cost camera and 2-D LIDAR fusion for target vehicle corner detection and tracking: Applications to micromobility devices
Hamidreza Alai,R. Rajamani +1 more
TL;DR: This paper proposes a low-cost camera and 2-D LIDAR fusion system for target vehicle corner detection and tracking, enhancing safety for micromobility devices like e-scooters by predicting collision danger with high accuracy.
3
Trajectory-Based 3D Point Cloud ROI Determination Methods for Autonomous Mobile Robot
01 Jan 2023
TL;DR: In this article , the authors proposed region of interest (ROI) determination methods that sequentially construct circular and rectangular ROIs along the target trajectory of the robot to extract only crucial data for the target task.
3
References
•Proceedings Article
Very Deep Convolutional Networks for Large-Scale Image Recognition
Karen Simonyan,Andrew Zisserman +1 more
- 04 Sep 2014
TL;DR: This work investigates the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting using an architecture with very small convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers.
102.6K
ImageNet: A large-scale hierarchical image database
Jia Deng,Wei Dong,Richard Socher,Li-Jia Li,Kai Li,Li Fei-Fei +5 more
- 20 Jun 2009
TL;DR: A new database called “ImageNet” is introduced, a large-scale ontology of images built upon the backbone of the WordNet structure, much larger in scale and diversity and much more accurate than the current image datasets.
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
TL;DR: This work introduces a Region Proposal Network (RPN) that shares full-image convolutional features with the detection network, thus enabling nearly cost-free region proposals and further merge RPN and Fast R-CNN into a single network by sharing their convolutionAL features.
•Proceedings Article
Very Deep Convolutional Networks for Large-Scale Image Recognition
Karen Simonyan,Andrew Zisserman +1 more
- 01 Jan 2015
TL;DR: In this paper, the authors investigated the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting and showed that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 layers.
51.9K
You Only Look Once: Unified, Real-Time Object Detection
Joseph Redmon,Santosh K. Divvala,Ross Girshick,Ali Farhadi +3 more
- 27 Jun 2016
TL;DR: Compared to state-of-the-art detection systems, YOLO makes more localization errors but is less likely to predict false positives on background, and outperforms other detection methods, including DPM and R-CNN, when generalizing from natural images to other domains like artwork.