Comparative Analysis of Effective AI-Based 3D Multi-Object Detection and Tracking Methods for Autonomous Driving

P.S. Dheepika; V. Umadevi

doi:10.14313/jamris-2026-014

Abstract

Object detection is a crucial task for autonomous driving, and different autonomous vehicles have varying perceptions. The advancements of object detection paved the way for 3D object detection, which is considered to be the central component of perception systems that predict obstacles, vehicles, pedestrians and other key features of the environmental backgorund. Generally, various sensors and cameras are used in autonomous driving producing accurate perediction of objects. Several algorithms have been employed in object detection, but they have not produced effective outcomes.

Thus, the present study implements HDL-MODT (hybrid deep learning based multi-object detection and tracking) using a sensor fusion approach. It uses solidstate LiDAR, pseudo-LiDAR and an RGB camera to capture objects and provide effective tracking abilities. Initially, the pre-processing methods involved noise removal using an A-Fuzzy (adaptive fuzzy) filter. Contrast enhancement is then performed using the MSO (moth swarm optimization) algorithm, and feature segmentation is done by LGAN (lightweight general adversial networks), where both channel and position attention mechanisms provide precise segmentation. The YOLOv4 approach is deployed for detection of objects such as ground, vehicles, pedstrians and obstacles. Finally, the tracking of objects is performed using IUKF (improved unscented Kalman filter). The simulation of the proposed method is demonstrated by using MATLAB R2020 simulation tool; the performance of the proposed method is also predicted by comparing the results with exisitng algorithms.

References

J. Mao, S. Shi, X. Wang, and H. Li,”3D Object Detection for Autonomous Driving: A Comprehensive Survey,” International Journal of Computer Vision, pp. 1–55, 2023.
Search in Google Scholar Back to article
Z. Wei, et al., “Mmwave Radar And Vision Fusion For Object Detection In Autonomous Driving: A Review,” Sensors, vol. 22, p. 2542, 2022.
Search in Google Scholar Back to article
B. Pan, L. Zhang, and H. Wang, “Multi-Stage Feature Pyramid Stereo Network-Based Disparity Estimation Approach For Two To ThreeDimensional Video Conversion,” IEEE Transactions on Circuits and Systems for Video Technology, vol. 31, pp. 1862–1875, 2020.
Search in Google Scholar Back to article
Y. Zhang, et al., ”PMPF: Point-Cloud MultiplePixel Fusion-Based 3D Object Detection for Autonomous Driving,” Remote Sensing, vol. 15, p. 1580, 2023.
Search in Google Scholar Back to article
D. Feng, et al., ”Deep Multi-Modal Object Detection And Semantic Segmentation for Autonomous Driving: Datasets, Methods, and Challenges,” IEEE Transactions on Intelligent Transportation Systems, vol. 22, pp. 1341–1360, 2020.
Search in Google Scholar Back to article
S. Yao, et al., ”Radar-Camera Fusion For Object Detection and Semantic Segmentation in Autonomous Driving: A Comprehensive Review,” arXiv preprint arXiv:2304.10410, 2023.
Search in Google Scholar Back to article
A. Hazarika, et al., ”Multi-camera 3D Object Detection for Autonomous Driving Using Deep Learning and Self-Attention Mechanism,” IEEE Access, 2023.
Search in Google Scholar Back to article
S. Rinchen, B. Vaidya, and H. T. Mouftah, ”Scalable Multi-Task Learning R-CNN for Object Detection in Autonomous Driving.” In 2023 International Wireless Communications and Mobile Computing (IWCMC), Marrakesh, 19–23 June 2023; pp. 518–523.
Search in Google Scholar Back to article
S. A. Khan, H. J. Lee, and H. Lim, ”Enhancing Object Detection in Self-Driving Cars Using a Hybrid Approach,” Electronics, vol. 12, p. 2768, 2023.
Search in Google Scholar Back to article
S. Liang, et al., ”Edge YOLO: Real-Time Intelligent Object Detection System Based on EdgeCloud Cooperation in Autonomous Vehicles,” IEEE Transactions on Intelligent Transportation Systems, vol. 23, pp. 25345–25360, 2022.
Search in Google Scholar Back to article
S.-W. Kim, et al., ”Edge-Network-Assisted Real-Time Object Detection Framework for Autonomous Driving,” IEEE Network, vol. 35, pp. 177–183, 2021.
Search in Google Scholar Back to article
Y. Wu, et al., ”An Enhanced Feature Pyramid Object Detection Network for Autonomous Driving,” Applied Sciences, vol. 9, p. 4363, 2019.
Search in Google Scholar Back to article
Y. Zhou, et al., ”Object Detection in Autonomous Driving Scenarios Based OnAn Improved Faster-RCNN,” Applied Sciences, vol. 11, p. 11630, 2021.
Search in Google Scholar Back to article
Y. Cao, C. Li, Y. Peng, and H. Ru,”MCSYOLO: A Multiscale Object Detection Method for Autonomous Driving Road Environment Recognition,” IEEE Access, vol. 11, pp. 22342–22354, 2023.
Search in Google Scholar Back to article
W. Jang, et al., ”R-TOD: Real-time Object Detector With Minimized End-To-End Delay for Autonomous Driving,” in 2020 IEEE Real-Time Systems Symposium (RTSS), 1–4^th December 2020, pp. 191–204.
Search in Google Scholar Back to article
S. Wu, Y. Yan, and W. Wang, ”CF-YOLOX: An Autonomous Driving Detection Model for MultiScale Object Detection,” Sensors, vol. 23, p. 3794, 2023.
Search in Google Scholar Back to article
Z. Yuan, et al., ”Temporal-Channel Transformer for 3D Lidar-Based Video Object Detection for Autonomous Driving,” IEEE Transactions on Circuits and Systems for Video Technology, vol. 32, pp. 2068–2078, 2021.
Search in Google Scholar Back to article
K. Geng, G. Dong, and W. Huang, ”Robust Dual-Modal Image Quality Assessment Aware Deep Learning Network for Traffic Targets Detection Of Autonomous Vehicles,” Multimedia Tools and Applications, vol. 81, pp. 6801–6826, 2022.
Search in Google Scholar Back to article
L.-H. Wen and K.-H. Jo, ”Fast and Accurate 3D Object Detection For Lidar-CameraBased Autonomous Vehicles Using One Shared VoxelBased Backbone,” IEEE Access, vol. 9, pp. 22080–22089, 2021.
Search in Google Scholar Back to article
K. Roszyk, M. R. Nowicki, and P. Skrzypczynski, ”Adopting the Yolov4 Architecture for Low-Latency Multispectral Pedestrian Detection in Autonomous Driving,” Sensors, vol. 22, p. 1082, 2022.
Search in Google Scholar Back to article
Y. Shao, et al., ”PV-SSD: A Projection and Voxelbased Double Branch Single-Stage 3D Object Detector,” arXiv preprint arXiv:2308.06791, 2023.
Search in Google Scholar Back to article
Y Cai, et al., ”YOLOv4-5D: An Effective And Efficient Object Detector for Autonomous Driving,” IEEE Transactions on Instrumentation and Measurement, vol. 70, pp. 1–13, 2021.
Search in Google Scholar Back to article
H. Nguyen, ”Improving Faster R-CNN Framework for Fast Vehicle Detection,” Mathematical Problems in Engineering, vol. 2019, pp. 1–11, 2019.
Search in Google Scholar Back to article
Q. Tang, G. Cao, and K.-H. Jo, ”Integrated Feature Pyramid Network with Feature Aggregation for Traffic Sign Detection,” IEEE Access, vol. 9, pp. 117784–117794, 2021.
Search in Google Scholar Back to article
N. Zaghari, et al., ”The Improvement in Obstacle Detection in Autonomous Vehicles Using YOLO Non-Maximum Suppression Fuzzy Algorithm,” The Journal of Supercomputing, vol. 77, pp. 13421–13446, 2021.
Search in Google Scholar Back to article
V. John and S. Mita, ”Deep feature-level Sensor Fusion Using Skip Connections for Real-Time Object Detection in Autonomous Driving,” Electronics, vol. 10, p. 424, 2021.
Search in Google Scholar Back to article

Comparative Analysis of Effective AI-Based 3D Multi-Object Detection and Tracking Methods for Autonomous Driving

Abstract

Paradigm

My account