Open Access Open Access  Restricted Access Subscription Access

Eyes on the Road: A Comprehensive Review of Object Detection and Tracking in Autonomous Vehicles

A. Pooja, A. Arya, C. Harini, Syeda Hifsa Naaz

Abstract


This review explores recent advancements in object detection and tracking techniques designed for autonomous vehicles (AVs). It focuses on cutting-edge algorithms like YOLOv4, YOLOv5, and YOLOv7, which tackle key challenges such as navigating adverse weather, meeting real-time processing demands, and handling multi-object tracking. The study highlights innovations like lightweight architectures, attention mechanisms, and domain adaptation techniques that improve detection accuracy, even in complex scenarios. Diverse datasets and standardized evaluation metrics are emphasized as vital for consistent performance measurement. The review also explores deep learning approaches, including model compression, to enhance efficiency. Key areas of focus include integrating object detection with tracking, optimizing algorithms for edge devices, and ensuring real-time capabilities. These insights contribute to building safer, smarter, and more reliable autonomous driving technologies.


Full Text:

PDF

References


Pedro Azevedo and Vítor Santos. Comparative analysis of multiple YOLO-based target detectors and trackers for ADAS in edge devices. Robotics and Autonomous Systems, 171:104558, January 2024.

Joseph Redmon and Ali Farhadi. YOLOv3: An Incremental Improvement, April 2018.

Mazin Hnewa and Hayder Radha. Object Detection Under Rainy Conditions for Autonomous Vehicles: A Review of State-of-the-Art and Emerging Techniques. IEEE Signal Processing Magazine, 38(1):53–67, January 2021.

Chien-Yao Wang, Alexey Bochkovskiy, and Hong-Yuan Mark Liao. YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors, July 2022.

Jun Liu, Qiqin Cai, Fumin Zou, Yintian Zhu, Lyuchao Liao, and Feng Guo. BiGA-YOLO: A Lightweight Object Detection Network Based on YOLOv5 for Autonomous Driving. Electronics, 12(12):2745, June 2023.

Mohammad Jani, Jamil Fayyad, Younes Al-Younes, and Homayoun Najjaran. Model Compression Methods for YOLOv5: A Review, July 2023.

Tyler Ward, Sherif Rashad, and Heba Elgazzar. Machine Learning Based Pedestrian Detection and Tracking for Autonomous Vehicles. In 2023 IEEE 13th Annual Computing and Communication Workshop and Conference (CCWC), pages 1294–1299, Las Vegas, NV, USA, March 2023. IEEE.

Joseph Redmon, Santosh Divvala, Ross Girshick, and Ali Farhadi. You Only Look Once: Unified, Real-Time Object Detection, May 2016.

Ratheesh Ravindran, Michael J. Santora, and Mohsin M. Jamali. Multi-Object Detection and Tracking, Based on DNN, for Autonomous Vehicles: A Review. IEEE Sensors Journal, 21(5):5668–5677, March 2021.

Shuman Guo, Shichang Wang, Zhenzhong Yang, Lijun Wang, Huawei Zhang, Pengyan Guo, Yuguo Gao, and Junkai Guo. A Review of Deep Learning-Based Visual Multi-Object Tracking Algorithms for Autonomous Driving. Applied Sciences, 12(21):10741, October 2022.


Refbacks

  • There are currently no refbacks.