Deep Learning for Traffic Scene Understanding: A Review
Open Access
- 13 January 2025
- journal article
- review article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 13187-13237
Abstract
This review paper presents an in-depth analysis of deep learning (DL) models applied to traffic scene understanding, a key aspect of modern intelligent transportation systems. It examines fundamental techniques such as classification, object detection, and segmentation, and extends to more advanced applications like action recognition, object tracking, path prediction, scene generation and retrieval, anomaly detection, Image-to-Image Translation (I2IT), and person re-identification (Person Re-ID). The paper synthesizes insights from a broad range of studies, tracing the evolution from traditional image processing methods to sophisticated DL techniques, such as Convolutional Neural Networks (CNNs) and Generative Adversarial Networks (GANs). The review also explores three primary categories of domain adaptation (DA) methods: clustering-based, discrepancy-based, and adversarial-based, highlighting their significance in traffic scene understanding. The significance of Hyperparameter Optimization (HPO) is also discussed, emphasizing its critical role in enhancing model performance and efficiency, particularly in adapting DL models for practical, real-world use. Special focus is given to the integration of these models in real-world applications, including autonomous driving, traffic management, and pedestrian safety. The review also addresses key challenges in traffic scene understanding, such as occlusions, the dynamic nature of urban traffic, and environmental complexities like varying weather and lighting conditions. By critically analyzing current technologies, the paper identifies limitations in existing research and proposes areas for future exploration. It underscores the need for improved interpretability, real-time processing, and the integration of multi-modal data. This reviewserves as a valuable resource for researchers and practitioners aiming to apply or advance DL techniques in traffic scene understanding.Keywords
Funding Information
- U.S. Department of Transportation (693JJ32350030)
This publication has 185 references indexed in Scilit:
- All-weather road drivable area segmentation method based on CycleGANThe Visual Computer, 2022
- MTSDet: multi-scale traffic sign detection with attention and path aggregationApplied Intelligence, 2022
- Unsupervised Domain Adaptation in the Dissimilarity Space for Person Re-identification2020
- End-to-End Object Detection with Transformers2020
- SNE-RoadSeg: Incorporating Surface Normal Information into Semantic Segmentation for Accurate Freespace Detection2020
- A survey of deep learning techniques for autonomous drivingJournal of Field Robotics, 2019
- AugGAN: Cross Domain Adaptation with GAN-Based Data Augmentation2018
- SSD: Single Shot MultiBox Detector2016
- Playing for Data: Ground Truth from Computer Games2016
- Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition2014