Deep Learning for Traffic Scene Understanding: A Review
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...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10839383/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832586886435045376 |
|---|---|
| author | Parya Dolatyabi Jacob Regan Mahdi Khodayar |
| author_facet | Parya Dolatyabi Jacob Regan Mahdi Khodayar |
| author_sort | Parya Dolatyabi |
| collection | DOAJ |
| description | 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 review serves as a valuable resource for researchers and practitioners aiming to apply or advance DL techniques in traffic scene understanding. |
| format | Article |
| id | doaj-art-c11fb7787dc042709d1cc72f5132cb19 |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-c11fb7787dc042709d1cc72f5132cb192025-01-25T00:01:11ZengIEEEIEEE Access2169-35362025-01-0113131871323710.1109/ACCESS.2025.352928910839383Deep Learning for Traffic Scene Understanding: A ReviewParya Dolatyabi0https://orcid.org/0009-0008-4020-7643Jacob Regan1https://orcid.org/0000-0003-3191-9426Mahdi Khodayar2https://orcid.org/0000-0003-4683-7810Department of Computer Science, University of Tulsa, Tulsa, OK, USADepartment of Computer Science, University of Tulsa, Tulsa, OK, USADepartment of Computer Science, University of Tulsa, Tulsa, OK, USAThis 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 review serves as a valuable resource for researchers and practitioners aiming to apply or advance DL techniques in traffic scene understanding.https://ieeexplore.ieee.org/document/10839383/Deep learningtraffic scene understandingdiscriminative modelsgenerative modelsdomain adaptationclassification |
| spellingShingle | Parya Dolatyabi Jacob Regan Mahdi Khodayar Deep Learning for Traffic Scene Understanding: A Review IEEE Access Deep learning traffic scene understanding discriminative models generative models domain adaptation classification |
| title | Deep Learning for Traffic Scene Understanding: A Review |
| title_full | Deep Learning for Traffic Scene Understanding: A Review |
| title_fullStr | Deep Learning for Traffic Scene Understanding: A Review |
| title_full_unstemmed | Deep Learning for Traffic Scene Understanding: A Review |
| title_short | Deep Learning for Traffic Scene Understanding: A Review |
| title_sort | deep learning for traffic scene understanding a review |
| topic | Deep learning traffic scene understanding discriminative models generative models domain adaptation classification |
| url | https://ieeexplore.ieee.org/document/10839383/ |
| work_keys_str_mv | AT paryadolatyabi deeplearningfortrafficsceneunderstandingareview AT jacobregan deeplearningfortrafficsceneunderstandingareview AT mahdikhodayar deeplearningfortrafficsceneunderstandingareview |