Real-Time Semantic Segmentation: A Comprehensive Review and Future Perspectives

Meng Gao

doi:10.62051/ijcsit.v5n3.03

Authors

Meng Gao

DOI:

https://doi.org/10.62051/ijcsit.v5n3.03

Keywords:

Semantic segmentation, Image perception, Real-time

Abstract

As a fundamental task in image perception and understanding, semantic segmentation has been extensively applied across various domains, including medical image processing, scene analysis, autonomous driving perception, and intelligent video analytics. Practical implementations often prioritize real-time semantic segmentation due to constraints in computational resources, interaction requirements, and cost considerations. To facilitate researchers' efficient comprehension of algorithmic design and applications in this field, this paper conducts a comprehensive review and analysis of deep learning-based real-time semantic segmentation methods. Specifically, 1) Fundamental concepts, application scenarios, and challenges of semantic segmentation and its real-time variant are introduced. 2) Essential techniques and design paradigms for real-time semantic segmentation algorithms are systematically elucidated. 3) State-of-the-art real-time semantic segmentation approaches are thoroughly categorized and summarized. 4) Practical application scenarios of real-time semantic segmentation are discussed. 5) A complete evaluation framework with standardized metrics is established. 6) Conclusions are drawn along with critical analysis of remaining challenges while proposing insightful perspectives for future research directions.

Downloads

Download data is not yet available.

References

[1] Qureshi I, Yan J, Abbas Q, et al. Medical image segmentation using deep semantic-based methods: A review of techniques, applications and emerging trends [J]. Information Fusion, 2023, 90: 316-352.

[2] Kaur A, Singh Y, Chinagundi B. ResUNet++: a comprehensive improved UNet++ framework for volumetric semantic segmentation of brain tumor MR images [J]. Evolving Systems, 2024, 15(4): 1567-1585.

[3] Lu Y, Li W, Cui Z, et al. Beyond low-dimensional features: Enhancing semi-supervised medical image semantic segmentation with advanced consistency learning techniques [J]. Expert Systems with Applications, 2025, 261: 125456.

[4] Dang T V, Bui N T. Multi-Scale Fully Convolutional Network-Based Semantic Segmentation for Mobile Robot Navigation [J]. Electronics, 2023, 12(3).

[5] Cheng J, Deng C, Su Y, et al. Methods and datasets on semantic segmentation for Unmanned Aerial Vehicle remote sensing images: A review [J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2024, 211: 1-34.

[6] Li X, Xu F, Yu A, et al. A Frequency Decoupling Network for Semantic Segmentation of Remote Sensing Images [J]. IEEE Transactions on Geoscience and Remote Sensing, 2025.

[7] Ma X, Wang Z, Hu Y, et al. Kolmogorov-Arnold Network for Remote Sensing Image Semantic Segmentation [J]. arXiv preprint arXiv:2501.07390, 2025.

[8] Voronin V, Semenishchev E, Zelensky A, et al. Real‐time deep learning semantic segmentation for 3-D augmented reality [C]//LI M, SHI K, ASGHARI H, et al. Real-time Photonic Measurements, Data Management, and Processing VII: Vol. 12772. SPIE, 2023: 127720L.

[9] Wang Y, Zhang J, Chen Y, et al. An Automated Learning Method of Semantic Segmentation for Train Autonomous Driving Environment Understanding [J]. IEEE Transactions on Industrial Informatics, 2024, 20(4): 6913-6922.

[10] Hao W, Wang J, Lu H. A Real-Time Semantic Segmentation Method Based on Transformer for Autonomous Driving [J]. Computers, Materials & Continua, 2024, 81(3).

[11] Lin F, Lin T, Yao Y, et al. VPA-Net: A visual perception assistance network for 3d lidar semantic segmentation [J]. Pattern Recognition, 2025, 158: 111014.

[12] Wang H, Jiang X, Ren H, et al. Swiftnet: Real-time video object segmentation [C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2021: 1296-1305.

[13] Otsu N. A Threshold Selection Method from Gray-Level Histograms [J]. IEEE Transactions on Systems, Man, and Cybernetics, 1979, 9(1): 62-66.

[14] MacQueen J. Some methods for classification and analysis of multivariate observations [C]//Proceedings of 5-th Berkeley Symposium on Mathematical Statistics and Probability/University of California Press. 1967.

[15] Meyer F, Beucher S. Morphological segmentation [J]. Journal of Visual Communication and Image Representation, 1990, 1(1): 21-46.

[16] Adams R, Bischof L. Seeded region growing [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1994, 16(6): 641-647.

[17] Kass M, Witkin A, Terzopoulos D. Snakes: Active contour models [J]. International Journal of Computer Vision, 1988, 1(4): 321-331.

[18] Boykov Y, Jolly M P. Interactive graph cuts for optimal boundary & region segmentation of objects in N-D images [J]. Proceedings of IEEE International Conference on Computer Vision (ICCV), 2001: 105-112.

[19] Lafferty J, McCallum A, Pereira F. Conditional random fields: Probabilistic models for segmenting and labeling sequence data [J]. Proceedings of the 18th International Conference on Machine Learning (ICML), 2001: 282-289.

[20] Li S Z. Markov random field modeling in image analysis [M]. Springer Science & Business Media, 2009.