Advances in Deep Learning for Semantic Segmentation of Low-Contrast Images: A Systematic Review of Methods, Challenges, and Future Directions
The semantic segmentation (SS) of low-contrast images (LCIs) remains a significant challenge in computer vision, particularly for sensor-driven applications like medical imaging, autonomous navigation, and industrial defect detection, where accurate object delineation is critical. This systematic re...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-03-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/25/7/2043 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850189015605575680 |
|---|---|
| author | Claudio Urrea Maximiliano Vélez |
| author_facet | Claudio Urrea Maximiliano Vélez |
| author_sort | Claudio Urrea |
| collection | DOAJ |
| description | The semantic segmentation (SS) of low-contrast images (LCIs) remains a significant challenge in computer vision, particularly for sensor-driven applications like medical imaging, autonomous navigation, and industrial defect detection, where accurate object delineation is critical. This systematic review develops a comprehensive evaluation of state-of-the-art deep learning (DL) techniques to improve segmentation accuracy in LCI scenarios by addressing key challenges such as diffuse boundaries and regions with similar pixel intensities. It tackles primary challenges, such as diffuse boundaries and regions with similar pixel intensities, which limit conventional methods. Key advancements include attention mechanisms, multi-scale feature extraction, and hybrid architectures combining Convolutional Neural Networks (CNNs) with Vision Transformers (ViTs), which expand the Effective Receptive Field (ERF), improve feature representation, and optimize information flow. We compare the performance of 25 models, evaluating accuracy (e.g., mean Intersection over Union (mIoU), Dice Similarity Coefficient (DSC)), computational efficiency, and robustness across benchmark datasets relevant to automation and robotics. This review identifies limitations, including the scarcity of diverse, annotated LCI datasets and the high computational demands of transformer-based models. Future opportunities emphasize lightweight architectures, advanced data augmentation, integration with multimodal sensor data (e.g., LiDAR, thermal imaging), and ethically transparent AI to build trust in automation systems. This work contributes a practical guide for enhancing LCI segmentation, improving mean accuracy metrics like mIoU by up to 15% in sensor-based applications, as evidenced by benchmark comparisons. It serves as a concise, comprehensive guide for researchers and practitioners advancing DL-based LCI segmentation in real-world sensor applications. |
| format | Article |
| id | doaj-art-e438ee85dcbb4a6e92fe1f261b0c8e35 |
| institution | OA Journals |
| issn | 1424-8220 |
| language | English |
| publishDate | 2025-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj-art-e438ee85dcbb4a6e92fe1f261b0c8e352025-08-20T02:15:42ZengMDPI AGSensors1424-82202025-03-01257204310.3390/s25072043Advances in Deep Learning for Semantic Segmentation of Low-Contrast Images: A Systematic Review of Methods, Challenges, and Future DirectionsClaudio Urrea0Maximiliano Vélez1Electrical Engineering Department, Faculty of Engineering, University of Santiago of Chile, Las Sophoras 165, Estación Central, Santiago 9170124, ChileElectrical Engineering Department, Faculty of Engineering, University of Santiago of Chile, Las Sophoras 165, Estación Central, Santiago 9170124, ChileThe semantic segmentation (SS) of low-contrast images (LCIs) remains a significant challenge in computer vision, particularly for sensor-driven applications like medical imaging, autonomous navigation, and industrial defect detection, where accurate object delineation is critical. This systematic review develops a comprehensive evaluation of state-of-the-art deep learning (DL) techniques to improve segmentation accuracy in LCI scenarios by addressing key challenges such as diffuse boundaries and regions with similar pixel intensities. It tackles primary challenges, such as diffuse boundaries and regions with similar pixel intensities, which limit conventional methods. Key advancements include attention mechanisms, multi-scale feature extraction, and hybrid architectures combining Convolutional Neural Networks (CNNs) with Vision Transformers (ViTs), which expand the Effective Receptive Field (ERF), improve feature representation, and optimize information flow. We compare the performance of 25 models, evaluating accuracy (e.g., mean Intersection over Union (mIoU), Dice Similarity Coefficient (DSC)), computational efficiency, and robustness across benchmark datasets relevant to automation and robotics. This review identifies limitations, including the scarcity of diverse, annotated LCI datasets and the high computational demands of transformer-based models. Future opportunities emphasize lightweight architectures, advanced data augmentation, integration with multimodal sensor data (e.g., LiDAR, thermal imaging), and ethically transparent AI to build trust in automation systems. This work contributes a practical guide for enhancing LCI segmentation, improving mean accuracy metrics like mIoU by up to 15% in sensor-based applications, as evidenced by benchmark comparisons. It serves as a concise, comprehensive guide for researchers and practitioners advancing DL-based LCI segmentation in real-world sensor applications.https://www.mdpi.com/1424-8220/25/7/2043semantic segmentationlow-contrast imagesdeep learninghybrid architectureseffective receptive fieldattention mechanisms |
| spellingShingle | Claudio Urrea Maximiliano Vélez Advances in Deep Learning for Semantic Segmentation of Low-Contrast Images: A Systematic Review of Methods, Challenges, and Future Directions Sensors semantic segmentation low-contrast images deep learning hybrid architectures effective receptive field attention mechanisms |
| title | Advances in Deep Learning for Semantic Segmentation of Low-Contrast Images: A Systematic Review of Methods, Challenges, and Future Directions |
| title_full | Advances in Deep Learning for Semantic Segmentation of Low-Contrast Images: A Systematic Review of Methods, Challenges, and Future Directions |
| title_fullStr | Advances in Deep Learning for Semantic Segmentation of Low-Contrast Images: A Systematic Review of Methods, Challenges, and Future Directions |
| title_full_unstemmed | Advances in Deep Learning for Semantic Segmentation of Low-Contrast Images: A Systematic Review of Methods, Challenges, and Future Directions |
| title_short | Advances in Deep Learning for Semantic Segmentation of Low-Contrast Images: A Systematic Review of Methods, Challenges, and Future Directions |
| title_sort | advances in deep learning for semantic segmentation of low contrast images a systematic review of methods challenges and future directions |
| topic | semantic segmentation low-contrast images deep learning hybrid architectures effective receptive field attention mechanisms |
| url | https://www.mdpi.com/1424-8220/25/7/2043 |
| work_keys_str_mv | AT claudiourrea advancesindeeplearningforsemanticsegmentationoflowcontrastimagesasystematicreviewofmethodschallengesandfuturedirections AT maximilianovelez advancesindeeplearningforsemanticsegmentationoflowcontrastimagesasystematicreviewofmethodschallengesandfuturedirections |