Previous studies in vision-based grade-crossing monitoring
| Reference | Methodology | Limitations |
|---|---|---|
| Amin et al. (2024) | Combine various YOLO models with UNet to detect traffic participants and the grade crossing area for enhanced safety | 1) The use of a data set with repeating images for both training and testing raises concerns about potential overfitting of the model; 2) the combination of YOLO and UNet is computationally expensive |
| Gong et al. (2022) | Propose an enhanced few-shot learning solution for intrusion detection to mitigate data imbalance | 1) Although suggested solutions achieved high accuracy, they are tested using limited data, which may affect their usefulness in the long run; 2) model iterations are based on manual work, which makes it time-consuming and labor-heavy; 3) the suggested solutions are only evaluated on proprietary data sets or in a single location, raising concerns about their extensibility |
| Klammsteiner et al. (2023) | Propose a railway track monitoring system based on Yolov5 for detection and BiSeNetv2 for segmentation to detect obstacles on various track areas | |
| Rahman et al. (2022) | Explore MobileNetv2 for obstacle detection at rail crossings through data augmentation and transfer learning | |
| Guo et al. (2022) | 1) Propose a transformer-based model for traffic detection in the occluded scenes; 2) provide performance under bad video quality such as extreme weather condition | The proposed solutions are evaluated solely on proprietary data sets with 2,358 images which are all from a single location, raising concerns about its generalizability |
| Tang et al. (2023) | 1) Adapt segmentation enhanced with SuBsense for background generation to detect grade-crossing trespassers; 2) training the model with weak supervised learning to mitigate the lack of annotated data | The solution combines background generation with semantic segmentation, leading to high latency |
| Reference | Methodology | Limitations |
|---|---|---|
| Combine various | 1) The use of a data set with repeating images for both training and testing raises concerns about potential overfitting of the model; 2) the combination of | |
| Propose an enhanced few-shot learning solution for intrusion detection to mitigate data imbalance | 1) Although suggested solutions achieved high accuracy, they are tested using limited data, which may affect their usefulness in the long run; 2) model iterations are based on manual work, which makes it time-consuming and labor-heavy; 3) the suggested solutions are only evaluated on proprietary data sets or in a single location, raising concerns about their extensibility | |
| Propose a railway track monitoring system based on Yolov5 for detection and BiSeNetv2 for segmentation to detect obstacles on various track areas | ||
| Explore MobileNetv2 for obstacle detection at rail crossings through data augmentation and transfer learning | ||
| 1) Propose a transformer-based model for traffic detection in the occluded scenes; 2) provide performance under bad video quality such as extreme weather condition | The proposed solutions are evaluated solely on proprietary data sets with 2,358 images which are all from a single location, raising concerns about its generalizability | |
| 1) Adapt segmentation enhanced with SuBsense for background generation to detect grade-crossing trespassers; 2) training the model with weak supervised learning to mitigate the lack of annotated data | The solution combines background generation with semantic segmentation, leading to high latency |
Sharing content requires targeting cookies to be enabled. Please update your cookie preferences to use this feature.