RailYolact -- A Yolact Focused on edge for Real-Time Rail Segmentation
This work addresses rail segmentation for autonomous train safety, but it is incremental as it builds upon an existing method with specific modifications.
The paper tackled the problem of rough edges in rail segmentation masks by enhancing Yolact with edge information in the loss function and smoothing ground truth masks, resulting in improved prediction accuracy on a custom rail dataset and a 4.1 and 4.6 increase in AP and AP50 on Cityscapes compared to Yolact.
Ensuring obstacle avoidance on the rail surface is crucial for the safety of autonomous driving trains and its first step is to segment the regions of the rail. We chose to build upon Yolact for our work. To address the issue of rough edge in the rail masks predicted by the model, we incorporated the edge information extracted by edge operator into the original Yolact's loss function to emphasize the model's focus on rail edges. Additionally, we applied box filter to smooth the jagged ground truth mask edges cause by linear interpolation. Since the integration of edge information and smooth process only occurred during the training process, the inference speed of the model remained unaffected. The experiments results on our custom rail dataset demonstrated an improvement in the prediction accuracy. Moreover, the results on Cityscapes showed a 4.1 and 4.6 improvement in $AP$ and $AP_{50}$ , respectively, compared to Yolact.