Abstract
Currently, deep learning-based segmentation methods are capable of achieving accurate segmentation. However, their deployment and training are costly and resource-intensive. To reduce deployment costs and facilitate the application of segmentation models for road imagery, this paper introduces a novel road segmentation algorithm based on few-shot learning. The algorithm consists of the back-projection module (BPM), responsible for generating target probabilities, and the segmentation module (SM), which performs image segmentation based on these probabilities. To achieve precise segmentation, the paper proposes a learning mechanism that simultaneously considers both positive and negative samples, effectively capturing the color features of the environment and objects. Additionally, through the workflow design, the algorithm can rapidly perform segmentation tasks across different scenarios without requiring transfer learning and with minimal sample prompts. Experimental results show that the algorithm achieves intersection over union segmentation accuracies of 94.9%, 92.7%, 94.9%, and 94.7% across different scenarios. Compared to state-of-the-art methods, it delivers precise segmentation with fewer local road image prompts, enabling efficient edge deployment.