Multiple Encoder-Decoders Net for Lane Detection

Yuetong Du, Xiaodong Gu, Junqin Liu, Liwen He

Abstract: For semantic image segmentation and lane detection, nets with a single spatial pyramid structure or encoder-decoder structure are usually exploited. Convolutional neural networks (CNNs) show great results on both high-level and low-level features representations, however, the capability has not been fully embodied for lane detection task. In especial, it's still a challenge for model-based lane detection to combine the multi-scale context with a pixel-level accuracy because of the weak visual appearance and strong prior information. In this paper, we we propose an novel network for lane detection, the three main contributions are as follows. First, we employ multiple encoder-decoders module in end-to-end ways and show the promising results for lane detection. Second, we analysis different configurations of multiple encoder-decoders nets. Third, we make our attempts to rethink the evaluation methods of lane detection for the limitation of the popular methods based on IoU.

Data: [CULane](https://paperswithcode.com/dataset/culane)