CANet: Curved Guide Line Network with Adaptive Decoder for Lane Detection
This addresses lane detection for autonomous driving systems, but it is incremental as it builds on existing methods to handle corner lanes better.
The paper tackles the problem of lane detection in complex road scenarios and camera perspectives, particularly for corner lanes, by proposing CANet, a top-down deep learning approach that achieves state-of-the-art results in various metrics.
Lane detection is challenging due to the complicated on road scenarios and line deformation from different camera perspectives. Lots of solutions were proposed, but can not deal with corner lanes well. To address this problem, this paper proposes a new top-down deep learning lane detection approach, CANET. A lane instance is first responded by the heat-map on the U-shaped curved guide line at global semantic level, thus the corresponding features of each lane are aggregated at the response point. Then CANET obtains the heat-map response of the entire lane through conditional convolution, and finally decodes the point set to describe lanes via adaptive decoder. The experimental results show that CANET reaches SOTA in different metrics. Our code will be released soon.