CondLaneNet: a Top-to-down Lane Detection Framework Based on Conditional Convolution
This work addresses lane detection for autonomous driving systems, offering improved accuracy and efficiency in handling complex scenarios, though it appears incremental as it builds on existing deep learning methods.
The authors tackled the problem of lane detection in complex topologies like dense or fork lines by proposing CondLaneNet, a top-to-down framework that detects lane instances and dynamically predicts shapes, achieving state-of-the-art performance with a 78.14 F1 score and 220 FPS on the CULane benchmark.
Modern deep-learning-based lane detection methods are successful in most scenarios but struggling for lane lines with complex topologies. In this work, we propose CondLaneNet, a novel top-to-down lane detection framework that detects the lane instances first and then dynamically predicts the line shape for each instance. Aiming to resolve lane instance-level discrimination problem, we introduce a conditional lane detection strategy based on conditional convolution and row-wise formulation. Further, we design the Recurrent Instance Module(RIM) to overcome the problem of detecting lane lines with complex topologies such as dense lines and fork lines. Benefit from the end-to-end pipeline which requires little post-process, our method has real-time efficiency. We extensively evaluate our method on three benchmarks of lane detection. Results show that our method achieves state-of-the-art performance on all three benchmark datasets. Moreover, our method has the coexistence of accuracy and efficiency, e.g. a 78.14 F1 score and 220 FPS on CULane. Our code is available at https://github.com/aliyun/conditional-lane-detection.