Topology-Aware Lane Detection with Relational Reasoning and Consistency Constraints

Lane detection is a fundamental perception task for autonomous driving and intelligent transportation systems. Although existing methods have achieved promising performance, many of them mainly focus on individual lane instances and insufficiently exploit the structural relationships among lanes, such as relative ordering, geometric continuity, and spatial parallelism. This limitation may lead to broken lanes, ordering errors, and geometric inconsistencies in complex road scenarios. To address these issues, we propose TPDNet, a topology-aware lane detection framework that incorporates structural reasoning into the detection pipeline at three complementary levels. First, a Topology-aware Perception Reasoner (TPR) is introduced at the feature level to capture relational dependencies among lane features and enhance the representation of global road topology. Second, a Topology-Decoupled Head (TDH) is designed at the prediction level to decouple geometric regression from lane classification, thereby reducing task interference and improving prediction stability. Third, a Topology Consistency Loss (TCL) is formulated as a complementary supervision term to encourage smoothness and ordering consistency in predicted lanes. Extensive experiments on three public benchmarks demonstrate the effectiveness of the proposed method. On CULane, TPDNet achieves an F1@50 of 81.46 with ResNet101 and remains competitive with the strongest compared methods, while showing improved robustness in challenging scenarios such as Curve and Dazzle light. On TuSimple, TPDNet obtains an F1 score of 98.01 among the compared methods, while maintaining competitive accuracy. On CurveLanes, TPDNet achieves an mF1 of 58.74, exceeding the strongest baseline by 4.98 points. These results suggest that topology-aware reasoning can improve the generalization capability of lane detection and help produce more structurally coherent lane predictions under diverse road conditions.