Multi-Stage Pyramid Parsing Network For Lane Marking Detection

2022 International Conference on INnovations in Intelligent SysTems and Applications (INISTA)(2022)

引用 0|浏览0
The recognition and segmentation of lane markings are one of the most difficult challenges in autonomous driving. One must overcome several challenges when attempting to solve this task, including trivial appearance, irregular painting, intricate shapes of lane markings, and limited spatial coverage of them w.r.t background. These problems lead to the generation of numerous false positives when traditional convolutional neural networks (CNN) are used. In this paper, we propose a novel MPP-Net model, which harnesses the power of attention and pyramid pooling operations to produce semantically consistent lane marking segmentations. In addition to that, the model is set up in a hierarchical manner to focus on both fine and coarse level features and yet produce less number of false positives due to the information regulation mechanism provided by the attention gates. We train and test our proposed model on two famous lane marking detection datasets VPGNet and Tusimple. The outcomes of our experimentation and ablation studies indicate that our model’s performance is better compared to most of the benchmarking models and is on par with some in terms of F1-score while improving semantic consistencies in those scenarios.
Lane Marking Detection,Semantic Segmentation,Attention Models,Multi-stage Networks
AI 理解论文
Chat Paper