Contextual road lane and symbol generation for autonomous driving
This addresses the problem of reliable lane and symbol detection for autonomous vehicles, but it is incremental as it builds on existing generative models for a specific domain.
The paper tackles lane detection and segmentation for autonomous driving by using a generative adversarial network to model the probability distribution of lanes and road symbols, achieving better performance than state-of-the-art methods on BDD100K and Baidu ApolloScape datasets with robustness in adverse conditions like faded or occluded lanes.
In this paper we present a novel approach for lane detection and segmentation using generative models. Traditionally discriminative models have been employed to classify pixels semantically on a road. We model the probability distribution of lanes and road symbols by training a generative adversarial network. Based on the learned probability distribution, context-aware lanes and road signs are generated for a given image which are further quantized for nearest class label. Proposed method has been tested on BDD100K and Baidu ApolloScape datasets and performs better than state of the art and exhibits robustness to adverse conditions by generating lanes in faded out and occluded scenarios.