🤖 AI Summary
To address the limitations of existing curb detection methods—including poor robustness of image-based approaches, high latency and difficulty in deep learning adaptation for point cloud–based methods, and prohibitive annotation costs—this paper proposes an unsupervised curb detection framework. Our method introduces three key innovations: (1) a novel Altitude Difference Image (ADI) representation that projects unstructured LiDAR point clouds into structured 2D images, ensuring illumination invariance and efficient inference; (2) an Automatic Curb Annotator (ACA) that leverages geometric priors to generate high-quality pseudo-labels, enabling fully annotation-free training; and (3) a lightweight U-Net–style segmentation network coupled with a dedicated post-processing module. Evaluated on the KITTI 3D Curb Dataset, our approach achieves state-of-the-art performance, reduces inference latency by an order of magnitude compared to mainstream point cloud–based methods, and is the first to realize end-to-end curb detection with high accuracy, low latency, and zero manual annotation.
📝 Abstract
Road curbs are considered as one of the crucial and ubiquitous traffic features, which are essential for ensuring the safety of autonomous vehicles. Current methods for detecting curbs primarily rely on camera imagery or LiDAR point clouds. Image-based methods are vulnerable to fluctuations in lighting conditions and exhibit poor robustness, while methods based on point clouds circumvent the issues associated with lighting variations. However, it is the typical case that significant processing delays are encountered due to the voluminous amount of 3D points contained in each frame of the point cloud data. Furthermore, the inherently unstructured characteristics of point clouds poses challenges for integrating the latest deep learning advancements into point cloud data applications. To address these issues, this work proposes an annotation-free curb detection method leveraging Altitude Difference Image (ADI), which effectively mitigates the aforementioned challenges. Given that methods based on deep learning generally demand extensive, manually annotated datasets, which are both expensive and labor-intensive to create, we present an Automatic Curb Annotator (ACA) module. This module utilizes a deterministic curb detection algorithm to automatically generate a vast quantity of training data. Consequently, it facilitates the training of the curb detection model without necessitating any manual annotation of data. Finally, by incorporating a post-processing module, we manage to achieve state-of-the-art results on the KITTI 3D curb dataset with considerably reduced processing delays compared to existing methods, which underscores the effectiveness of our approach in curb detection tasks.