In autonomous driving applications, accurate and efficient road surface reconstruction is paramount. This paper introduces RoMe, a novel framework designed for the robust reconstruction of large-scale road surfaces. Leveraging a unique mesh representation, RoMe ensures that the reconstructed road surfaces are accurate and seamlessly aligned with semantics. To address challenges in computational efficiency, we propose a waypoint sampling strategy, enabling RoMe to reconstruct vast environments by focusing on sub-areas and subsequently merging them. Furthermore, we incorporate an extrinsic optimization module to enhance the robustness against inaccuracies in extrinsic calibration. Our extensive evaluations of both public datasets and wild data underscore RoMe's superiority in terms of speed, accuracy, and robustness. For instance, it costs only 2 GPU hours to recover a road surface of $600\times 600$ square meters from thousands of images. Notably, RoMe's capability extends beyond mere reconstruction, offering significant value for auto-labeling tasks in autonomous driving applications. All related data and code are available at GitHub.
In this paper, we introduce a novel approach for ground plane normal estimation of wheeled vehicles. In practice, the ground plane is dynamically changed due to braking and unstable road surface. As a result, the vehicle pose, especially the pitch angle, is oscillating from subtle to obvious. Thus, estimating ground plane normal is meaningful since it can be encoded to improve the robustness of various autonomous driving tasks (e.g., 3D object detection, road surface reconstruction, and trajectory planning). Our proposed method only uses odometry as input and estimates accurate ground plane normal vectors in real time. Particularly, it fully utilizes the underlying connection between the ego pose odometry (ego-motion) and its nearby ground plane. Built on that, an Invariant Extended Kalman Filter (IEKF) is designed to estimate the normal vector in the sensor’s coordinate. Thus, our proposed method is simple yet efficient and supports both camera- and inertial-based odometry algorithms. Its usability and the marked improvement of robustness are validated through multiple experiments on public datasets. For instance, we achieve state-of-the-art accuracy on KITTI dataset with the estimated vector error of 0.39°.
Real-time detection and tracking of vehicles is very important in the field of automatic driving. In this paper, a YOLOv3 network based on pruning algorithm is proposed to solve the problem of real-time vehicle detection. Through reducing the number of channels and layers in the backbone network, the computation of the model is reduced. And thus, the rate of detection is greatly increased. On the basis of vehicle detection, the real-time tracking of multiple vehicle targets is completed by using Kalman filter algorithm for prediction and Hungarian algorithm for data association. The experimental results show that compared with the original YOLOv3 network, the model size is compressed by 95% to 11.25 MB and the detection rate is doubled to 128.1 frames/s while the average accuracy is basically unchanged. The detection and tracking frame rate of the whole algorithm is 18fps, and the recall is 98.5%. The algorithm also has strong robustness on complex traffic roads, and can basically realize real-time detection and tracking of road vehicles.