Stixel-based segmentation is specifically designed towards obstacle detection which combines road surface estimation in traffic scenes, stixel calculations, and stixel clustering. Stixels are defined by observed height above road surface. Road surfaces (ground manifolds) are represented by using an occupancy grid map. Stixel-based segmentation may improve the accuracy of real-time obstacle detection, especially if adaptive to changes in ground manifolds (e.g. with respect to non-planar road geometry). In this paper, we propose the use of a polynomial curve fitting algorithm based on the v-disparity space for ground manifold estimation. This is beneficial for two reasons. First, the coordinate space has inherently finite boundaries, which is useful when working with probability densities. Second, it leads to reduced computation time. We combine height segmentation and improved ground manifold algorithms together for stixel extraction. Our experimental results show a significant improvement in the accuracy of the ground manifold detection (an 8% improvement) compared to occupancy-grid mapping methods.
This paper highlights the role of ground manifold modelling for stixel calculations; stixels are medium-level data representations used for the development of computer vision modules for self-driving cars. By using single disparity maps and simplifying ground manifold models, calculated stixels may suffer from noise, inconsistency, and false-detection rates for obstacles, especially in challenging datasets. Stixel calculations can be improved with respect to accuracy and robustness by using more adaptive ground manifold approximations. A comparative study of stixel results, obtained for different groundmanifold models (e.g. plane-fitting, line-fitting in v-disparities or polynomial approximation, and graph cut), defines the main part of this paper. The paper also considers the use of trinocular stereo vision and shows that this provides options to enhance stixel results compared to binocular recording. Comprehensive experiments are performed on two publicly available challenging datasets. We also use a novel way for comparing calculated stixels with ground truth. We compare depth information, as given by extracted stixels, with ground-truth depth, provided by depth measurements using a highly accurate LiDAR range sensor (as available in one of the public datasets). We evaluate the accuracy of four different ground-manifold methods. Experimental results also include quantitative evaluations of the trade-off between accuracy and run time. As a result, the proposed trinocular recording together with graph-cut estimation of ground manifolds appears to be a recommended way, also considering challenging weather and lighting conditions.
We present a novel method for stixel construction using a calibrated collinear trinocular vision system. Our method takes three conjugate stereo images at the same time to measure the consistency of disparity values by means of the transitivity error in disparity space. Unlike previous stixel estimation methods that are built based on a single disparity map, our proposed method introduces a multi-map fusion technique to obtain more robust stixel calculations. We apply a polynomial curve fitting approach to detect an accurate road manifold, using the v-disparity space which is built based on a confidence map. Comparing the depth information from the extracted stixels (using stixel maps) with depth measurements obtained from a highly accurate LiDAR range sensor, we evaluate the accuracy of the proposed method. Experimental results indicate a significant improvement of 13.6% in the accuracy of stixel detection compared to conventional binocular vision.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.