Abstract
This article presents a GPU-accelerated software design of the recently proposed model of Slanted Stixels, which represents the geometric and semantic information of a scene in a compact and accurate way. We reformulate the measurement depth model to reduce the computational complexity of the algorithm, relying on the confidence of the depth estimation and the identification of invalid values to handle outliers. The proposed massively parallel scheme and data layout for the irregular computation pattern that corresponds to a Dynamic Programming paradigm is described and carefully analyzed in performance terms. Performance is shown to scale gracefully on current generation embedded GPUs. We assess the proposed methods in terms of semantic and geometric accuracy as well as run-time performance on three publicly available benchmark datasets. Our approach achieves real-time performance with high accuracy for 2048 × 1024 image sizes and 4 × 4 Stixel resolution on the low-power embedded GPU of an NVIDIA Tegra Xavier.
Highlights
ADVANCED driver assistance systems (ADAS), autonomous vehicles, robots and other intelligent devices need to understand their environment
The Stixel world defines a compact representation of the dense 3D disparity data obtained from stereo vision that uses rectangles, the so called Stixels, as elements
We propose a novel depth measurement model that enables the application of several algorithmic techniques to reduce the computational complexity of Slanted Stixels from Oðw  h3Þ to Oðw  h2Þ
Summary
ADVANCED driver assistance systems (ADAS), autonomous vehicles, robots and other intelligent devices need to understand their environment. We want to process highresolution input images at high speed in order to reach realtime performance with low energy consumption, but without sacrificing segmentation accuracy To this extent, we propose a novel depth measurement model that enables the application of several algorithmic techniques to reduce the computational complexity of Slanted Stixels from Oðw  h3Þ to Oðw  h2Þ. The last row in the table describes our proposal for a novel cost equation that basically removes the usage of a uniform distribution to model the occurrence of disparity measurement outliers by the usage of the confidence of the depth estimation and of the semantic cues Thanks to this reformulation, our algorithm has lower computational complexity than the original algorithm for Slanted Stixels.
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: IEEE Transactions on Parallel and Distributed Systems
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
