Point cloud segmentation for unstructured regions is challenging. Especially, the diversity and complexity of the terrains in surface mine make point cloud segmentation more difficult, which brings potential risks for autonomous driving. To solve this problem, a Variance and Slope ratio based Segmentation method, named VSSeg was proposed. The proposed VSSeg method takes advantage of the different distributions of scatter diagrams projected in the height direction to obtain the variance-based discriminant slope characteristics. And it uses the slope changes at critical points of the ground and the unstructured regions to achieve slope-ratio-based segmentation. Experiments were conducted on the mining datasets with annotation, and the results showed the effectiveness and robustness of our proposed VSSeg method. Especially, for dumping berm segmentation, the accuracy reached 95% on average with a real-time speed.

VSSeg: A Point Cloud Segmentation Approach for Unstructured Region in Surface Mine

Ground segmentation and modeling for point clouds generated by mobile laser scanners is an important processing step in the environment perception of mobile robots. Many methods that work well in urban areas do not work correctly in unstructured environments such as meadows or forests. We present a new method that works reliably in both structured urban areas and unstructured outdoor environments. Overall we design a three steps pipeline. First individual scattered ground base points are identified using purely geometric criteria. Based on the ground base points, the ground is then modeled as a triangle mesh in a second step. The triangle mesh is used to provide a relative height and a local slope. The effectiveness and robustness of the proposed method are confirmed and it shows promising results even under difficult conditions.

LiDAR Ground Segmentation and Modeling for Mobile Robots in Unstructured Terrain

Abstract. Point cloud registration algorithms have been studied for several decades. In the SLAM domain, dense local convergence based methods are typically used to register consecutive scans. Since these procedures are not globally optimal, it happens that they converge to a wrong local minimum. This can lead to gross errors during mapping and can make entire datasets unusable. We introduce a new branch and bound based point cloud registration method that is globally optimal. The method is able to reliably determine the global optimum within a given parameter search space. We show how this method can be used in a mapping system as a fallback function to correct gross errors. Using various public datasets, we demonstrate the capabilities of the method.


/pdf/globally-optimal-point-cloud-registration-for-robust-mobile-qsdxfzlz.pdf

Globally optimal point cloud registration for robust mobile mapping

Abstract. The field of visual localization has been researched for several decades and has meanwhile found many practical applications. Despite the strong progress in this field, there are still challenging situations in which established methods fail. We present an approach to significantly improve the accuracy and reliability of established visual localization methods by adding rendered images. In detail, we first use a modern visual SLAM approach that provides a 3D Gaussian Splatting (3DGS) based map to create reference data. We demonstrate that enriching reference data with images rendered from 3DGS at randomly sampled poses significantly improves the performance of both geometry-based visual localization and Scene Coordinate Regression (SCR) methods. Through comprehensive evaluation in a large industrial environment, we analyze the performance impact of incorporating these additional rendered views.


pdf/3d-gaussian-splatting-aided-localization-for-large-and-cevkdzj5fpck.pdf

3D Gaussian Splatting aided Localization for Large and Complex Indoor-Environments

Handle everyday research tasks with reliable, citation-backed results

Your personal Research Agent to handle research tasks with citation-backed results

Popular Tasks used by Researchers

How can I help with your research?

Meet SciSpace

Get more enhanced response by uploading the PDFs you want me to reference.

No relevant PDFs in your library

SciSpace is the AI research assistant for academics. Run systematic literature reviews on 280M+ papers, and write papers with cited sources. Trusted by 1M+ students, PhDs & researchers.

SciSpace | AI for Research

Analyze PDFs

Code & Manuscripts

Funding & Grants

Literature & Patents

Medical & Clinical Data

Systematic Review

Visualize & Present

Web & Data

Build a Google Scholar-like website for your research.

Build a website

Create charts and images for your research

Create a Chart

Write a paper for submission to a journal

Draft a manuscript

Patent Search

Design eye-catching scientific posters in minutes.

Scientific Poster Generation

Systematic Literature Review

One task is running at the moment. Your messages will be shown right after.

Drag and drop or click here to browse

Loved by <highlight>1 million+</highlight> researchers

Extract a list of specific topics and their sources from unstructured text

Topics

Compare and analyze relevant papers that matches with your search

Papers

Get insights from PDFs and bookmarked papers from your library

My library

Recent searches

Try searching for:

Catch AI-generated content in scholarly and non-scholarly content

{ai} Detector

Ai Writer

Get PDF Summaries, highlighted text explanations 

Chat with PDF

Effortlessly create in-text citations and bibliographies in APA and 2,500 other formats

Citation generator

Get explanations, summaries, and answers on academic papers

Ease up your research workflow with {scispace}'s cohort of exciting AI tools

Elevate your academic writing skills and convey your ideas the way you want

Paraphraser

Explore our range of reading and writing tools

Your file is being prepared and should be ready in a few minutes. If it's a large file, it might take a bit longer. You can close this window, and we'll email you the file when it's done.

You have reached a maximum limit of <strong>{limit}</strong> columns in the table. Remove at least <strong>1</strong> column to add or create another one.

D. Skuddis

Author Tools

Chat about Author

Papers

LiDAR Ground Segmentation and Modeling for Mobile Robots in Unstructured Terrain

Globally optimal point cloud registration for robust mobile mapping

3D Gaussian Splatting aided Localization for Large and Complex Indoor-Environments