检索结果-内蒙古大学图书馆

2025 IEEE/CVF Winter Conference on Applications of Computer vision, WACV 2025

作者： Steininger, Daniel Simon, Julia Trondl, Andreas Murschitz, Markus Ait Austrian Institute of Technology Center for Vision Automation & Control Austria

ISBN: (纸本)9798331510831

Timber represents an increasingly valuable and versatile resource. However, forestry operations such as harvesting, handling and measuring logs still require substantial human labor in remote environments posing significant safety risks. Progressively automating these tasks has the potential of increasing their efficiency as well as safety, but requires an accurate detection of individual logs as well as live trees and their context. Although initial approaches have been proposed for this challenging application domain, specialized data and algorithms are still too scarce to develop robust solutions. To mitigate this gap, we introduce the Timbervision dataset, consisting of more than 2k annotated RGB images containing a total of 51k trunk components including cut and lateral surfaces, thereby surpassing any existing dataset in this domain in terms of both quantity and detail by a large margin. Based on this data, we conduct a series of ablation experiments for oriented object detection and instance segmentation and evaluate the influence of multiple scene parameters on model performance. We introduce a generic framework to fuse the components detected by our models for both tasks into unified trunk representations. Furthermore, we automatically derive geometric properties and apply multi-object tracking to further enhance robustness. Our detection and tracking approach provides highly descriptive and accurate trunk representations solely from RGB image data, even under challenging environmental conditions. Our solution is suitable for a wide range of application scenarios and can be readily combined with other sensor modalities. © 2025 IEEE.

关键词： Logging (forestry)

来源：评论

学校读者我要写书评

暂无评论

Pushing the limit to near real-time indoor LiDAR-based semantic segmentation 8

Pushing the limit to near real-time indoor LiDAR-based seman...

引用

8th International ISPRS Workshop LowCost 3D - Sensors, Algorithms, Applications

作者： Bournez, Pierrick Salzinger, Jules Cella, Marco Vultaggio, Francesco d'Apolito, Francesco Fanta-Jende, Phillipp AIT Austrian Institute of Technology Center for Vision Automation and Control Unit Assistive and Autonomous Systems Austria

Semantic segmentation of indoor 3D point clouds is a critical technology for understanding three dimensional indoor environments, with significant applications in indoor navigation, positioning, and intelligent robotics. While real-time semantic segmentation is already a reality for images, existing classification pipelines for LiDAR point clouds assume a pre-existing map which relies on data collected from accurate but heavy sensors. However, this approach is impractical for high-level task planning and autonomous exploration, which benefits from a rapid 3D structure understanding of the environment. Furthermore, while RGB cameras remain a popular choice in good visibility conditions, such sensors are inefficient in environments where visibility is hindered. Consequently, LiDAR point clouds emerge as a rather reliable source of environmental information in such circumstances. In this paper, we adapt an existing semantic segmentation model, Superpoint Transformer, to LiDAR-based situation where RGB inputs are not available and near real-time processing is attempted. To this end, we simulated our robot's trajectory and leveraged Hidden Point Removal using the open-source dataset S3DIS to train the model. We investigated various strategies such as modifying the interval prediction and thoroughly study its influence on the prediction intervals. Our model demonstrates an improvement from 40 to 67.6 mean Intersection over Union (mIoU) compared to the baseline on simple (floor, ceiling, walls) and complex (doors, windows) classes. Copyright: © 2024 Pierrick Bournez et al.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Active Learning with Alternating Acquisition Functions: Balancing the Exploration-Exploitation Dilemma

Active Learning with Alternating Acquisition Functions: Bala...

引用

2024 IEEE International Conference on Big Data, BigData 2024

作者： Jung, Cedric Salehi, Shirin Schmeink, Anke Vienna Austria Ait Austrian Institute of Technology GmbH Center for Vision Automation & Control Vienna Austria Aachen Germany

ISBN: (纸本)9798350362480

Active learning (AL) is a machine learning technique that aims to reduce annotation costs by selectively choosing the most informative samples for labeling. This process relies on acquisition functions, which can be broadly categorized into two types: representativity-based and uncertainty-based. Representativity-based functions focus on exploring the dataset, while uncertainty-based functions refine decision boundaries. This creates a trade-off known as the exploration-exploitation dilemma. To address this challenge, we propose a novel approach that alternates between these two types of acquisition functions. Our method employs an adaptive feedback-driven selection mechanism, an annealing-based approach, or a baseline random criterion to guide the alternation process. This strategy helps mitigate common AL issues, such as batch mode inefficiency and cold start problems. Our experiments demonstrate that the alternating approach enhances both the accuracy and robustness of the AL process. Additionally, we consider the balance between accuracy and energy consumption, contributing to the development of more sustainable AI systems. By evaluating our criterion across various models and datasets, we show its potential to reduce computational costs while maintaining or even improving accuracy. Notably, alternating between the BALD and BADGE acquisition functions yields particularly robust results. © 2024 IEEE.

关键词： Active learning

来源：评论

学校读者我要写书评

暂无评论

SIMULATION OF LOW-COST MEMS-LIDAR AND ANALYSIS OF ITS EFFECT ON THE PERFORMANCES OF STATE-OF-THE-ART SLAMS 12

SIMULATION OF LOW-COST MEMS-LIDAR AND ANALYSIS OF ITS EFFECT...

引用

12th International Symposium on Mobile Mapping Technology, MMT 2023

作者： Vultaggio, F. d’Apolito, F. Sulzbachner, C. Fanta-Jende, P. AIT - Austrian Institute of Technology Center for Vision Automation and Control Assistive Autonomous Systems Austria

Indoor Unmanned Aerial Vehicles have often been tasked with performing SLAM, and the sensors most used in literature and industry have been cameras. Spanning from stereo to event cameras, visual algorithms have often been the de facto choice for localization. While visual SLAM has reached a high level of accuracy in localization, accurate map reconstruction still proves to be challenging. Meanwhile, LiDAR sensors have been used for years to obtain accurate maps. First in surveying applications and in the past ten years in the automotive sector. The weight, power, and size constraints of most traditional LiDARs have prevented their installation on UAVs for indoor use. MEMS-based LiDARs have already been used in UAVs but had to rely on algorithms designed to deal with their small FOV. Recently, a MEMS-based LiDAR with a wide field of view (360°*59°) and weighing 265 g has sparked interest in its potential for indoor UAV SLAM. We performed an extensive battery of tests in simulation environments to provide a first look into its effect on state-of-the-art SLAM algorithms, highlight which ones can provide the best results, and what improvements may be most beneficial. This paper aims to provide assistance in further research in the field by releasing the tool used for this work. © Author(s) 2023. CC BY 4.0 License.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

FUELING GLOCAL: OPTIMIZATION-BASED PATH PLANNING FOR INDOOR UAVS IN AN AUTONOMOUS EXPLORATION FRAMEWORK 12

FUELING GLOCAL: OPTIMIZATION-BASED PATH PLANNING FOR INDOOR ...

引用

12th International Symposium on Mobile Mapping Technology, MMT 2023

作者： Cella, Marco d’Apolito, Francesco Fanta-Jende, Phillipp Sulzbachner, Christoph AIT – Austrian Institute of Technology Center for Vision Automation and Control – Assistive and Autonomous Systems Austria

Exploration is a fundamental problem in robotics that requires robots to navigate through unknown environments to autonomously gather information about their surroundings while executing collision-free paths. In this paper, we propose a method for producing smooth paths during the exploration process in indoor environments using UAVs to improve battery efficiency and enhance the quality of pose estimation. The developed framework is built by merging two approaches that represent the state of the art in the field of autonomous exploration with UAVs. The overall exploration logic is given by GLocal, a paper that introduces an hybrid, i.e. both sampling-based and frontier-based, framework that is able to cope with the issue of odometry drift when exploring indoor environments due to the absence of absolute localization, e.g. through GNSS. The second paper is FUEL, which introduces a frontier-based exploration methodology which computes the drone’s path as an optimized non-uniform B-Spline. The framework described in this paper borrows the optimized B-Spline trajectory generation from FUEL and implements it in GLocal. The presented system is evaluated in two different simulated environments, which show the pros and the cons of such method. © Author(s) 2023.

关键词： Motion planning

来源：评论

学校读者我要写书评

暂无评论

Towards SHACL-based Knowledge Graph Transformation of Visual Domain Knowledge 20

Towards SHACL-based Knowledge Graph Transformation of Visual...

引用

Joint of Posters, Demos, Workshops, and Tutorials of the 20th International Conference on Semantic Systems, SEMANTiCS-PDWT 2024

作者： Bischof, Stefan Filtz, Erwin Parreira, Josiane Xavier Steyskal, Simon Baumgart, Michael Gruber, David Liebetreu, Maximilian Rötzer, Florian Strommer, Stephan Siemens AG Österreich Vienna Austria AIT Austrian Institute of Technology GmbH Center for Vision Automation & Control Vienna Austria

Effective knowledge representation plays a pivotal role in harnessing the full potential of domain-specific *** tools like Infinity Maps, domain knowledge can be easily captured in a visual ***, translating these visually intuitive representations to formal, machine-processable formats often necessitates expert knowledge, thereby creating a significant barrier between domain experts and knowledge *** domain experts possess deep understanding of their respective domains, they often lack the formalisation skills required to transform this knowledge into machine-readable ***, knowledge engineers can design and implement sophisticated knowledge graphs, but may not have access to the domain-specific expertise necessary for effective knowledge *** address this challenge, we propose a novel approach that leverages SHACL (Shape Constraint Language) rules to transform visual domain knowledge expressed as Infinity Maps into knowledge *** method enables domain experts to define their knowledge structures using familiar Infinity Map representations, which are then transformed into standardised knowledge graphs compliant with the SHACL standard. © 2024 Copyright for this paper by its authors.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Reinforcement Learning Training Environment for Fixed Wing UAV Collision Avoidance 21

Reinforcement Learning Training Environment for Fixed Wing U...

引用

21st IFAC Conference on Technology, Culture and International Stability, TECIS 2022

作者： d'Apolito, Francesco AIT - Austrian Institute of Technology Vision Automation and Control Center Austria

In recent years, Unmanned Aerial Vehicles (UAVs) are emerging as a key technology with possible uses for several applications. To fully exploit their potential, UAVs needs to be able to be fully automatized and they need to be allowed to go Beyond Visual Line of Sight (BVLOS). Nowadays, autopilots and Detect and Avoid (DAA) systems, essential components for BVLOS operations, are developed with classical control approaches and classical algorithm for identification and avoidance of collision in the airspace. However, new methods based on Artificial Intelligence and, in particular, on Reinforcement Learning are attracting scientific interest. In order to train an agent with Reinforcement Learning methods, the development of the training environment is of utmost importance. This paper aims to present the development of a training environment to train an agent to avoid collisions in the airspace by setting desired values of roll, pitch and throttle. It will describe the developed training environment and the PID controllers implemented for allowing the own aircraft to receive the roll, pitch and throttle commands and to control the intruders' trajectory. Copyright © 2022 The Authors.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Timbervision: A Multi-Task Dataset and Framework for Log-Component Segmentation and Tracking in Autonomous Forestry Operations

TimberVision: A Multi-Task Dataset and Framework for Log-Com...

引用

IEEE Workshop on Applications of Computer vision (WACV)

作者： Daniel Steininger Julia Simon Andreas Trondl Markus Murschitz AIT Austrian Institute of Technology (Center for Vision Automation & Control)

ISBN: (数字)9798331510831

ISBN: (纸本)9798331510848

关键词： Accuracy Three-dimensional displays Fuses Forestry Object detection Vegetation Multitasking Robustness Real-time systems Safety

来源：评论

学校读者我要写书评

暂无评论

A Robust LiDAR-Based Indoor Exploration Framework For UAVs in Uncooperative Environments

A Robust LiDAR-Based Indoor Exploration Framework For UAVs i...

引用

International Conference on Unmanned Aircraft Systems (ICUAS)

作者： Wolfgang Bolz Marco Cella Noah Maikisch Francesco Vultaggio Francesco D’Apolito Felix Bruckmüller Christoph Sulzbachner Phillipp Fanta-Jende Austrian Institute of Technology - Center for Vision Automation and Control

ISBN: (数字)9798350357882

ISBN: (纸本)9798350357899

This paper introduces a robust frame-work for autonomous exploration using UAVs in uncooperative indoor environments, i.e. destroyed, unknown, and with limited visibility. The proposed system integrates a LiDAR-based Simultaneous Localization and Mapping (SLAM) algorithm, a Euclidian/Truncated Signed Distance Field (E/TSDF) mapping approach, a frontier-based exploration logic, a B-Spline motion planner, and a parallel Collision Avoidance (CA) module to ensure safe and efficient navigation through unexplored areas in real-time. Successful validation in simulated environments demonstrates the system's robustness in handling real-world issues such as odometry uncertainty, depleted point clouds, and intermittent networking in distributed setups.

关键词： Point cloud compression Simultaneous localization and mapping Uncertainty Aircraft navigation Robustness Real-time systems Indoor environment

来源：评论

学校读者我要写书评

暂无评论

Timbervision: A Multi-Task Dataset and Framework for Log-Component Segmentation and Tracking in Autonomous Forestry Operations

arXiv

引用

arXiv 2025年

作者： Steininger, Daniel Simon, Julia Trondl, Andreas Murschitz, Markus AIT Austrian Institute of Technology Center for Vision Automation & Control Austria

关键词： Logging (forestry)

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：