检索结果-内蒙古大学图书馆

27th International Conference on Pattern Recognition, ICPR 2024

作者： Wu, Chengzhi Wang, Kaige Zhong, Zeyun Fu, Hao Zheng, Junwei Zhang, Jiaming Pfrommer, Julius Beyerer, Jürgen Institute for Anthropomatics and Robotics Karlsruhe Institute of Technology Karlsruhe Germany Fraunhofer Institute of Optronics System Technologies and Image Exploitation IOSB Karlsruhe Germany

ISBN: (纸本)9783031783944

In recent years, there have been significant advancements in applying attention mechanisms to point cloud analysis. However, attention module variants featured in various research papers often operate under diverse settings and tasks, incorporating potential training strategies. This heterogeneity poses challenges in establishing a fair comparison among these attention module variants. In this paper, we address this issue by rethinking and exploring attention module design within a consistent base framework and settings. Both global-based and local-based attention methods are studied, with a focus on the selection basis and scales of neighbors for local-based attention. Different combinations of aggregated local features and computation methods for attention scores are evaluated, ranging from the initial addition/concatenation-based approach to the widely adopted dot product-based method and the recently proposed vector attention technique. Various position encoding methods are also investigated. Our extensive experimental analysis reveals that there is no universally optimal design across diverse point cloud tasks. Instead, drawing from best practices, we propose tailored attention modules for specific tasks, leading to superior performance on point cloud classification and segmentation benchmarks. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Attention mechanism Module design exploration. Point cloud data

来源：评论

学校读者我要写书评

暂无评论

An Evaluation of Virtual Reality for Terrain Assessment 25th

An Evaluation of Virtual Reality for Terrain Assessment

引用

25th International Conference on Human-Computer Interaction, HCII 2023

作者： Wagner, Boris Hoppe, Adrian H. van de Camp, Florian Maier, Sebastian Fraunhofer Institute of Optronics System Technologies and Image Exploitation IOSB Karlsruhe76131 Germany

ISBN: (纸本)9783031360039

With the availability of quickly created and inexpensive 3D representations of the real world, it is important to investigate whether users can derive additional value from them, particularly when combined with the possibilities of Virtual Reality (VR) visualization. To evaluate possible benefits, a study was conducted which focused on the specific tasks of aerial image analysts and covered the use of 3D geodata in terrain assessment. The study compared the use of 3D geodata in VR with 2D displays, using a digital orthophoto with 20 cm resolution and digital terrain models from the ASTER system. The task for the user was to find a route with minimal gradient between a start and destination point while avoiding steep gradients. The base map used was a digital orthophoto in 20 cm resolution (DOP20). In 2D, the height information was conveyed by isohypses. In VR, the digital terrain model (DTM) from the ASTER system was used. The results of the evaluation showed that the actual task goal, the lowest maximum gradient, was best achieved in VR. However, the subjects needed considerably more time to complete the tasks in VR. In VR, the test persons were also more cautious, they planned the routes considerably longer, but as already mentioned, they achieved the objective better. Overall, the results of this study suggest that while VR may offer added value in terrain assessment, it may not be as efficient as 2D planning for those trained in map reading. However, for new users or those who are less familiar with the terrain, VR may offer a more intuitive and immersive experience, allowing them to better understand and interpret the data. Further research is needed to fully understand the potential benefits and limitations of using VR for terrain assessment and to identify the most appropriate use cases for this technology. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Virtual reality

来源：评论

学校读者我要写书评

暂无评论

Improving Self-Supervised Segmentation of Urban Scenes using NDSM-Enhanced CRF 5

Improving Self-Supervised Segmentation of Urban Scenes using...

引用

Land Surface and Cryosphere Remote Sensing V 2024

作者： Qiu, Kevin Wagenbach, Lars Bulatov, Dimitri Iwaszczuk, Dorota Fraunhofer Institute of Optronics System Technologies and Image Exploitation Ettlingen76275 Germany Technical University of Darmstadt Darmstadt64287 Germany

ISBN: (数字)9781510682696

ISBN: (纸本)9781510682689

Semantic segmentation of urban areas is crucial for many applications. Self-supervised networks require few or no labels for training, making them highly appealing approaches. One such network is STEGO1, which builds upon DINO2 and operates without any labeled data, yet effectively segments buildings, vegetation, and roads in the ISPRS Potsdam dataset3. The resulting segmentations are refined using Conditional Random Fields (CRF). In remote sensing, additional channels like the Normalized Digital Surface Model (NDSM) enhance the segmentation task, as pixels of the same class often exhibit similar elevation characteristics, especially when adjacent. Since the transformer-based DINO network is built for RGB data, we extend the CRF with NDSM information to overcome this limitation, introducing a second pairwise potential that encourages neighboring pixels with similar elevation to have the same label. For evaluation in both the linear and cluster probe, we employ Adjusted Mutual Information (AMI) and Adjusted Rand Index (ARI) to assess the segmentation against the six classes of the Potsdam dataset, besides standard IoU and accuracy metrics. Enhancing the CRF with elevation information improves the mIoU by 0.83% over the RGB only baseline in the cluster probe, which constitutes a considerable improvement. © 2025 SPIE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Applying Differential Privacy to Medical Questionnaires

Applying Differential Privacy to Medical Questionnaires

引用

2023 IEEE International Conference on Pervasive Computing and Communications Workshops and other Affiliated Events, PerCom Workshops 2023

作者： Appenzeller, Arno Terzer, Nick Philipp, Patrick Beyerer, Jurgen Karlsruhe Germany Fraunhofer Institute of Optronics System Technologies and Image Exploitation Iosb Karlsruhe Germany

ISBN: (纸本)9781665453813

Currently, the medical sector sees a lot of digitization efforts. Besides the already available and growing amount of data there is still a need to receive data from patients. A special form of data donation are medical questionnaires. They come with a fixed set of questions regarding medical conditions and can be performed regularly or once. Such data donations show promising potential for research but come with open questions regarding privacy. There are many examples that show that re-identification is even possible with anonymized data. To mitigate such risks privacy enhancing technologies like Differential Privacy (DP) can be used. This paper presents a procedure for privacy preserving questionnaires using an implementation of DP called RAPPOR. Through its Randomized Response mechanism RAPPOR is well suited to be used with questionnaires. To proof feasibility of this procedure various experiments are conducted that show that this approach can improve privacy while still retaining a good level of utility. © 2023 IEEE.

关键词： Privacy-preserving techniques

来源：评论

学校读者我要写书评

暂无评论

Simultaneous measurement of surface geometry and film thickness distribution by retroreflex ellipsometry

Simultaneous measurement of surface geometry and film thickn...

引用

作者： Chen, Chia-Wei Hartrumpf, Matthias Längle, Thomas Beyerer, Jürgen Fraunhofer Institute of Optronics System Technologies and Image Exploitation IOSB Karlsruhe Germany Karlsruhe Germany

A holistic approach to determine the surface orientation and film thickness for nonplanar isotropic three-phase systems (ambient-film-substrate) by retroreflex ellipsometry is presented. After scanning the surface of the sample, the ellipsometric parameters (Ψ, Δ), the surface orientation (θ0,) and the film thickness d can be measured simultaneously. Then, the surface geometry can be reconstructed by numerical gradient integration. The influence of the spot size and incident angle on the measurement results is simulated and discussed. The experiments show satisfactory results for film thickness distribution and surface geometry, which prove that the method is capable of measuring nonplanar surfaces. © 2024

关键词： Film thickness

来源：评论

学校读者我要写书评

暂无评论

A multimode quantum optics approach to incoherent imaging

A multimode quantum optics approach to incoherent imaging

引用

London Imaging Meeting, LIM 2024

作者： Sorelli, Giacomo Fraunhofer IOSB Ettlingen Fraunhofer Institute of Optronics System Technologies and Image Exploitation Gutleuthausstr. 1 Ettlingen76275 Germany

ISBN: (纸本)9780892083671

Recent works employing tools from quantum optics and quantum metrology proposed a new passive imaging technique that allows to resolve details far below the diffraction limit. This technique is based on replacing standard spatially-resolved intensity measurements, e.g. at each pixel of a camera, with spatial-mode demultiplexing (SpaDe) measurements that allow to acquire information in a more efficient way. In this contribution, we want to provide an intuitive explanation of why such a SpaDe approach is so effective, and illustrate how we used these idea to discriminate one point source from two, and to estimate the separation between two incoherent sources. © 2024 Society for Imaging Science and Technology.

关键词： Quantum optics

来源：评论

学校读者我要写书评

暂无评论

DustNet++: Deep Learning-Based Visual Regression for Dust Density Estimation

引用

International Journal of Computer Vision 2025年第7期133卷 1-25页

作者： Michel, Andreas Weinmann, Martin Kuester, Jannick AlNasser, Faisal Gomez, Tomas Falvey, Mark Schmitz, Rainer Middelmann, Wolfgang Hinz, Stefan Fraunhofer Institute of Optronics System Technologies and Image Exploitation IOSB Ettlingen Germany Institute of Photogrammetry and Remote Sensing Karlsruhe Institute of Technology Karlsruhe Germany Department of Civil and Environmental Engineering Massachusetts Institute of Technology Cambridge United States Meteodata Santiago Chile

Detecting airborne dust in standard RGB images presents significant challenges. Nevertheless, the monitoring of airborne dust holds substantial potential benefits for climate protection, environmentally sustainable construction, scientific research, and various other fields. To develop an efficient and robust algorithm for airborne dust monitoring, several hurdles have to be addressed. Airborne dust can be opaque or translucent, exhibit considerable variation in density, and possess indistinct boundaries. Moreover, distinguishing dust from other atmospheric phenomena, such as fog or clouds, can be particularly challenging. To meet the demand for a high-performing and reliable method for monitoring airborne dust, we introduce DustNet++, a neural network designed for dust density estimation. DustNet++ leverages feature maps from multiple resolution scales and semantic levels through window and grid attention mechanisms to maintain a sparse, globally effective receptive field with linear complexity. To validate our approach, we benchmark the performance of DustNet++ against existing methods from the domains of crowd counting and monocular depth estimation using the Meteodata airborne dust dataset and the URDE binary dust segmentation dataset. Our findings demonstrate that DustNet++ surpasses comparative methodologies in terms of regression and localization capabilities. © The Author(s) 2025.

关键词： Dust

来源：评论

学校读者我要写书评

暂无评论

Power in the fiber for atmospheric turbulence-affected laser beams 6

Power in the fiber for atmospheric turbulence-affected laser...

引用

Environmental Effects on Light Propagation and Adaptive systems VI 2023

作者： Toselli, Italo Fraunhofer IOSB Ettlingen Fraunhofer Institute of Optronics System Technologies and Image Exploitation Gutleuthausstr. 1 Ettlingen76275 Germany

ISBN: (纸本)9781510666917

The analysis of budget link and free space optical system performances requires the calculation of several metrics of the atmospheric turbulence-affected collected light. In this paper, assuming the collected light is focused into an optical fiber positioned in the focal plane, we use the ABCD ray-matrix representation to show the impact of Kolmogorov and non-Kolmogorov turbulence on the Power in the Fiber (PIF). Calculation of the PIF requires also the knowledge of the transmitted average power that enters the receiver aperture (power in the bucket) and the long-term beam spread in the focal plane. © 2023 SPIE.

关键词： Atmospheric turbulence

来源：评论

学校读者我要写书评

暂无评论

Area reconnaissance with heterogeneous groups of autonomous systems 8

Area reconnaissance with heterogeneous groups of autonomous ...

引用

Emerging Imaging and Sensing technologies for Security and Defence VIII 2023

作者： Tchouchenkov, I. Segor, F. Buller, A. Kollmann, M. Fraunhofer Institute of Optronics System Technologies and Image Exploitation IOSB Fraunhoferstr.1 Karlsruhe76133 Germany

ISBN: (纸本)9781510667099

In the last years Unmanned Vehicles for different environments (UxVs) have been recognized as relevant game changers and key technologies for a wide range of military and civilian applications. Even parallel deployment of heterogeneous autonomous assets as swarms or cooperating teams is no longer science fiction, but a realistic operational scenario. Their effectiveness can be significantly increased by optimization of number, capabilities and application strategy of assigned assets, particularly in time-critical tasks (e.g. the search for missing persons, disaster relief and modern warfare operations). Especially, the movements of the vehicles must be carefully managed. However, the use of small UxVs is often accompanied by limitations like short mission time and limited sensor coverage, which in turn can be compensated by the intelligent assignment of vehicles with increased autonomy in cooperating groups. An important basis for efficient and effective autonomous reconnaissance, especially in swarming or teaming scenarios, is movement optimization considering the capabilities of the heterogeneous vehicles equipped with different sensor systems operating in a combined mission. For this purpose, algorithms have been developed at fraunhofer IOSB that enable appropriate planning and dynamic processing in very different situations for heterogeneous groups of cooperating vehicles. In the following, two exploration methods for reconnaissance missions are described in more detail and their possibilities are discussed and compared. © 2023 SPIE.

关键词： Drones

来源：评论

学校读者我要写书评

暂无评论

CNN based track detection in coherent SAR imagery: A distinction between foot and vehicle tracks 14

CNN based track detection in coherent SAR imagery: A distinc...

引用

Earth Resources and Environmental Remote Sensing/GIS Applications XIV 2023

作者： Kuny, Silvia Hammer, Horst Thiele, Antje Fraunhofer Institute of Optronics System Technologies and Image Exploitation IOSB Gutleuthausstrasse 1 EttlingenD-76275 Germany

ISBN: (纸本)9781510666979

The goal of this paper is to assess the capability of a CNN based algorithm to detect vehicle and foot tracks and to distinguish them. The used CNN architecture has already proven to be very effective for the segmentation of vehicle tracks in previous work and thus was chosen for this investigation. Foot tracks in general are of a poorer distinctness and not as linear or constant as vehicle tracks. Also, when heavily overlapping, the signatures of foot tracks lose some of their structural features and instead are more likely to be distinguishable by their texture. Thus, two approaches for segmentation labeling are investigated: First, a line-based labeling, which considers the individual tracks;and second a region-based labeling, allowing for textural features. How well these two labeling approaches perform, is tested and results are shown regarding the detection of foot tracks and their distinction from vehicle tracks. © 2023 SPIE. All rights reserved.

关键词： Vehicles

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：