24,731 research outputs found
WiFi CSI-Based Long-Range Through-Wall Human Activity Recognition with the ESP32
No full text<p><strong>WiFi CSI-Based Long-Range Through-Wall Human Activity Recognition with the ESP32</strong></p>
<p>This repository contains the WiFi CSI human presence detection and activity recognition datasets proposed in [1].</p>
<p><strong>Datasets</strong></p>
<ul>
<li><strong>DP_LOS</strong> - Line-of-sight (LOS) presence detection dataset, comprised of 392 CSI amplitude spectrograms.</li>
<li><strong>DP_NLOS </strong>- Non-line-of-sight (NLOS) presence detection dataset, comprised of 384 CSI amplitude spectrograms.</li>
<li><strong>DA_LOS</strong> - LOS activity recognition dataset, comprised of 392 CSI amplitude spectrograms.</li>
<li><strong>DA_NLOS</strong> - NLOS activity recognition dataset, comprised of 384 CSI amplitude spectrograms.</li>
</ul>
<p>Table 1: Characteristics of presence detection and activity recognition datasets. </p>
<table>
<tbody>
<tr>
<td><strong>Dataset</strong></td>
<td><strong>Scenario</strong></td>
<td><strong>#Rooms</strong></td>
<td><strong>#Persons</strong></td>
<td><strong>#Classes</strong></td>
<td><strong>Packet Sending Rate</strong></td>
<td><strong>Interval </strong></td>
<td><strong>#Spectrograms</strong></td>
</tr>
<tr>
<td>DP_LOS</td>
<td>LOS</td>
<td>1</td>
<td>1</td>
<td>6</td>
<td>100Hz</td>
<td>4s (400 packets)</td>
<td>392</td>
</tr>
<tr>
<td>DP_NLOS</td>
<td>NLOS</td>
<td>5</td>
<td>1</td>
<td>6</td>
<td>100Hz</td>
<td>4s (400 packets)</td>
<td>384</td>
</tr>
<tr>
<td>DA_LOS</td>
<td>LOS</td>
<td>1</td>
<td>1</td>
<td>3</td>
<td>100Hz</td>
<td>4s (400 packets)</td>
<td>392</td>
</tr>
<tr>
<td>DA_NLOS</td>
<td>NLOS</td>
<td>5</td>
<td>1</td>
<td>3</td>
<td>100Hz</td>
<td>4s (400 packets)</td>
<td>384</td>
</tr>
</tbody>
</table>
<p> </p>
<p><strong>Data Format</strong></p>
<p>Each dataset employs an 8:1:1 training-validation-test split, defined in the provided label files <em>trainLabels.csv</em>, <em>validationLabels.csv</em>, and <em>testLabels.csv</em>. Label files use the sample format [<em>i c</em>], with <em>i</em> corresponding to the spectrogram index (i.png) and <em>c </em>corresponding to the class. For presence detection datasets (DP_LOS <em>, </em>DP_NLOS), c in {0 = "no presence", 1 = "presence in room 1", ..., 5 = "presence in room 5"}. For activity recognition datasets (DA_LOS <em>, </em>DA_NLOS), c in {0="no activity", 1="walking", and 2="walking + arm-waving"}. Furthermore, the mean and standard deviation of a given dataset are provided in <em>meanStd.csv</em>.</p>
<p><strong>Download and Use</strong><br>This data may be used for non-commercial research purposes only. If you publish material based on this data, we request that you include a reference to our paper [1].</p>
<p>[1] Strohmayer, Julian, and Martin Kampel. "WiFi CSI-Based Long-Range Through-Wall Human Activity Recognition with the ESP32" <em>International Conference on Computer Vision Systems</em>. Cham: Springer Nature Switzerland, 2023. </p>
<p>BibTeX citation:</p>
<pre>@inproceedings{strohmayer2023wifi,
title={WiFi CSI-Based Long-Range Through-Wall Human Activity Recognition with the ESP32},
author={Strohmayer, Julian and Kampel, Martin},
booktitle={International Conference on Computer Vision Systems},
pages={41--50},
year={2023},
organization={Springer}
}</pre>
Synthetic Depth & Thermal (SDT) Dataset
No full textThe Synthetic Depth & Thermal (SDT) dataset consists of 40k synthetic and 8k real depth and thermal stereo images, depicting human behavior in indoor environments. Included samples show uniquely posed lying, sitting and standing persons within four different room types (living room, bed room, bath room and kitchen), recorded from an elevated position. Furthermore, a fourth control class with empty rooms is provided as well. Both parts of SDT are balanced sets of these four classes and room types. The synthetic part of the dataset is intended to be used as training (and validation) data for uni-/multi-modal pose classification or person detection models, while the real part can be used to assess the generalization performance. To facilitate supervised training, pose labels and person bounding boxes are provided for all images. The real images in the dataset were captured by a multi-modal stereo camera system, consisting of an Orbbec Astra depth camera and a Flir Lepton 3.5 thermal camera, while synthetic images, which share the image characteristics of these cameras, were acquired through 3D rendering of virtual scenes within Blender and subsequent introduction of camera-specific noise.
Download and Use
The dataset is freely available for non-commerical research use. Please also cite our paper [1] when using the dataset for your research.
[1] Pramerdorfer Ch., Strohmayer J., Kampel M. “SDT: A synthetic multi-modal dataset for person detection and pose classification”, accepted at the Int. IEEE Conference in Image Processing (ICIP), Abu Dhabi, Oct. 2020
Jack Alive / Martin Dead : The Location of the "Author" in Jack London\u27s Martin Eden
No full textThis essay is an attempt to read Martin Eden, Jack Londonʼs autobiographical novel, in terms of the inextricable relationship between the author and the protagonist. Critics have often taken the unbalanced plot and the lack of ironic distance between narrator and character in Martin Eden as the technical weakness of London, but this paper argues that the achievement of this novel owes a great deal to the attachment of London to Martin. The unbalanced structure is a necessary product of the severe struggle of the author to kill his romantic alter ego. // Martin, who aspires to win Ruth Morse, tries to cross class boundaries by making a career of a writer. Even after realizing the emptiness of Ruth, who turns out to be nothing but a typical figure of the bourgeoisie, he somehow persists in loving her. The notion underlying here is that, for Martin, love, career and art are fundamentally inseparable. He objects to the aestheteʼs view of Brissenden on account of his separation of art from career. Martinʼs identity and life consist only in the triunity of love/career/art; the alternative is the repudiation of life. Thus, the unnatural delay of his disappointment in love can be regarded as Londonʼs strategy to set the suicide of Martin as the necessary consequence of the story. // By finishing the story and killing Martin, London finally detaches himself from Martin, reconstructs his self, and, unlike Martin, survives as a professional writer. In this sense, Martin Eden is a story about “writerʼs self-reconstruction.
Recommended from our members
Letter from Martin Chizzick
No full textCongratulations to Duane Pearsall for receiving the Enterpreneur of the Year award; note on the letter was written by Pearsall and it mentions that Martin, the author of the letter, died in a airplane accident
Robert Martin Tiffin's Mystery Man Newspaper Articles
No full textAdvertiser-Tribune newspaper clippings featuring a story about Robert Martin (written by Nancy Kleinhenz), a local author from Tiffin (Ohio) who wrote under the pseudonym of Lee Roberts, and two of his short stories. Martin wrote mystery novels in his spare time, creating more than 22 mystery novels. For more information about Robert Martin and a list of books go to http://www.mysteryfile.com/RMartin/JBennett.html
Experiences Using Large Scale Video Walls for Distance Education
No full textWe describe our experiences building and using the Rutgers Videowall, a low-cost telepresence system that has been used teaching 15 courses and colloquia. By relaxing typical spatial telepresence features, such as background continuity, we greatly reduced costs and gained flexibility in the rooms it could be deployed in. The lower costs and room flexibility enabled academic departments to use the wall, in contrast to traditional telepresence systems which remained inaccessible. We found that the Videowall’s spatial distortions did not have a significant impact on useability, as our initial survey results show that students had an overall positive experience.Technical report DCS-tr-72
Hans Martin Schwarz Collection 1934 - 1938
No full textThis collection contains clippings of articles by Hans Martin Schwarz (1917, Hamburg – 2006, New York, better known as Martin Ebon), published between 1934 and 1938 in German-Jewish newspapers on a wide variety of subjects such as sports, emigration, the political situation in Germany, and religious attitudes of the young. It also contains reviews of his books "Einer wie Du und Ich" and "Heiteres, Besinnliches, Nachdenkliches."digitizedHans Martin Schwarz (1917, Hamburg – 2006, New York, better known as Martin Ebon), was a journalist and author. In Germany during the 1930s, he published in a variety of German-Jewish periodicals, primarily the Israelitisches Familienblatt. After immigrating to the United States in 1938, he changed his name to Martin Ebon, and published dozens of books in the areas of world affairs and parapsychology.Processe
Interview with Father James Martin
Get PDFIn May 2011, the Ignatian Faculty Scholars at Regis University conducted a Skype interview with Father James Martin, S. J., author of The Jesuit Guide to Almost Everything. The Scholars had used Father Martin’s book as a text for their year of study, which focused on Ignatian Spirituality, the Ignatian Pedagogical Paradigm, and teaching and learning at a Jesuit university. The interview was transcribed and is printed below. Father Martin reflects on the book, and responds to questions about the book itself, about finding God in all learners, and about the Church
Menschliche Szenenrekonstruktion für städtische Such- und Rettungseinsätze
Get PDFStädtische Such- und Rettungseinsätze (USAR) in Post-Katastrophenumgebungen stellen kritische Herausforderungen für autonome Robotersysteme dar, insbesondere bei der Aufrechterhaltung einer genauen Lokalisierung während der Navigation durch dynamische Szenen mit Überlebenden und Rettungspersonal. Diese Arbeit präsentiert ein verteiltes Computer-Vision-System, das diese Herausforderungen bewältigt, indem es robuste Simultane Lokalisierung und Kartierung (SLAM) in von Menschen bevölkerten Katastrophenumgebungen ermöglicht, dabei gleichzeitig die Privatsphäre wahrt und innerhalb der Rechenbeschränkungen mobiler Roboterplattformen operiert. Das vorgeschlagene System teilt die Verarbeitung zwischen einem Edge-Gerät (NVIDIA Jetson Xavier AGX) und einem lokalen Server auf und implementiert eine Architektur, die menschenbewusstes visuelles SLAM mit datenschutzfreundlicher 3D-Rekonstruktion integriert. Das Edge-Modul führt Echtzeit-Tracking und menschliche Bewegungsanalyse durch, wobei semantische Maskierung und anthropometrische Beschränkungen in ein modifiziertes ORB-SLAM3-Framework [18] integriert werden. Das Server-Modul übernimmt die globale Optimierung und generiert hochauflösende 3D-Rekonstruktionen mittels Gaussian Splatting, während die Privatsphäre durch Schwärzung menschlicher Subjekte gewahrt bleibt. Die experimentelle Evaluation auf erweiterten RGB-D-Datensätzen zeigt, dass die Einbeziehung menschlicher Pose-Beschränkungen eine Reduzierung des Absoluten Trajektorienfehlers um 90,6% im Vergleich zu Baseline-SLAM-Systemen erreicht. Das System hält eine Genauigkeit unter 16cm in verschiedenen von Menschen bevölkerten Szenarien aufrecht. Diese Ergebnisse belegen die Praktikabilität von menschenbewusstem SLAM für den praktischen Einsatz in USAR-Operationen, wo eine genaue Navigation in dynamischen Umgebungen für den Missionserfolg entscheidend ist.Urban Search and Rescue (USAR) missions in post-disaster environments are challenging for autonomous robotic systems, particularly in maintaining accurate localization while navigating dynamic scenes populated with survivors and rescue personnel. This thesis presents a distributed computer vision system that addresses these challenges by enabling Simultaneous Localization and Mapping (SLAM) in human-populated disaster environments while preserving privacy and operating within computational constraints of mobile robotic platforms. The proposed system partitions processing between an edge device (NVIDIA Jetson Xavier AGX) and a local server, implementing an architecture that integrates human-aware visual SLAM with privacy-preserving 3D reconstruction. The edge module performs real-time tracking and human motion analysis, incorporating semantic masking and anthropometric constraints into a modified ORB-SLAM3 [18] framework. The server module generates high-fidelity 3D reconstructions using Gaussian Splatting while maintaining privacy through redaction of human subjects. Experimental evaluation on RGB-D datasets demonstrates that incorporating human pose constraints achieves a 90.6% reduction in Absolute Trajectory Error compared to baseline SLAM systems. The system maintains sub-16cm accuracy in diverse human-populated scenarios. These results establish the viability of human-aware SLAM for practical deployment in USAR operations, where accurate navigation in dynamic environments is essential for mission success
- …
