Lisandro Roldan’s Post

The Fraunhofer ITWM is celebrating its premiere at SMM 2024. Researchers from the Fraunhofer Institute for Industrial Mathematics ITWM present the MESHFREE tool, which simulates complex processes - such as moving ships and their interactionwith waves, tank sloshing, spray cleaning, flooding or floating bridges - with great time savings andtherefore cost-effectively. The grid-free method is superior to conventional software, which often doesnot map such highly dynamic processes satisfactorily. This allows us to identify optimization potentialat an early design stage. MESHFREE was awarded the Joseph von Fraunhofer Prize 2024 for this. We will be presenting many other projects at our joint stand. We, that is: Fraunhofer IFAM, Fraunhofer IGP, Fraunhofer ITWM, Fraunhofer LBF and Fraunhofer CML. #FraunhoferIFAM #FraunhoferIGP #FraunhoferITWM #FraunhoferLBF #FraunhoferCML #SMMfair #InnovationInShipping #ArtificialIntelligence

🐝 WeBEEnar 🐝 👀 Are you interested in the latest #digital innovations for the #beekeeping sector? JOIN US! ⬇️ 📢 On January 27th at 12:00 CET time our CEO Iratxe Perales will present NosemAI, our latest development to support nosemosis #diagnosis in #beehives. The event is coordinated and organized by BeSafeBeeHoney. 🔬 Want to learn how to use this automated tool and how #accurate it is? REGISTER! #apiculture #AI #microscopy #veterinarians

I’m thrilled to announce that our paper titled “Edge Detection Based on Soft Piezoelectric Tactile Sensing System and Machine Learning” has been accepted at the AISEM Conference in Trento, Italy! This paper presents a tactile sensing system for edge detection based on a flexible piezoelectric sensing array (P(VDF-TrFE)) combined with machine learning. A set of features was extracted from the tactile signals and used to train a Support Vector Machine (SVM) model, achieving an accuracy of 90.21% in edge classification. #AISEM2025 #MachineLearning #TactileSensing #Piezoelectric #EdgeDetection

📢 The items have been tested on more than 4000 pupils in 6 countries in Europe. Did the sentence above get your attention? Good. From time to time, I like to share our (VU and partners) projects content on Linkedin. Updates about the processes, important milestones, events, achievements, etc. Below you can check out the interview with Pekka Räsänen, Daranee Lehtonen and Arnold Pears on YouTube, which in my biased opinion, greatly describes what researchers are doing on CT&MathABLE project, what the goals are, current achievements, and what interesting data is analysed. Those who are interested in computation thinking or/and algebraic thinking, join us in on Linkedin group: https://lnkd.in/ePTpdviM More about the project: https://lnkd.in/eR3e7Du9 Instagram: ct_mathable Valentina Dagienė, Tugba Ozturk, ismail güven, Rumbus Anikó, Pál Sarmasági, Zsuzsa Pluhár, Javier Bilbao, Asta Jankauskiene, Heidi Kaarto

Thank you to everyone who visited our poster at #MICCAI2024 and contributed to such insightful discussions! I sincerely appreciate the engaging conversations and valuable feedback. For those interested in diving deeper into the research, you can explore our paper [https://lnkd.in/efgx4H6h]. Stay tuned for more papers expanding on this work, and look out for additional presentations from our lab throughout the rest of the conference. #MedicalImageAnalysis #ComputerVision #MachineLearning #VideoUnderstanding

🚀 We are thrilled to unveil our latest innovation: the new laser scanning confocal FLIM platform. 🌟 This cutting-edge addition perfectly complements our existing range of HORIBA FLIM solutions, promising exciting possibilities for our customers. Our fully automated InverScan system promises to revolutionize workflows, making experimentation smoother and more efficient than ever before. With intuitive controls and seamless integration, researchers can expect a hassle-free experience from start to finish. But that's not all! 🎉 Our EzTime Image software takes productivity to new heights, offering a user-friendly interface that enhances both experimentation and data analysis. Say goodbye to unnecessary complexity and hello to streamlined processes. And for those developing fluorescence probes, look no further than our promotional Duetta 2-in-1 fluorescence and absorbance spectrometer. 🌈 It's the perfect tool for characterizing your creations, providing accurate and reliable results every time. Exciting times lie ahead, and we can't wait to see how our latest innovations empower researchers around the globe. Stay tuned for more updates and insights. #FLIM #Innovation #ResearchTools 🛠️🔬

I am excited to share that our latest work on Referring Atomic Video Action Recognition (RAVAR) is accepted by ECCV2024! Thanks all of the coauthors for their great works.🎥🔍 We introduce RAVAR, a novel task focused on identifying atomic actions of specific individuals in video data based on textual descriptions, which is a new VLM task, in this paper. The arxiv version is available here, https://lnkd.in/eyXXMm5i. Another paper is accepted by IROS2024 with the topic skeleton-based human action recognition under noisy label. https://lnkd.in/e58sVAdR #ComputerVision #MachineLearning #VLM #ECCV2024 #IROS2024 #ActionRecognition

✨✨✨ LRPL-VIO: A Lightweight and Robust Visual–Inertial Odometry with Point and Line Features 🧑🔬 Feixiang Zheng, Lu Zhou, Wanbiao Lin, Jingyang Liu, Lei Sun 🏫 Nankai University 🚩 Visual-inertial odometry (#VIO) algorithms, fusing #various #features such as points and lines, are able to improve their performance in challenging scenes while the running time severely increases. In this paper, we propose a novel lightweight point–line visual–inertial odometry algorithm to solve this problem, called LRPL-VIO. Firstly, a fast line matching method is proposed based on the assumption that the #photometric #values of endpoints and midpoints are invariant between #consecutive #frames, which greatly reduces the time consumption of the #front end. Then, an efficient filter-based state estimation framework is designed to finish information fusion (point, line, and inertial). Fresh measurements of line features with good tracking quality are selected for state estimation using a unique feature selection scheme, which improves the efficiency of the proposed algorithm. Finally, validation experiments are conducted on public datasets and in real-world tests to evaluate the performance of LRPL-VIO and the results show that we outperform other state-of-the-art algorithms especially in terms of speed and robustness. https://lnkd.in/ebspvifB

Infinite-dimensional Geometry: Theory and Applications Alice Barbora Tumpach Erwin schrödinger institute https://lnkd.in/eQ3Z6vEQ The aim of the project is to reinforce the collaboration between scientists from Austrian research institutions and international institutions around the topic of infinite dimensional geometry. Direct applications of the theoretical aspects of infinite dimensional geometry to shape analysis and medical imaging are part of the program. The programme will last five 5 weeks, each devoted to different topic ranging from abstract theoretical questions to very concrete applications (e.g. medical). Each week mini-courses lecturers and keynote speakers will share their understanding on particular topics. Short talks from the participants will complete the programme. Week 1: Geometric structures and infinite-dimensional manifolds Week 2: Dynamical systems and infinite-dimensional manifolds Week 3: Homeomorphisms of S^1 and their extensions Week 4: Shape Analysis and Geometry Week 5: Shape Analysis and Medical Applications

Sally returns with new insights on EQAS informatics, diving into personalised feedback, graphical results, and how our OASYS system benchmarks your lab’s performance globally. Got questions? Get in touch via eqas@nrlquality.org.au or ask Sally below! #scienceofquality #asksally