In mobile robotics, LASER scanners have a wide spectrum of indoor and outdoor applications, both in structured and unstructured environments, due to their accuracy and precision. Most works that use this sensor have their own data representation and their own case-specific modeling strategies, and no common formalism is adopted. To address this issue, this manuscript presents an analytical approach for the identification and localization of objects using 2D LiDARs. Our main contribution lies in formally defining LASER sensor measurements and their representation, the identification of objects, their main properties, and their location in a scene. We validate our proposal with experiments in generic semi-structured environments common in autonomous navigation, and we demonstrate its feasibility in multiple object detection and identification, strictly following its analytical representation. Finally, our proposal further encourages and facilitates the design, modeling, and implementation of other applications that use LASER scanners as a distance sensor.
DOCUMENT
This article deals with automatic object recognition. The goal is that in a certain grey-level image, possibly containing many objects, a certain object can be recognized and localized, based upon its shape. The assumption is that this shape has no special characteristics on which a dedicated recognition algorithm can be based (e.g. if we know that the object is circular, we could use a Hough transform or if we know that it is the only object with grey level 90, we can simply use thresholding). Our starting point is an object with a random shape. The image in which the object is searched is called the Search Image. A well known technique for this is Template Matching, which is described first.
DOCUMENT
In recent years, drones have increasingly supported First Responders (FRs) in monitoring incidents and providing additional information. However, analysing drone footage is time-intensive and cognitively demanding. In this research, we investigate the use of AI models for the detection of humans in drone footage to aid FRs in tasks such as locating victims. Detecting small-scale objects, particularly humans from high altitudes, poses a challenge for AI systems. We present first steps of introducing and evaluating a series of YOLOv8 Convolutional Neural Networks (CNNs) for human detection from drone images. The models are fine-tuned on a created drone image dataset of the Dutch Fire Services and were able to achieve a 53.1% F1-Score, identifying 439 out of 825 humans in the test dataset. These preliminary findings, validated by an incident commander, highlight the promising utility of these models. Ongoing efforts aim to further refine the models and explore additional technologies.
MULTIFILE
The increasing amount of electronic waste (e-waste) urgently requires the use of innovative solutions within the circular economy models in this industry. Sorting of e-waste in a proper manner are essential for the recovery of valuable materials and minimizing environmental problems. The conventional e-waste sorting models are time-consuming processes, which involve laborious manual classification of complex and diverse electronic components. Moreover, the sector is lacking in skilled labor, thus making automation in sorting procedures is an urgent necessity. The project “AdapSort: Adaptive AI for Sorting E-Waste” aims to develop an adaptable AI-based system for optimal and efficient e-waste sorting. The project combines deep learning object detection algorithms with open-world vision-language models to enable adaptive AI models that incorporate operator feedback as part of a continuous learning process. The project initiates with problem analysis, including use case definition, requirement specification, and collection of labeled image data. AI models will be trained and deployed on edge devices for real-time sorting and scalability. Then, the feasibility of developing adaptive AI models that capture the state-of-the-art open-world vision-language models will be investigated. The human-in-the-loop learning is an important feature of this phase, wherein the user is enabled to provide ongoing feedback about how to refine the model further. An interface will be constructed to enable human intervention to facilitate real-time improvement of classification accuracy and sorting of different items. Finally, the project will deliver a proof of concept for the AI-based sorter, validated through selected use cases in collaboration with industrial partners. By integrating AI with human feedback, this project aims to facilitate e-waste management and serve as a foundation for larger projects.
‘Dieren in de dijk’ aims to address the issue of animal burrows in earthen levees, which compromise the integrity of flood protection systems in low-lying areas. Earthen levees attract animals that dig tunnels and cause damages, yet there is limited scientific knowledge on the extent of the problem and effective approaches to mitigate the risk. Recent experimental research has demonstrated the severe impact of animal burrows on levee safety, raising concerns among levee management authorities. The consortium's ambition is to provide levee managers with validated action perspectives for managing animal burrows, transitioning from a reactive to a proactive risk-based management approach. The objectives of the project include improving failure probability estimation in levee sections with animal burrows and enhancing risk mitigation capacity. This involves understanding animal behavior and failure processes, reviewing existing and testing new deterrence, detection, and monitoring approaches, and offering action perspectives for levee managers. Results will be integrated into an open-access wiki-platform for guidance of professionals and in education of the next generation. The project's methodology involves focus groups to review the state-of-the-art and set the scene for subsequent steps, fact-finding fieldwork to develop and evaluate risk reduction measures, modeling failure processes, and processing diverse quantitative and qualitative data. Progress workshops and collaboration with stakeholders will ensure relevant and supported solutions. By addressing the knowledge gaps and providing practical guidance, the project aims to enable levee managers to effectively manage animal burrows in levees, both during routine maintenance and high-water emergencies. With the increasing frequency of high river discharges and storm surges due to climate change, early detection and repair of animal burrows become even more crucial. The project's outcomes will contribute to a long-term vision of proactive risk-based management for levees, safeguarding the Netherlands and Belgium against flood risks.
Rotating machinery, such as centrifugal pumps, turbines, bearings, and other critical systems, is the backbone of various industrial processes. Their failures can lead to significant maintenance costs and downtime. To ensure their continuous operation, we propose a fault diagnosis and monitoring framework that leverages the innovative use of acoustic sensors for early fault detection, especially in components less accessible for traditional vibration-based monitoring strategies. The main objective of the proposed project is to develop a fault diagnosis and monitoring framework for rotating machinery, including the fusion of acoustic sensors and physics-based models. By combining real-time monitoring data from acoustic sensors with an understanding of first principles, the framework will enable maintenance practitioners to identify and categorize different failure modes such as wear, fatigue, cavitation, reduced flow, bearing damage, impeller damage, misalignment, etc. In the initial phase, the focus will be on centrifugal pumps using the existing test set-up at the University of Twente. Sorama specializes in acoustic sensors to locate noise sources and will provide acoustic cameras to capture sound patterns related to pump deterioration during various operating conditions. These acoustic signals will then be correlated with the different failure modes and mechanisms that will be described by physics-based models, such as wear, fatigue, cavitation, corrosion, etc. Furthermore, a recently published data set by the Dynamics Based Maintenance research group that includes vibration analysis data and motor current analysis data of various fault scenarios, such as mentioned above, will be used as validation. The anticipated outcome of this project is a versatile framework for a physics-informed acoustic monitoring system. This system is designed to enhance early fault detection significantly, reducing maintenance costs and downtime across a broad spectrum of industrial applications, from centrifugal pumps to turbines, bearings, and beyond.
