Refine
Department, Institute
- Fachbereich Informatik (30) (remove)
Document Type
- Conference Object (16)
- Article (8)
- Part of a Book (2)
- Patent (2)
- Report (2)
Year of publication
Keywords
- machine learning (2)
- Circular saws (1)
- Exergame (1)
- Field sequential imaging (1)
- Hand injuries (1)
- Light curtain (1)
- MOOC (1)
- NIR (1)
- Protective system (1)
- Safety guard (1)
The choice of suitable semiconducting metal oxide (MOX) gas sensors for the detection of a specific gas or gas mixture is time-consuming since the sensor’s sensitivity needs to be characterized at multiple temperatures to find its optimal operating conditions. To obtain reliable measurement results, it is very important that the power for the sensor’s integrated heater is stable, regulated and error-free (or error-tolerant). Especially the error-free requirement can be only be achieved if the power supply implements failure-avoiding and failure-detection methods. The biggest challenge is deriving multiple different voltages from a common supply in an efficient way while keeping the system as small and lightweight as possible. This work presents a reliable, compact, embedded system that addresses the power supply requirements for fully automated simultaneous sensor characterization for up to 16 sensors at multiple temperatures. The system implements efficient (avg. 83.3% efficiency) voltage conversion with low ripple output (<32 mV) and supports static or temperature-cycled heating modes. Voltage and current of each channel are constantly monitored and regulated to guarantee reliable operation. To evaluate the proposed design, 16 sensors were screened. The results are shown in the experimental part of this work.
The proper use of protective hoods on panel saws should reliably prevent severe injuries from (hand) contact with the blade or material kickbacks. It also should minimize long-term lung damages from fine-particle pollution. To achieve both purposes the hood must be adjusted properly by the operator for each workpiece to fit its height. After a work process is finished, the hood must be lowered down completely to the bench. Unfortunately, in practice the protective hood is fixed at a high position for most of the work time and herein loses its safety features. A system for an automatic height adjustment of the hood would increase comfort and safety. If the system can distinguish between workpieces and skin reliably, it furthermore will reduce occupational hazards for panel saw users. A functional demonstrator of such a system has been designed and implemented to show the feasibility of this approach. A specific optical sensor system is used to observe a point on the extended cut axis in front of the blade. The sensor determines the surface material reliably and measures the distance to the workpiece surface simultaneously. If the distance changes because of a workpiece fed to the machine, the control unit will set the motor-adjusted hood to the correct height. If the sensor detects skin, the hood will not be moved. In addition a camera observes the area under the hood. If there are no workpieces or offcuts left under the hood, it will be lowered back to the default position.
This paper presents recent research on an active multispectral scanning sensor capable of classifying an object's surface material in order to distinguish between different kinds of materials and human skin. The sensor itself has already been presented in previous work and can be used in conjunction with safeguarding equipment at manually-fed machines or robot workplaces, for example. This work shows how an extended sensor system with advanced material classifiers can be used to provide additional value by distinguishing different materials of work pieces in order to suggest different tools or parameters for the machine (e.g. the use of a different saw blade or rotation speed at table saws). Additionally, a first implementation and evaluation of an active multispectral camera system addressing new safety applications is described. Both approaches intend to increase the productivity and the user's acceptance of the sensor technology.
Sicherheitsanforderungen an Transponder steigen mit zunehmendem Einsatz - in der Produktion, Logistik und Handel - insbesondere beim Endverbraucher bei der stationären und mobilen Nutzung. Standards und derzeit gebräuchliche Radio Frequency Identification (RFID-)Protokolle beinhalten bisher nur wenige Sicherheitsmechanismen und in proprietären Protokollen wird nur ein Teil davon genutzt. Insbesondere im Bereich der Low-Cost-Transponder werden nur einfache Sicherheitsfunktionen implementiert, die einen geringen Widerstandswert zu besitzen scheinen. Mit Verschlüsselungs-, Challenge-Response-Verfahren und digitalen Signaturen stehen allerdings Mechanismen zur Verfügung, mit denen ein hoher Widerstandswert erreicht werden kann. Diese Mechanismen werden jedoch bisher nur teilweise und bei hochpreisigen Transpondern verwendet. Hier werden einige zur Erreichung der Sachziele der Informationssicherheit bei RFID-Transpondern eingesetzte und einsetzbare Mechanismen dargestellt und hinsichtlich ihrer Anwendbarkeit und Angreifbarkeit bewertet. U.a. sind dies Back-Office-Verschlüsselung, Silent Tree Walking, Meta-IDs, Re-Encryption und distanzbasierte Zugriffskontrolle. Die Ergebnisse zeigen, dass Verfahren zur Erreichung eines mittleren bis hohen Sicherheitsniveaus (Widerstandswert gegen Angriffe) vorhanden sind. Im Beitrag wird je ein relevanter Mechanismus zur Erreichung der drei Sachziele der Informationssicherheit Verfügbarkeit, Vertraulichkeit und Pseudonymität bewertet: Verfügbarkeit: Widerstandswert gegen Strahlenbelastung bei medizinischen Anwendungen. Vertraulichkeit: Dazu wurde der Widerstandswert des Passwortschutzes von Transpondern mit Hilfe eines Brute-Force-Angriffs untersucht. Pseudonymität: Anwendbarkeit von Meta-ID-Verfahren.
This work addresses the problem of measuring psychological strain in humans by the use of physiological data. The aim of the work is the research, development and evaluation of a measurement system for the acquisition of such data from humans and the differentiation of psychological and physical strain with the help of machine learning algorithms. The developed system records and analyzes the ECG, the EMG, as well as the skin conductance, and combines these physiological parameters with the subject’s physical activity. The main purpose of this measurement system is to assess both types of strain in employees at their workplaces.
Design of an Active Multispectral SWIR Camera System for Skin Detection and Face Verification
(2016)
Biometric face recognition is becoming more frequently used in different application scenarios. However, spoofing attacks with facial disguises are still a serious problem for state of the art face recognition algorithms. This work proposes an approach to face verification based on spectral signatures of material surfaces in the short wave infrared (SWIR) range. They allow distinguishing authentic human skin reliably from other materials, independent of the skin type. We present the design of an active SWIR imaging system that acquires four-band multispectral image stacks in real-time. The system uses pulsed small band illumination, which allows for fast image acquisition and high spectral resolution and renders it widely independent of ambient light. After extracting the spectral signatures from the acquired images, detected faces can be verified or rejected by classifying the material as "skin" or "no-skin". The approach is extensively evaluated with respect to both acquisition and classification performance. In addition, we present a database containing RGB and multispectral SWIR face images, as well as spectrometer measurements of a variety of subjects, which is used to evaluate our approach and will be made available to the research community by the time this work is published.
Commercial light curtains use a technique known as muting to differentiate between work pieces and other objects (e.g., human limbs) based on precise model knowledge of the process. At manually fed machinery (e.g., bench saws), such precise models cannot be derived due to the way the machinery is used. This paper presents a multispectral scanning sensor to classify an object's surface material as a new approach for the problem. The system is meant to detect the presence of limbs and therefore optimized for human skin detection. Evaluation on a test set of skin and (wet) wood samples showed a sufficiently high reliability with respect to safety standards.
In this paper we present a new initiative to promote collaborative learning through industry partnered, interdisciplinary, student and user centred projects. This was achieved through the development of rehabilitation devices augmented with gamified software. Today development of software systems often requires people from different specialities who can work in multidisciplinary teams to achieve a common objective. A key challenge, therefore, is producing graduates with an understanding of a number of disparate skills across many discipline boundaries. Undergraduates may be knowledgeable in one specific discipline but will not be aware of the issues brought to bear by other relevant disciplines. In an effort to overcome this limitation, a cross-discipline course “Serious Games and Welfare Technology” was developed that allows students from different disciplines to work together to produce innovative, technology- supported health solutions. The course, an EU funded Erasmus+ initiative, was supported by a MOOC and enabled multi- disciplined and multinational teams to produce solutions for leading Health technology companies in the areas of rehabilitation and aging support. Following the first year of offering the course with a cohort of students from 5 countries, we report on the experiences and outcomes achieved from a number of viewpoints.
Several hundred accidents involving the use of circular saws and resulting in injury, to hands or fingers occur each year in Germany.
In the presented project, new approaches for the prevention of hand injuries and for the contactless detection of fingers are being investigated for comprehensive protection on circular saws. The basic principles can be applied to other machines with manual loading and/or unloading. This paper describes several principles to distinct human skin and wood and a safety guard that prevents touching the rotating blade. In a first approach a reliable protective device with functional diversity has been developed using a passive infrared sensor in combination with a capacitive field sensor. Second the distinction between skin and wood or other material is done by dedicated kind of spectral analysis in the near infrared region. With a kind of light curtain the intrusion into the dangerous zone near the blade can be prevented.
The safety guard protects the operator’s hand within 50 ms. The forces of the protective system peak at no more than 120 N. We are presenting a complete strategy for such different tasks as cutting wedges, stopped cutting and hidden cutting, which have a very high odds ratio.
In the presented project, new approaches for the prevention of hand movements leading to hazards and for non-contact detection of fingers are intended to permit comprehensive and economical protection on circular saws. The basic principles may also be applied to other machines with manual loading and/or unloading. Two new detection principles are explained. The first is the distinction between skin and wood or other material by spectral analysis in the near infrared region. Using LED and photodiodes it is possible to detect fingers and hands reliable. With a kind of light curtain the intrusion into the dangerous zone near the blade can be prevented. The second principle is video image processing to detect persons, arms and fingers. In the first stage of development the detection of upper limb extremities within a defined hazard area by means of a computer based video image analysis is investigated.
In the presented project, a new approach for the prevention of hand movements leading to hazards and for non-contact detection of fingers is intended to permit comprehensive and economical protection on circular saws. The basic principles may also be applied to other machines with manual loading and / or unloading. With an automatic blade guard an improved integration of the protection system can be achieved. In addition a new detection principle is explained. The distinction between skin and wood or other material is achieved by a dedicated spectral analysis in the near infrared region. Using LED and photodiodes it is possible to detect fingers and hands reliably. With a kind of light curtain the intrusion of hands or fingers into the dangerous zone near the blade guard can be prevented.
Safety applications require fast, precise and highly reliable sensors at low costs. This paper presents signal processing methods for an active multispectral optical point sensor instrumentation for which a first technical implementation exists. Due to the very demanding requirements for safeguarding equipment, these processing methods are targeted to run on a small embedded system with a guaranteed reaction time T < 2 ms and a sufficiently low failure rate according to applicable safety standards, e.g., ISO-13849. The proposed data processing concept includes a novel technique for distance-aided fusion of multispectral data in order to compensate for displacement-related alteration of the measured signal. The distance measuring is based on triangulation with precise results even for low-resolution detectors, thus strengthening the practical applicability. Furthermore, standard components, such as support vector machines (SVMs), are used for reliable material classification. All methods have been evaluated for variants of the underlying sensor principle. Therefore, the results of the evaluation are independent of any specific hardware.
Persons entering the working range of industrial robots are exposed to a high risk of collision with moving parts of the system, potentially causing severe injuries. Conventional systems, which restrict the access to this area, range from walls and fences to light barriers and other vision based protective devices (VBPD). None of these systems allow to distinguish between humans and workpieces in a safe and reliable manner. In this work, a new approach is investigated, which uses an active near-infrared (NIR) camera system with advanced capabilities of skin detection to distinguish humans from workpieces based on characteristic spectral signatures. This approach allows to implement more intelligent muting processes and at the same time increases the safety of persons working close to the robots. The conceptual integration of such a camera system into a VBPD and the enhancement of person detection methods through skin detection are described and evaluated in this paper. Based upon this work, next steps could be the development of multimodal sensor systems to safeguard working ranges of collaborating robots using the described camera system.
Entering the work envelope of an industrial robot can lead to severe injury from collisions with moving parts of the system. Conventional safety mechanisms therefore mostly restrict access to the robot using physical barriers such as walls and fences or non-contact protective devices including light curtains and laser scanners. As none of these mechanisms applies to human-robot-collaboration (HRC), a concept in which human and machine complement one another by working hand in hand, there is a rising need for safe and reliable detection of human body parts amidst background clutter. For this application camera-based systems are typically well suited. Still, safety concerns remain, owing to possible detection failures caused by environmental occlusion, extraneous light or other adverse imaging conditions. While ultrasonic proximity sensing can provide physical diversity to the system, it does not yet allow to reliably distinguish relevant objects from background objects.This work investigates a new approach to detecting relevant objects and human body parts based on acoustic holography. The approach is experimentally validated using a low-cost application-specific ultrasonic sensor system created from micro-electromechanical systems (MEMS). The presented results show that this system far outperforms conventional proximity sensors in terms of lateral imaging resolution and thus allows for more intelligent muting processes without compromising the safety of people working close to the robot. Based upon this work, a next step could be the development of a multimodal sensor systems to safeguard workers who collaborate with robots using the described ultrasonic sensor system.