004 Datenverarbeitung; Informatik
Refine
H-BRS Bibliography
- yes (27)
Departments, institutes and facilities
- Institut für Sicherheitsforschung (ISF) (27) (remove)
Document Type
- Conference Object (12)
- Article (10)
- Patent (2)
- Part of a Book (1)
- Contribution to a Periodical (1)
- Research Data (1)
Year of publication
Keywords
- Cooperative Awareness Message (2)
- Intelligent Transport System (2)
- Privacy (2)
- Pseudonym Concept (2)
- Vehicular Ad hoc Networks (2)
- machine learning (2)
- Chemical imaging (1)
- Circular saws (1)
- Hand injuries (1)
- Hyperspectral image (1)
The following work presents algorithms for semi-automatic validation, feature extraction and ranking of time series measurements acquired from MOX gas sensors. Semi-automatic measurement validation is accomplished by extending established curve similarity algorithms with a slope-based signature calculation. Furthermore, a feature-based ranking metric is introduced. It allows for individual prioritization of each feature and can be used to find the best performing sensors regarding multiple research questions. Finally, the functionality of the algorithms, as well as the developed software suite, are demonstrated with an exemplary scenario, illustrating how to find the most power-efficient MOX gas sensor in a data set collected during an extensive screening consisting of 16,320 measurements, all taken with different sensors at various temperatures and analytes.
The application of Raman and infrared (IR) microspectroscopy is leading to hyperspectral data containing complementary information concerning the molecular composition of a sample. The classification of hyperspectral data from the individual spectroscopic approaches is already state-of-the-art in several fields of research. However, more complex structured samples and difficult measuring conditions might affect the accuracy of classification results negatively and could make a successful classification of the sample components challenging. This contribution presents a comprehensive comparison in supervised pixel classification of hyperspectral microscopic images, proving that a combined approach of Raman and IR microspectroscopy has a high potential to improve classification rates by a meaningful extension of the feature space. It shows that the complementary information in spatially co-registered hyperspectral images of polymer samples can be accessed using different feature extraction methods and, once fused on the feature-level, is in general more accurately classifiable in a pattern recognition task than the corresponding classification results for data derived from the individual spectroscopic approaches.
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.
A deployment of the Vehicle-2-Vehicle communication technology according to ETSI is in preparation in Europe. Currently, a policy for a necessary Public Key Infrastructure to enrol cryptographic keys and certificates for vehicles and infrastructure component is in discussion to enable an interoperable Vehicle-2-Vehicle communication. Vehicle-2-Vehicle communication means that vehicles periodically send Cooperative Awareness Messages. These messages contain the current geographic position, driving direction, speed, acceleration, and the current time of a vehicle. To protect privacy (location privacy, “speed privacy”) of vehicles and drivers ETSI provides a specific pseudonym concept. We show that the Vehicle-2-Vehicle communication can be misused by an attacker to plot a trace of sequent Cooperative Awareness Messages and to link this trace to a specific vehicle. Such a trace is non-disputable due to the cryptographic signing of the messages. So, the periodically sending of Cooperative Awareness Messages causes privacy problems even if the pseudonym concept is applied.
A deployment of the Vehicle-to-Vehicle communication technology according to ETSI is in preparation in Europe. Currently, a Public Key Infrastructure policy for Intelligent Transport Systems in Europe is in discussion to enable V2V communication. This policy set aside two classes of keys and certificates for ITS vehicle stations: long term authentication keys and pseudonymous keys and certificates. We show that from our point of view the periodic sent Cooperative Awareness Messages with extensive data have technical limitations and together with the pseudonym concept cause privacy problems.
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.
Im Rahmen der Forschungsprojekte FeGeb und SPAI wurden bei zahlreichen Probanden Hautproben an mehreren Stellen des Gesichts, sowie der Arme und Hände, mit einem Nahinfrarot-Spektrometer (NIR, auch „Short Wave Infrared“, SWIR) erfasst und die Gesichter der Probanden zusätzlich mit einer hochwertigen Farb-Kamera, sowie einem selbst entwickelten multispektralen NIR-Kamerasystem aus mehreren Perspektiven aufgenommen. Vorrangiges Ziel dieser Messreihe war es, die Robustheit des an der Hochschule entwickelten Verfahrens zur berührungslosen Hauterkennung mittels multispektraler Nahinfrarotsensorik nachzuweisen. Haut ist im nahinfraroten Spektralbereich unabhängig von Geschlecht, Alter und Hauttyp sehr gut von anderen Materialien unterscheidbar. Weiterhin konnte mit Hilfe der so aufgenommenen Daten ein Klassifikator trainiert werden, der auch „Fälschungen“ wie beispielsweise Latexmasken zuverlässig von echter Haut unterscheiden kann.
Ein Teil der aus dieser Messreihe entstandenen Datenbank kann zum Download angefordert und für wissenschaftliche und akademische Zwecke in Forschung und Lehre kostenfrei verwendet werden.
At previous SIAS conferences, we presented a novel opto-electronic safety sensor system for skin detection at circular saws jointly developed with the Institute for Occupational Safety and Health of the German Social Accident Insurance (IFA). This work now presents the development results of our consecutive research on a prototype of a sensor system for more general production machine applications including robot workplaces. The system uses offthe shelf LEDs and photodiodes in combination with dedicated optics and a microcontroller system to implement a so-called spectral light curtain.
Microcontroller-based sensor systems offer great opportunities for the implementation of safety features for potentially dangerous machinery. However, in general they are difficult to assess with regard to their reliability and failure rate. This paper describes the safety assessment of hardware and software of a new and innovative sensor system. The hardware is assessed by standardized methods according to norm EN ISO 13849-1, while the use of model checking is presented as an approach to solve the problem of validating the software.
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.
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.
Vorrichtung zur Authentifikation einer Person anhand mindestens eines biometrischen Parameters
(2008)
Die Vorrichtung zur Authentifikation einer Person anhand mindestens eines biometrischen Parameters, insbesondere anhand eines Fingerabdrucks, ist versehen mit einem Biometrie-Detektor (20) zur Detektion eines biometrischen Parameters, einem Haut-Detektor (24) zur berührungslosen Erkennung lebender menschlicher Haut innerhalb eines Erfassungsbereichs. Der Haut-Detektor (24) weist mindestens eine Gruppe aus mindestens einer Strahlungseinheit (26, 28) und mindestens einer Empfangseinheit (30) auf. Die mindestens eine Strahlungseinheit (26, 28) gibt in Richtung auf den Erfassungsbereich Strahlung bei mindestens zwei unterschiedlichen Wellenlängen im Wellenlängenbereich zwischen 400 nm und 1500 nm ab, wobei mindestens eine der Wellenlängen (26, 28) im Wellenlängenbereich von 900 nm bis 1500 nm liegt und die mindestens eine Empfangseinheit (30) aus dem Erfassungsbereich reflektierte Strahlung empfängt. Ferner ist die Vorrichtung versehen mit einer mit dem Biometer-Detektor (20) und dem Haut-Detektor (24) verbundenen Signalauswerteeinheit (22) zur Auswertung der Intensität der von der Empfangseinheit (30) empfangenen reflektierten Strahlungen der Strahlungseinheit (26, 28). In der Signalauswerteeinheit (22) ist anhand der Intensitäten der von der Empfangseinheit (30) empfangenen reflektierten Strahlungen der Strahlungseinheit (26, 28) bei den zwei unterschiedlichen Wellenlängen ermittelbar, ob der Haut-Detektor lebende menschliche Haut erkennt.