Open Access Zeitschriften des Universitätsverlages der Technischen Universität Chemnitz
Not a member yet
466 research outputs found
Sort by
Traffic Light and Back-light Recognition using Deep Learning and Image Processing with Raspberry Pi
Get PDFTraffic light detection and back-light recognition are essential research topics in the area of intelligent vehicles because they avoid vehicle collision and provide driver safety. Improved detection and semantic clarity may aid in the prevention of traffic accidents by self-driving cars at crowded junctions, thus improving overall driving safety. Complex traffic situations, on the other hand, make it more difficult for algorithms to identify and recognize objects. The latest state-of-the-art algorithms based on Deep Learning and Computer Vision are successfully addressing the majority of real-time problems for autonomous driving, such as detecting traffic signals, traffic signs, and pedestrians. We propose a combination of deep learning and image processing methods while using the MobileNetSSD (deep neural network architecture) model with transfer learning for real-time detection and identification of traffic lights and back-light. This inference model is obtained from frameworks such as Tensor-Flow and Tensor-Flow Lite which is trained on the COCO data. This study investigates the feasibility of executing object detection on the Raspberry Pi 3B+, a widely used embedded computing board. The algorithm’s performance is measured in terms of frames per second (FPS), accuracy, and inference time
Towards Autonomous Driving Using Vision Based Intelligent Systems
Get PDFVision Based systems have become an integral part when it comes to autonomous driving. The autonomous industry has seen a made large progress in the perception of environment as a result of the improvements done towards vision based systems. As the industry moves up the ladder of automation, safety features are coming more and more into the focus. Different safety measurements have to be taken into consideration based on different driving situations. One of the major concerns of the highest level of autonomy is to obtain the ability of understanding both internal and external situations. Most of the research made on vision based systems are focused on image processing and artificial intelligence systems like machine learning and deep learning. Due to the current generation of technology being the generation of “Connected World”, there is no lack of data any more. As a result of the introduction of internet of things, most of these connected devices are able to share and transfer data. Vision based techniques are techniques that are hugely depended on these vision based data
Classification for Quality Assessment of the User Interface and its Application in the Development of Web-applications
Get PDFThe article considers a classification for validation and quality assessment of the user interface (UI) from the point of view of the main aspects of design and its application in the development of web-applications. The problem with inaccurately crafted user interface requirements is relevant and as a result, developers often have to redesign the interface and architecture of the application. The article analyzes the role and place of UI in the architecture of client-server applications, analyzes aspects of UI design, on the basis of which the classification is formed. The classification is used to analyze UI design oversights of the developed web-applications for BPMS “Fireproof Corporation” company. Based on the results of UI validation, a set of typical UI design oversights has been added
Towards Collection of Smart City Data for Cloud Storage Using UAVs
Get PDFThe article describes the methodology and process of collecting smart city data using drones for cities that do not have a sufficiently developed infrastructure. For storage and subsequent analysis of data, a cloud server is required; TUC DriveCloud is presented as an example of such a server in the article. Traffic analysis and building inspection are described as examples of drone data collection tasks. The advantages and disadvantages of collecting data using a thermal imaging camera are also discussed using the example of the problem of detecting and tracking the movement of people
Collision Avoidance by Identifying Risks for Detected Objects in Autonomous Vehicles
Get PDFWe propose a system which will detect objects onour roads, estimate the distance of these object from the cameraand alert the driver if this distance is equal or less than thethreshold value(02meters),and assist the driver and alert him assoon as possible in order for him to take appropriate actions assoon as possible which can avoid any collision or significantlyreduce it. We plan to use state of the arts object detection modelslike YOLO to identify the target object classes and use depthmaps from monocular camera to be give an accurate estimate ofthe distance of the detected object from the camera. one majorrequirement of this system is the real-time behaviour and a highaccuracy for the detected and estimated distance, A secondrequirement is to make the system cheap and easy useablecomparatively to the other existing methods. That is why wedecided to use monocular camera images and depth maps whichmakes the solution cheap and innovative. This project(prototype) provide room for bigger and more complete projectwhich will contribute to the creation of tool which can save livesand improve security on our road
Analysis of Machine Learning Approach for the mode model in SWC Mapping in Automotive Systems
Get PDFAutomotive technologies are ever-increasinglybecoming digital. Highly autonomous driving together withdigital E/E control mechanisms include thousands of softwareapplications which are called as software components.Together with the industry requirements, and rigoroussoftware development processes, mapping of components as asoftware pool becomes very difficult. This article analyses anddiscusses the integration possibilities of machine learningapproaches to our previously introduced concept of mappingof software components through a common software poo
Investigating the Lifetime of Fibre Ropes
Get PDFSteel wire ropes have established as transmission, connection and safety elements in transporters such as cranes and elevators, due to their high breaking strength and operational safety as well as out of many years of experience. However, steel wire ropes have disadvantages such as high dead weight, high bending stiffness and sensitivity to corrosion. Increasing requirements on the energy-efficient and resource-saving operation of technical systems demand new materials, technologies and processes. As a result, textile machine elements like HM-HT fibre ropes (high modulus, high tenacity) come into focus of considerations. The aim of the research is to expand the level of knowledge with regard to the state of wear and aging. Another aim is to find out the influencing factors on the lifetime, discard criteria of high-strength fibre ropes and to derive methods for lifetime detection
Calculation Approaches for Determining the Sliding Friction Coefficient – Analytical Consideration and FE-Modelling
Get PDFMicrostructures on polymer surfaces are known to reduce friction and thevisibility of scratches. Due to the complex interaction of multiple surface areas in contactwith each other the prediction of coefficient of friction (COF) or wear is difficult and dependson an empirical solution. This article deals with possibilities of calculating the deformingpart of friction via an analytical solution and a FE-model. In a first step the modelling ofsingle contacts is demonstrated. The analytical calculation based on the Hertzian contactequations is extended regarding viscoelastic material parameters. The basic approach ofFE-modelling is explained including calibration of the material model using the softwareMCalibration®. The article introduces the different procedures of simulating and modellingCOF and wear taking into account the area of contact and resulting stress distribution
Kupferwerkstoffe im Sekundärteil eines linearen Asynchronmotors – Betrachtung der mechanischen Eigenschaften
Get PDFIn dem Forschungsprojekt wird ein berührungsloses Direktantriebssystem für hochdynamische Bandförderer entwickelt. Die Förderkraft wird nach dem Prinzip der linearen Asynchronmaschine in den Gurt eingeleitet. Zur Umsetzung des Antriebsprinzips muss der Gurt flächig eine Kupferstruktur, die den Sekundärteil der Asynchronmaschine darstellt, beinhalten. Die Herausforderungen bei der Auslegung dieser Struktur bestehen in der Berücksichtigung der elektrischen Anforderungen zur Umsetzung des Linearmotors einerseits und anderseits in der Berücksichtigung der mechanischen Anforderungen die während des Betriebs des Förderers auftreten. Im weiteren Projektverlauf wird das Antriebssystem um Condition-Monitoring-Funktionalitäten erweitert: Anhand der Statorströme wird die elektrodynamische Rückwirkung der Kupferstruktur im Gurt ausgewertet. Die gewonnenen Daten ermöglichen einen Rückschluss auf den Zustand der Kupferstruktur und gestatten somit eine Beurteilung des Verschleißzustandes des Motors und des Gurts. Ferner lässt sich der Bewegungszustand des Bandförderers bestimmen. Aus wirtschaftlichen Gründen soll sich der resultierende Bandförderer mit neuartigem Antriebssystem durch kleine Umlenkradien, den Verzicht auf zusätzliche Zugträger sowie die Erreichung eines bestmöglichen motorischen Wirkungsgrades auszeichnen. Für diese Forschungsziele ist die Kupferstruktur, welche in den Gurt integriert wird, von herausragender Bedeutung. In diesem Beitrag wird das Ergebnis der Betrachtung der Kupferwerkstoffe dargestellt
Capabilities of Additively Manufactured Rope Drums
Get PDFMany industry sectors benefit from the new opportunities additive manufacturing provides. Lightweight designs and integration of function are only two aspects. As there are no approaches present to insert additive manufacturing into the design of hoisting appliances though, we try to evaluate the room for improvement through experimental analysis. Additively manufactured synthetic drum-bodies fit for 8 mm wire ropes and containing different infill structures were tested for tensile strength. The cylindrical gyroid TPMS and straight spokes structures performed best with standardised tensile strengths of 17.53 and 16.40 kN/kg. Our findings indicate that additively manufactured rope drums can be a viable option for future hoisting appliances