In this paper, we propose an efficient disparity map generation method for multi-view video sequences captured by a forward moving multi-camera system. Forward camera moving increases the minimum and ...maximum disparity value of each frame with time. Thus, computational complexity can be increased and the quality of generated disparity can be degraded since the stereo matching operation has to deal with a wide range of the disparity candidates. In order to solve this problem, we employ a time-of-flight (TOF) depth sensor as a guide to find the minimum and maximum disparity values for each frame. Then, the stereo matching process for video sequences captured by the moving multi-camera system becomes simple without quality degradation.
Realtime 3D depth sensor technologies, as manifested in several consumers' electronics products, have potential for a technological breakthrough in various robotic applications. Depth sensing of ...human body motions can promote intuitive gesture inputs for natural HMI (Human Machine Interface) as well as HRI (Human Robot Interaction) for various applications. In today's industry, the dominant trends in 3D depth sensing are shifting from the traditional laser based scanning or TOF (Time of Flight) depth sensing to the intensity based Infrared 3D depth sensing mechanism. However, the majority of 3D depth sensors does not function properly in a short range due to the limit of shutter speed or light speculation resolution. In this paper, we investigate currently available mono-vision based 3D sensor technologies followed by the results of a novel short range 3D depth sensing technology via multiple intensity differentiation. Our approach is to simultaneously calculate the 3D depth and the surface angle of an object to generate high quality 3D surfaces with an illumination intensity matrix from multiply adjacent light sources.
Virtual try-on of footwear in mixed reality using depth sensors Yang, Yu-I; Yang, Chih-Kai; Chu, Chih-Hsing
Proceedings of the 12th ACM SIGGRAPH International Conference on Virtual-Reality Continuum and Its Applications in Industry,
11/2013
Conference Proceeding
This paper presents a virtual try-on system of footwear in mixed reality. A user can virtually put on 3D shoe models on his/her feet in a video stream. Real time object tracking integrated with depth ...sensing technologies enables that the shoe models stay correctly with respect to the positions of the moving feet during the try-on process. The system facilitates evaluating consumer products that are highly interactive with the users. It thus serves as an essential element in realizing human-centric design. This study also demonstrates a new application of depth sensing technologies in product design.
Interest in nanoindentation has spawned a number of nanoindentation instruments that compete on a world market. Purchasers of such instruments are usually universities, private and government ...research organisations, and quality control laboratories. There is particular interest within the semiconductor industry that is concerned with the mechanical properties of a wide range of thin films.
Behind the Technology Kean, Sean; Hall, Jonathan C.; Perry, Phoenix
Meet the Kinect
Book Chapter
In this chapter, we’ll demystify the underlying technology behind Kinect. You’ll learn about the principles of depth-sensing imagers, discover alternatives to Kinect that are available through other ...manufacturers, and understand the general data output that all of these devices offer to your potential applications. You can create applications through various drivers, processing libraries, and application development environments. You’ll be exposed to new language that is used to describe working with depth and natural interface technology and be provided with a mental framework for relating these new ideas to ones you’re already familiar with from 2D technology.
Reinforced Pressure Sensor for Marine Environment Aravamudhan, S.; Bhansali, S.
TRANSDUCERS 2007 - 2007 International Solid-State Sensors, Actuators and Microsystems Conference,
2007-June
Conference Proceeding
Pressure measurements in marine environment are of utmost importance to better understand the ocean processes, for maritime security and even for tsunami wave detection. In this work, a MEMS ...reinforced piezoresistive pressure sensor with packaging and protective coatings was tested to achieve both higher sensitivity and larger full scale span compared to conventional single diaphragm. By eliminating large deflections and non-linearities, the reinforced design showed about 15% higher sensitivity and twice the operating range. Further, reliability of protective coatings was evaluated in real ocean conditions.
The MIT Sea Grant AUV Lab, in association with Bluefin Robotics Corporation, has undertaken the task of designing a new autonomous underwater vehicle, a holonomic hover-capable robot capable of ...performing missions where an inspection capability similar to that of a remotely operated vehicle is the primary goal. One of the primary issues in this mode of operating AUVs is how the robot perceives its environment and thus navigates. The predominant methods for navigating in close proximity to large iron structures, which precludes accurate compass measurements, require the AUV to receive position information updates from an outside source, typically an acoustic LBL or USBL system. The new paradigm we present in this paper divorces the navigation routine from any absolute reference frame; motions are referenced directly to the hull. We argue that this technique offers some substantial benefits over the conventional approaches, and will present the current status of our project.
Provider: - Institution: - Data provided by Europeana Collections- Saarbrücken, Universität des Saarlandes, Diss., 2013- All metadata published by Europeana are available free of restriction under ...the Creative Commons CC0 1.0 Universal Public Domain Dedication. However, Europeana requests that you actively acknowledge and give attribution to all metadata sources including Europeana
Provider: - Institution: - Data provided by Europeana Collections- Advances in depth sensing provide great opportunities for the development of new methods for human computer interactivity. With the ...launch of the Microsoft Kinect sensor, high-resolution depth and visual sensing has become available for widespread use. As it is suitable for measuring distances to objects at high frame rate, such kind of sensors are increasingly used for 3D acquisitions, and more generally for applications in robotics or computer vision. The aim of this survey is to implement a gesture recognition system using the Kinect version 2 of Microsoft in order to interact with a virtual TV weather studio. The Kinect sensor was used to build up a dataset, which contains motion recordings of 8 different gestures and was build up by two different gesture training machine learning algorithms. Then, the system is evaluated in a user study, which allows a direct comparison and reveals benefits and limits of using such technique. Finally, it is given an overview of the challenges in this field and future work trends.- Los avances en los sensores de profundidad ofrecen grandes oportunidades para el desarrollo de nuevos métodos para la interactividad computadora-humano. Con el lanzamiento del sensor Kinect de Microsoft, la detección de profundidad de alta resolución se ha convertido en un componente disponible para el uso generalizado. Como es adecuado para medir distancias a objetos a alta velocidad, este tipo de sensores se utilizan cada vez más para adquirir información 3D, y más en general para aplicaciones en robótica o en visión artificial. El objetivo de este estudio es implementar un sistema de reconocimiento de gestos utilizando la Kinect versión 2 de Microsoft con el fin de interactuar con un estudio virtual de TV. El sensor Kinect se utilizó para construir una base de datos, que contiene grabaciones de movimientos para 8 gestos distintos y fue entrenado por dos algoritmos diferentes de aprendizaje de máquinas. A continuación, el sistema se evaluó con un conjunto de usuarios en un estudio virtual, lo que permite una comparación directa y revela los beneficios y los límites de la utilización de tal técnica. Por último, se da una visión general de los retos en este campo y futuras líneas de trabajo- Els avenços en els sensors de profunditat ofereixen grans oportunitats per al desenvolupament de nous mètodes per a la interactivitat ordinador-humà. Amb el llançament del sensor Kinect de Microsoft, la detecció de profunditat d’alta resolució s’ha convertit en un component disponible per a l’ús generalitzat. Com és adequat per mesurar distàncies a objectes a alta velocitat, aquest tipus de sensors s’utilitzen cada vegada més per adquirir informació 3D, i més en general per a aplicacions en robòtica i en visió artificial. L’objectiu d’aquest estudi és implementar un sistema de reconeixement de gestos utilitzant la Kinect versió 2 de Microsoft per tal d’interactuar amb un estudi virtual de TV. El sensor Kinect es va utilitzar per construir una base de dades, que conté gravacions de moviments per a 8 gestos diferents i va ser entrenat per dos algoritmes diferents d’aprenentatge de màquines. A continuació, el sistema es va avaluar amb un conjunt d’usuaris en un estudi virtual, el que permet una comparació directa i revela els beneficis i els límits de la utilització de tal tècnica. Finalment, es dóna una visió general dels reptes en aquest camp i futures línies de treball.- All metadata published by Europeana are available free of restriction under the Creative Commons CC0 1.0 Universal Public Domain Dedication. However, Europeana requests that you actively acknowledge and give attribution to all metadata sources including Europeana
Automatic human activity recognition is being studied widely by researchers for various applications. However, majority of the existing work are limited to recognition of isolated activities, though ...human activities are inherently continuous in nature with spatial and temporal transitions between various segments. Therefore, there are scopes to develop a robust and continuous Human Activity Recognition (HAR) system. In this paper, we present a novel Coarse-to-Fine framework for continuous HAR using Microsoft Kinect. The activity sequences are captured in the form of 3D skeleton trajectories consisting of 3D positions of 20 joints estimated from the depth data. The recorded sequences are first coarsely grouped into two activity sequences performed during sitting and standing. Next, the activities present in the segmented sequences are recognized into fine-level activities. Activity classification in both stages are performed using Bidirectional Long Short-Term Memory Neural Network (BLSTM-NN) classifier. A total of 1110 continuous activity sequences have been recorded using a combination of 24 isolated human activities. Recognition rates of 68.9% and 64.45% have been recorded using BLSTM-NN classifier when tested using length-modeling and without length-modeling, respectively. We have also computed results for isolated activity recognition performance. Finally, the performance has been compared with existing approaches.
