Depth sensors-based upper limb motion capture system for functional neurorehabilitation

Versatile and accurate motion capture systems, with the required properties to be integrated within both clinical and domiciliary environments, would represent a significant advance in following the progress of the patients as well as in allowing the incorporation of new data exploitation and analysis methods to enhance the functional neurorehabilitation therapeutic processes. Besides, these systems would permit the later development of new applications focused on the automatization of the therapeutic tasks in order to increase the therapist/patient ratio, thus decreasing the costs [1]. However, current motion capture systems are not still ready to work within uncontrolled environments.

A survey of human motion analysis using depth imagery

Analysis of human behaviour through visual information has been a highly active research topic in the computer vision community. This was previously achieved via images from a conventional camera, but recently depth sensors have made a new type of data available. This survey starts by explaining the advantages of depth imagery, then describes the new sensors that are available to obtain it. In particular, the Microsoft Kinect has made high-resolution real-time depth cheaply available. The main published research on the use of depth imagery for analysing human activity is reviewed. Much of the existing work focuses on body part detection and pose estimation. A growing research area addresses the recognition of human actions. The publicly available datasets that include depth imagery are listed, as are the software libraries that can acquire it from a sensor. This survey concludes by summarising the current state of work on this topic, and pointing out promising future research directions.

Measuring depth accuracy in RGBD cameras

This paper presents the comparison between the Microsoft Kinect depth sensor and the Asus Xtion for computer vision applications. Depth sensors, known as RGBD cameras,
project an infrared pattern and calculate the depth from the reflected light using an infrared sensitive camera. In this research, we compare the depth sensing capabilities of the two sensors under various conditions. The purpose is to give the reader a background to whether use the Microsoft Kinect or Asus Xtion sensor to solve a specific computer vision problem. The properties of the two depth sensors were investigated by conducting a series of experiments evaluating the accuracy of the sensors under various conditions, which shows the advantages and disadvantages of both Microsoft Kinect and Asus Xtion sensor.

LGT/VOT tracking performance evaluation of depth images

This paper presents object tracking in depth, RGB and normal-maps images using LGT tracker. The depth and RGB images are rendered using depth imaging plugins. A series of experiments were held to evaluate the tracker performance in tracking objects in different image sequences. The experiments conducted were from the Visual Object Tracking (VOT) challenge that was arranged in association with ICCV'13 The accuracy was chosen as the evaluation measure, where the the tracker's bounding box was compared against the ground truth bounding box. Results show that tracking object using depth images gives better results and is more accurate than tracking using either the RGB or nomal maps images.

An evaluation of volumetric interest points

This paper presents the first performance evaluation of interest points on scalar volumetric data. Such data encodes 3D shape, a fundamental property of objects. The use of another such property, texture (i.e. 2D surface colouration), or appearance, for object detection, recognition and registration has been well studied; 3D shape less so. However, the increasing prevalence of depth sensors and the diminishing returns to be had from appearance alone have seen a surge in shape-based methods. In this work we investigate the performance of several detectors of interest points in volumetric data, in terms of repeatability, number and nature of interest points. Such methods form the first step in many shape-based applications. Our detailed comparison, with both quantitative and qualitative measures on synthetic and real 3D data, both point-based and volumetric, aids readers in selecting a method suitable for their application. © 2011 IEEE.

研究海水温盐结构的反射地震方法

在物理海洋学的研究中，利用CTD（Conductivity，Temperature and Depth sensors）测量方法研究海水温盐

Efficacy comparison of clustering systems for limb detection

This paper presents a comparison of applying different clustering algorithms on a point cloud constructed from the depth maps captured by a RGBD camera such as Microsoft Kinect. The depth sensor is capable of returning images, where each pixel represents the distance to its corresponding point not the RGB data. This is considered as the real novelty of the RGBD camera in computer vision compared to the common video-based and stereo-based products. Depth sensors captures depth data without using markers, 2D to 3D-transition or determining feature points. The captured depth map then cluster the 3D depth points into different clusters to determine the different limbs of the human-body. The 3D points clustering is achieved by different clustering techniques. Our Experiments show good performance and results in using clustering to determine different human-body limbs.

Advanced CMOS Interfaces for Bio-Nanosensors

The improvement of devices provided by Nanotechnology has put forward new classes of sensors, called bio-nanosensors, which are very promising for the detection of biochemical molecules in a large variety of applications. Their use in lab-on-a-chip could gives rise to new opportunities in many fields, from health-care and bio-warfare to environmental and high-throughput screening for pharmaceutical industry. Bio-nanosensors have great advantages in terms of cost, performance, and parallelization. Indeed, they require very low quantities of reagents and improve the overall signal-to-noise-ratio due to increase of binding signal variations vs. area and reduction of stray capacitances. Additionally, they give rise to new challenges, such as the need to design high-performance low-noise integrated electronic interfaces. This thesis is related to the design of high-performance advanced CMOS interfaces for electrochemical bio-nanosensors. The main focus of the thesis is: 1) critical analysis of noise in sensing interfaces, 2) devising new techniques for noise reduction in discrete-time approaches, 3) developing new architectures for low-noise, low-power sensing interfaces. The manuscript reports a multi-project activity focusing on low-noise design and presents two developed integrated circuits (ICs) as examples of advanced CMOS interfaces for bio-nanosensors. The first project concerns low-noise current-sensing interface for DC and transient measurements of electrophysiological signals. The focus of this research activity is on the noise optimization of the electronic interface. A new noise reduction technique has been developed so as to realize an integrated CMOS interfaces with performance comparable with state-of-the-art instrumentations. The second project intends to realize a stand-alone, high-accuracy electrochemical impedance spectroscopy interface. The system is tailored for conductivity-temperature-depth sensors in environmental applications, as well as for bio-nanosensors. It is based on a band-pass delta-sigma technique and combines low-noise performance with low-power requirements.

Physical oceanography from eight Seaglider missions in the Mediterranean Sea, Eastern Basin

In 2008, the Oceanography Center at the University of Cyprus acquired two underwater gliders in the framework of a nationally-managed infrastructure upgrade program. The gliders were purchased from the Seaglider Fabrication Center at the University of Washington. Both gliders are rated to 1000 m and carry a typical sensor payload: non-pumped conductivity-temperature-depth sensors (CTD), a dissolved oxygen sensor, an optical triplet to measure optical backscatter at 400 nm, 700 nm, and chlorophyll-a fluorescence. Since March of 2009, the gliders have been used in a long-term observing program of the Cypriot EEZ, and by September 2015, have covered more than 15300 km over ground and 3500 dive cycles in 940 glider days. Butterfly patterns have been flown in two configurations, either on the western or eastern side of the EEZ south of Cyprus. The glider endurance lines criss-cross the region in order to more accurately locate and investigate the mesoscale structures south of Cyprus, and in particular the Cyprus eddy which is often the dominant feature. Based on the near real time observations, the glider mission was sometimes altered in order to more fully sample the Cyprus eddy, or to locate its center or extent. A summary of the raw and processed data collected, and the quality control procedures are presented, in order for future users to take advantage of this unique data set.

Water temperature and salinity data from southern elephant seals from Marion Island

Over the last decade, several hundred seals have been equipped with conductivity-temperature-depth sensors in the Southern Ocean for both biological and physical oceanographic studies. A calibrated collection of seal-derived hydrographic data is now available, consisting of more than 165,000 profiles. The value of these hydrographic data within the existing Southern Ocean observing system is demonstrated herein by conducting two state estimation experiments, differing only in the use or not of seal data to constrain the system. Including seal-derived data substantially modifies the estimated surface mixedlayer properties and circulation patterns within and south of the Antarctic Circumpolar Current. Agreement with independent satellite observations of sea ice concentration is improved, especially along the East Antarctic shelf. Instrumented animals efficiently reduce a critical observational gap, and their contribution to monitoring polar climate variability will continue to grow as data accuracy and spatial coverage increase.

Registro global de nuvens de pontos RGB-D em tempo real usando fluxo óptico e marcadores

Registration of point clouds captured by depth sensors is an important task in 3D reconstruction applications based on computer vision. In many applications with strict performance requirements, the registration should be executed not only with precision, but also in the same frequency as data is acquired by the sensor. This thesis proposes theuse of the pyramidal sparse optical flow algorithm to incrementally register point clouds captured by RGB-D sensors (e.g. Microsoft Kinect) in real time. The accumulated errorinherent to the process is posteriorly minimized by utilizing a marker and pose graph optimization. Experimental results gathered by processing several RGB-D datasets validatethe system proposed by this thesis in visual odometry and simultaneous localization and mapping (SLAM) applications.

Body parts segmentation with attached props using RGB-D imaging

People detection is essential in a lot of different systems. Many applications nowadays tend to require people detection to achieve certain tasks. These applications come under many disciplines, such as robotics, ergonomics, biomechanics, gaming and automotive industries. This wide range of applications makes human body detection an active area of research. With the release of depth sensors or RGB-D cameras such as Micosoft Kinect, this area of research became more active, specially with their affordable price. Human body detection requires the adaptation of many scenarios and situations. Various conditions such as occlusions, background cluttering and props attached to the human body require training on custom built datasets. In this paper we present an approach to prepare training datasets to detect and track human body with attached props. The proposed approach uses rigid body physics simulation to create and animate different props attached to the human body. Three scenarios are implemented. In the first scenario the prop is closely attached to the human body, such as a person carrying a backpack. In the second scenario, the prop is slightly attached to the human body, such as a person carrying a briefcase. In the third scenario the prop is not attached to the human body, such as a person dragging a trolley bag. Our approach gives results with accuracy of 93% in identifying both the human body parts and the attached prop in all the three scenarios.

Combat sports analytics: Boxing punch classification using overhead depth imagery

In competitive combat sporting environments like boxing, the statistics on a boxer's performance, including the amount and type of punches thrown, provide a valuable source of data and feedback which is routinely used for coaching and performance improvement purposes. This paper presents a robust framework for the automatic classification of a boxer's punches. Overhead depth imagery is employed to alleviate challenges associated with occlusions, and robust body-part tracking is developed for the noisy time-of-flight sensors. Punch recognition is addressed through both a multi-class SVM and Random Forest classifiers. A coarse-to-fine hierarchical SVM classifier is presented based on prior knowledge of boxing punches. This framework has been applied to shadow boxing image sequences taken at the Australian Institute of Sport with 8 elite boxers. Results demonstrate the effectiveness of the proposed approach, with the hierarchical SVM classifier yielding a 96% accuracy, signifying its suitability for analysing athletes punches in boxing bouts.

Feedback on the Rate and Depth of Chest Compressions during Cardiopulmonary Resuscitation Using Only Accelerometers

Background Quality of cardiopulmonary resuscitation (CPR) is key to increase survival from cardiac arrest. Providing chest compressions with adequate rate and depth is difficult even for well-trained rescuers. The use of real-time feedback devices is intended to contribute to enhance chest compression quality. These devices are typically based on the double integration of the acceleration to obtain the chest displacement during compressions. The integration process is inherently unstable and leads to important errors unless boundary conditions are applied for each compression cycle. Commercial solutions use additional reference signals to establish these conditions, requiring additional sensors. Our aim was to study the accuracy of three methods based solely on the acceleration signal to provide feedback on the compression rate and depth. Materials and Methods We simulated a CPR scenario with several volunteers grouped in couples providing chest compressions on a resuscitation manikin. Different target rates (80, 100, 120, and 140 compressions per minute) and a target depth of at least 50 mm were indicated. The manikin was equipped with a displacement sensor. The accelerometer was placed between the rescuer's hands and the manikin's chest. We designed three alternatives to direct integration based on different principles (linear filtering, analysis of velocity, and spectral analysis of acceleration). We evaluated their accuracy by comparing the estimated depth and rate with the values obtained from the reference displacement sensor. Results The median (IQR) percent error was 5.9% (2.8-10.3), 6.3% (2.9-11.3), and 2.5% (1.2-4.4) for depth and 1.7% (0.0-2.3), 0.0% (0.0-2.0), and 0.9% (0.4-1.6) for rate, respectively. Depth accuracy depended on the target rate (p < 0.001) and on the rescuer couple (p < 0.001) within each method. Conclusions Accurate feedback on chest compression depth and rate during CPR is possible using exclusively the chest acceleration signal. The algorithm based on spectral analysis showed the best performance. Despite these encouraging results, further research should be conducted to asses the performance of these algorithms with clinical data.

The use of fibre optic sensors to monitor pipeline response to tunnelling

This paper describes the use of fibre optic sensing with Brillouin Optical Time-Domain Reflectometry (BOTDR) for near-continuous (distributed) strain monitoring of a large diameter pipeline, buried in predominantly granular material, subjected to a pipe jack tunnelling operation in London Clay. The pipeline, buried at shallow depth, comprises 4.6 m long sections connected with standard bell and spigot type joints, which connect to a continuous steel pipeline. In this paper the suitability of fibre optic sensing with BOTDR for monitoring pipeline behaviour is illustrated. The ability of the fibre optic sensor to detect local strain changes at joints and the subsequent impact on the overall strain profile is shown. The BOTDR strain profile was also used to infer pipe settlement through a process of double-integration and was compared to pipe settlement measurements. The close approximation of the measured pipe settlement provides further confidence in fibre optic strain sensing with BOTDR to investigate the intricacies of pipeline behaviour, pipe-soil interaction and interaction between pipe sections when subjected to ground movement. Copyright ASCE 2006.