Towards a real-time 3D object recognition pipeline on mobile GPGPU computing platforms using low-cost RGB-D sensors

In this project, we propose the implementation of a 3D object recognition system which will be optimized to operate under demanding time constraints. The system must be robust so that objects can be recognized properly in poor light conditions and cluttered scenes with significant levels of occlusion. An important requirement must be met: the system must exhibit a reasonable performance running on a low power consumption mobile GPU computing platform (NVIDIA Jetson TK1) so that it can be integrated in mobile robotics systems, ambient intelligence or ambient assisted living applications. The acquisition system is based on the use of color and depth (RGB-D) data streams provided by low-cost 3D sensors like Microsoft Kinect or PrimeSense Carmine. The range of algorithms and applications to be implemented and integrated will be quite broad, ranging from the acquisition, outlier removal or filtering of the input data and the segmentation or characterization of regions of interest in the scene to the very object recognition and pose estimation. Furthermore, in order to validate the proposed system, we will create a 3D object dataset. It will be composed by a set of 3D models, reconstructed from common household objects, as well as a handful of test scenes in which those objects appear. The scenes will be characterized by different levels of occlusion, diverse distances from the elements to the sensor and variations on the pose of the target objects. The creation of this dataset implies the additional development of 3D data acquisition and 3D object reconstruction applications. The resulting system has many possible applications, ranging from mobile robot navigation and semantic scene labeling to human-computer interaction (HCI) systems based on visual information.

Methodology based on registration techniques for representing subjects and their deformations acquired from general purpose 3D sensors

In this thesis a methodology for representing 3D subjects and their deformations in adverse situations is studied. The study is focused in providing methods based on registration techniques to improve the data in situations where the sensor is working in the limit of its sensitivity. In order to do this, it is proposed two methods to overcome the problems which can difficult the process in these conditions. First a rigid registration based on model registration is presented, where the model of 3D planar markers is used. This model is estimated using a proposed method which improves its quality by taking into account prior knowledge of the marker. To study the deformations, it is proposed a framework to combine multiple spaces in a non-rigid registration technique. This proposal improves the quality of the alignment with a more robust matching process that makes use of all available input data. Moreover, this framework allows the registration of multiple spaces simultaneously providing a more general technique. Concretely, it is instantiated using colour and location in the matching process for 3D location registration.

Vertical profiles of environmental parameters measured from physical, optical and imaging sensors during Tara Oceans expedition 2009-2013

The present data publication provides permanent links to original and updated versions of validated data files. The data files include properties of seawater, particulate matter and dissolved matter from physical, optical and imaging sensors mounted on a vertical sampling system (Rosette) used during the 2009-2013 tara Oceans Expedition. It comprised 2 pairs of conductivity and temperature sensors (SEABIRD components), and a complete set of WEtLabs optical sensors, including chrorophyll and CDOM fluorometers, a 25 cm transmissiometer, and a one-wavelength backscatter meter. In addition, a SATLANTIC ISUS nitrate sensor and a Hydroptic Underwater Vision Profiler (UVP) were mounted on the rosette. In the Arctic Ocean and Arctic Seas (2013), a second oxygen sensor (SBE43) and a four frequency Aquascat acoustic profiler were added. The system was powered on specific Li-Ion batteries and data were self-recorded at 24HZ. Sensors have all been factory calibrated before, during and after the four year program. Oxygen was validated using climatologies (WOA09). Nitrate and Fluorescence data were adjusted with discrete measurements from Niskin bottles mounted on the Rosette, and optical darks were performed monthly on board. A total of 839 quality checked vertical profiles were made during the tara Oceans expedition 2009-2013.

Evaluation of sensors for monitoring truck speeds.

Texas Department of Transportation, Austin

Development and evaluation of Hybrid III multi-point thoracic deflection measurement sensors. Final report.

Mode of access: Internet.

Occupant motion sensors: rotational accelerometer development. Technical report.

Mode of access: Internet.

Development of high temperature sensors : July 1, 1959-April 30, 1961 /

"Contract AT(11-1)-229."

Refrigeration for cryogenic sensors and electronic systems : proceedings of a conference held at the National Bureau of Standards, Boulder, CO, October 6-7, 1980 /

Item 247.

Development of buoy-mounted oceanographic sensors (BMOS) Progress report, phase II, no.2

Photocopy.

In-home Assessment of Turning and Transitions using Inertial Sensors in Older Adults with Dementia and Older Caregivers

Thesis (Master's)--University of Washington, 2016-06

Oxygen sensors and energy sensors act synergistically to achieve a graded alteration in gene expression: Consequences for assessing the level of neuroprotection in response to stressors

Changes in gene expression are associated with switching to an autoprotected phenotype in response to environmental and physiological stress. Ubiquitous molecular chaperones from the heat shock protein (HSP) superfamily confer neuronal protection that can be blocked by antibodies. Recent research has focused on the interactions between the molecular sensors that affect the increased expression of neuroprotective HSPs above constitutive levels. An examination of the conditions under which the expression of heat shock protein 70 (Hsp70) was up regulated in a hypoxia and anoxia tolerant tropical species, the epaulette shark (Hemiscyllium ocellatum), revealed that up-regulation was dependent on exceeding a stimulus threshold for an oxidative stressor. While hypoxic-preconditioning confers neuroprotective changes, there was no increase in the level of Hsp70 indicating that its increased expression was not associated with achieving a neuroprotected state in response to hypoxia in the epaulette shark. Conversely, there was a significant increase in Hsp70 in response to anoxic-preconditioning, highlighting the presence of a stimulus threshold barrier and raising the possibility that, in this species, Hsp70 contributes to the neuroprotective response to extreme crises, such as oxidative stress. Interestingly, there was a synergistic effect of coincident stressors on Hsp70 expression, which was revealed when metabolic stress was superimposed upon oxidative stress. Brain energy charge was significantly lower when adenosine receptor blockade, provided by treatment with aminophylline, was present prior to the final anoxic episode, under these circumstances, the level of Hsp70 induced was significantly higher than in the pair-matched saline treated controls. An understanding of the molecular and metabolic basis for neuroprotective switches, which result in an up-regulation of neuroprotective Hsp70 expression in the brain, is needed so that intervention strategies can be devised to manage CNS pathologies and minimise damage caused by ischemia and trauma. In addition, the current findings indicate that measurements of HSP expression per se may provide a useful correlate of the level of neuroprotection achieved in the switch to an autoprotected phenotype.

Feasibility of controlling nitrification in predenitrification plants using DO, pH and ORP sensors

Experimental studies were carried out on a bench-scale nitrogen removal system with a predenitrification configuration to gain insights into the spatial and temporal variations of DO, pH and ORP in such systems. It is demonstrated that these signals correlate strongly with the operational states of the system, and could therefore be used as system performance indicators. The DO concentration in the first aerobic zone, when receiving constant aeration, and the net pH change between the last and first aerobic zones display strong correlations with the influent ammonia concentration for the domestic wastewater used in this study. The pH profile along the aerobic zones gives good indication on the extent of nitrification. The experimental results also showed a good correlation between ORP values in the last aerobic zone and effluent ammonia and nitrate concentrations, provided that DO in this zone is controlled at a constant level. These results suggest that the DO, pH and ORP sensors could potentially be used as alternatives to the on-line nutrient sensors for the control of continuous systems. An idea of using a fuzzy inference system to make an integrated use of these signals for on-line aeration control is presented and demonstrated on the bench-scale system with promising results. The use of these sensors has to date only been demonstrated in intermittent systems, such as sequencing batch reactor systems.