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.

Comparing Common Data Environment Platforms for Student Collaborative Working: A Case Study from Ulster University

PAS1192-2 (2013) outlines the “fundamental principles of Level 2 information modeling”, one of these principles is the use of what is commonly referred to as a Common Data Environment (CDE). A CDE could be described as an internet-enabled cloudhosting platform, accessible to all construction team members to access shared project information. For the construction sector to achieve increased productivity goals, the next generation of industry professionals will need to be educated in a way that provides them with an appreciation of Building Information Modelling (BIM) working methods, at all levels, including an understanding of how data in a CDE should be structured, managed, shared and published. This presents a challenge for educational institutions in terms of providing a CDE that addresses the requirements set out in PAS1192-2, and mirrors organisational and professional working practices without causing confusion due to over complexity. This paper presents the findings of a two-year study undertaken at Ulster University comparing the use of a leading industry CDE platform with one derived from the in-house Virtual Learning Environment (VLE), for the delivery of a student BIM project. The research methodology employed was a qualitative case study analysis, focusing on observations from the academics involved and feedback from students. The results of the study show advantages for both CDE platforms depending on the learning outcomes required.

Pencil it in: pencil drawn electrochemical sensing platforms

Inspired by recent reports concerning the utilisation of hand drawn pencil macroelectrodes (PDEs), we report the fabrication, characterisation (physicochemical and electrochemical) and implementation (electrochemical sensing) of various PDEs drawn upon a flexible polyester substrate. Electrochemical characterisation reveals that there are no quantifiable electrochemical responses upon utilising these PDEs with an electroactive analyte that requires an electrochemical oxidation step first, therefore the PDEs have been examined towards the electroactive redox probes hexaammineruthenium(III) chloride, potassium ferricyanide and ammonium iron(II) sulfate. For the first time, characterisation of the number of drawn pencil layers and the grade of pencil are examined; these parameters are commonly overlooked when utilising PDEs. It is demonstrated that a PDE drawn ten times with a 6B pencil presented the most advantageous electrochemical platform, in terms of electrochemical reversibility and peak height/analytical signal. In consideration of the aforementioned limitation, analytes requiring an electrochemical reduction as the first process were solely analysed. We demonstrate the beneficial electroanalytical capabilities of these PDEs towards p-benzoquinone and the simultaneous detection of heavy metals, namely lead(II) and cadmium(II), all of which are explored for the first time utilising PDEs. Initially, the detection limits of this system were higher than desired for electroanalytical platforms, however upon implementation of the PDEs in a back-to-back configuration (in which two PDEs are placed back-to-back sharing a single connection to the potentiostat), the detection limits for lead(II) and cadmium(II) correspond to 10 μg L−1 and 98 μg L−1 respectively within model aqueous (0.1 M HCl) solutions.