Bernardo Reis

Nearest Neighbor Searches on the GPU

We introduce a GPU grid-based data structure for massively parallel nearest neighbor searches for dynamic point clouds. The implementation provides real-time performance and it is executed on GPU, both grid construction and nearest neighbors (approximate or exact) searches. This minimizes the memory transfer between device and system memories, improving overall performance. The proposed algorithm may be used across different applications with static and dynamic scenarios. Moreover, our data structure supports three-dimensional point clouds and given its dynamic nature, the user can change the data structure’s parameters at runtime. The same applies to the number of neighbors to be found. Performance comparisons were made against previous works, endorsing the benefits of our solution. Finally, we were able to develop a real-time Point-Based Rendering application for validation of the data structure. Its drawbacks and data distribution’s impact on performance were analysed and some directions for further investigation are given.

Open/Closed Hand Classification Using Kinect Data

This work proposes a study over five different hand gesture classifiers using depth and skeleton data from the Kinect sensor. Evaluations of sensibility, specificity and computational costs are performed for the purpose of choosing which methods are the most adequate. In spite of the low computational complexity of the tested classifiers, the results obtained are of similar quality compared to other complex approaches. All tested classifiers have been gathered in an open-source library for hand classification using the Kinect.

Increasing kinect application development productivity by an enhanced hardware abstraction

Designing and implementing the interaction behavior for body tracking capable systems requires complex modeling of actions and extensive calibration. Being the most recent and successful device for robust interactive body tracking, Microsofts Kinect has enabled natural interaction by the use of consumer hardware, providing detailed and powerful information to designers and developers, but little tooling. To fulfill this lack of adequate tools for helping developers in the prototyping and implementation of such interfaces, we present Kina, a toolkit that makes the development not fully conditional to the existence of a sensor. By providing playback capabilities together with an online movement database, it reduces the physical effort found while performing testing activities.

Stereo Tracking and 3D Reconstruction of Underwater Pipes.

Installing flexible oil pipes in deep underwater environments is a risky operation, which is currently monitored by manually comparing the geometric conditions to the simulated studies. In order to avoid this error-prone assessment, this paper proposes an algorithm to track and reconstruct the pipe medial axis using stereo cameras. By taking advantage of the scenario illumination and the pipe texture, it is possible to devise an energy maximization approach that efficiently tracks the pipe. The reconstruction technique is an enhancement over a state-of-the-art B-spline reconstruction algorithm, specializing it for plane curves. Experiments on synthetic and laboratory videos report a very low mean tracking and reconstruction errors, while there are strong evidences of the robustness on a real scenario.

Design Methodology for Body Tracking Based Applications - A Kinect Case Study

Along with the popularization of new body tracking technologies such as Microsoft Kinect, and the increasing individual initiatives in order to design solutions for such platforms, it is necessary to improve and to adapt all the framework of methods and processes for developing new applications for this context. Just like that, this paper proposes a direction towards the formalization of an agile methodology for developing new applications on the background of body interaction, suitable for modest innovation projects with short schedules and small teams. To achieve that, we executed an experiment during a graduate course in Informatics, due to its similarities to the start-up context. The participating students followed a four-step methodology comprehending the stages of requirements identification, ideas generation, prototyping, and evaluation. The experiment outcomes are described in a way to enlighten the methodology techniques. As a conclusion, the students provided an extremely positive feedback regarding the adoption of the proposed methodology during the development of body interaction applications.

Dynamic QR Codes for Augmented Reality

This work proposes the use of Quick Response (QR) codes as a mechanism of simultaneous data transmission and also 2D-3D registration for marker-based augmented reality (AR) systems. The decisions regarding the chosen 2D barcode were based on an analysis of the relationship between data size and available transmission time. The developed case study showed to be successful both at the detection of QR codes under perspective distortion and at the transmission of 3D models over the codes for further rendering.

An optimized label-broadcast parallel algorithm for connected components labeling

This paper presents a simple and fast algorithm for labeling connected components in binary images, based on a parallel label-broadcast paradigm. A grid of processing units (called spiders) is used and each element is responsible for updating its label value, during a specific number of iterations. We describe the design and implementation of an embedded architecture for real-time labeling of black and white images based on FPGA technology. Since the image is divided and processed independently by processing elements, it is possible to use the proposed algorithm in an FPGA platform attached to an image sensor and have a focal plane processor circuit-like.