Danilo Pietro Pau

Sort Middle Pipeline Architecture for Efficient 3D Rendering

This paper presents a high performance fixed function 3D graphics pipeline based on sort-middle computing paradigm. The proposed architecture implements the full specification of the OpenGL|ES 1.1 open standard and is specifically designed for a cost effective integration on consumer devices, in particular on low-power mobile ones.

Visual Search of multiple objects from a single query

Hundreds of millions of images are uploaded to the cloud every day. Innovative applications able to analyze and extract efficiently information from such a big database are needed nowadays more than ever. Visual Search is an application able to retrieve information of a query image comparing it against a large image database. In this paper a Visual Search pipeline implementation is presented able to retrieve multiple objects depicted in a single query image. Quantitative and qualitative precision results are shown on both real and synthetic datasets.

Mixing retrieval and tracking using compact visual descriptors

Visual search has seen many improvements over the years, but its application on video content is still an open research problem and it is often limited to still images. Based on the tools devised by the standardization group MPEG CDVS, we developed a processing flow that processes at nearly real-time a video acquired with a low cost imager and performs content search and retrieval of the top match from a local database. To allow efficient interest point detection, we used a GPU accelerated SIFT library. To process the video frames efficiently, we developed a new dataflow processing which allows switching between object searching, retrieving and tracking in order to keep at minimum the number of queries sent to the database. A search into a local database is performed only when no object has been recognized, and once a good match has been found, the algorithm switches to tracking mode.

FAST detector on many-core computers

Many-core architectures are becoming increasingly popular due to advances in open programming environments. Typical architectures are Graphics Processing Units (GPUs) and Homogenous Computing Fabrics, offering high computing parallelism in order to decrease execution time of computationally intensive algorithms, for example in Computer Vision. In this paper, a low complexity interest point detector has been written in OpenCL language and executed on different desktop and embedded computing platforms. The algorithm performs interest point detection in an image, around which there is enough distinctive information to enable further description. The algorithm has been optimized on the targeted platforms and performance and accuracy comparison has been performed.

Embedded Real-Time Visual Search with Visual Distance Estimation

Visual Search algorithms are a class of methods that retrieve images by their content. In particular, given a database of reference images and a query image the goal is to find an image among the database that depicts the same object as in the query, if any. Moreover, in many different real case applications more than one object of interest could be viewed in the query image. Furthermore, in this kind of situations, often, it is not sufficient to identify the object depicted on a query image but its precise localization inside the scene viewed by the camera is also requested. In this paper we propose to couple a Visual Search system, which can retrieve multiple objects from the same query image, with an additional Distance Estimation module that exploits the localization information already computed inside the Visual Search stage to estimate localization of the object in three dimensions. In this work we implement the complete image retrieval and spatial localization pipeline (including relative distance estimation) on two different embedded devices, exploiting also their GPU in order to get near real time performances on low-power devices. Lastly, the accuracy of the proposed distance estimation is evaluated on a dataset of annotated query-reference pairs ad-hoc created.

Accurate cyber-physical system simulation for distributed visual search applications

A Cyber-Physical System (CPS) is defined as a, usually distributed, system that links the digital (cyber) and physical world. They feature different computational cores and heterogeneous sensors linked through networks of different types allowing a deeper interaction with the physical world, collecting, storing and exchanging information intelligently. In this work, an open source CPS simulator called COSSIM is described and a smart mechanism is proposed in order to turn it into a co-simulator. In addition to this, a CPS based on a Computer Vision application, called Mobile Visual Search (MVS), is described and ported to COSSIM in order to test the correctness of the simulation and to prove the benefit of the proposed acceleration. Quantitative and qualitative precision results in both real and simulated scenarios are also presented.

Acceleration of SVD routines in LAPACK

Singular Value Decomposition is widely used in many different engineering applications like Image Processing, Image Compression, Principle Component Analysis etc. It is also very useful in statistical analysis for Least Squares Approximations, and Data Clustering for reducing data dimensionality. Its power consists in its capability to serve as a single method for analysing several features in a matrix. Its computation involves a sequence of vector kind operations which makes it computationally intensive. This paper addresses optimisations of computation of Singular Value Decomposition as implemented in LAPACK library by parallelizing on the Graphics Processing Unit architecture using OpenCL. Its programmable architecture suits well because of its flexibility and native support for vector operations and OpenCL is a key enabler for making the implementation platform independent and portable.

Adaptive Frame Rate Up-conversion for 3D Graphics Pipelines

This paper presents a novel 3D graphics pipeline for consumer devices able to achieve increased frame-rate at its output, high picture quality, improved temporal anti-aliasing, thanks to a frame-rate up-conversion algorithm based on motion extraction from 3D primitives and efficient compensation, without the need for any motion estimation tool.

3D Graphics Pipeline Enabled for MPEG2 Decoding

A novel fixed functionality computing model for synthetic and video image rendering is presented. An OpenGL-ES 1.1 3D graphics pipeline has been used and modified to decode MPEG2 bitstreams ranging from QCIF up to HD resolution achieving drift free quality compared to an MPEG2 decoder output.