is then refined and simplified so as to include as few points as possible, giving a compact representation of the original scene. After that, a mesh of the scene is created which virtual reality engines can then use to render the scene in a virtual environment. Heikkilä and his team also hope to make


advances in reproducing the colours of objects as accurately as possible. “Photographs usually don’t represent the true colours of objects,” he explains. “The colours you see are a combination of the reflectance that comes from the object as well as the effect of illumination. We try to compensate for the illumination effect and find the actual colours to reproduce for the models.” Another part of Heikkilä’s research


concerns free-viewpoint rendering. This involves the generation of synthetic images of a scene from a set of reference photos. “Assuming you have enough images of a scene from different viewpoints, it is possible to generate synthetic images from new viewpoints that maintain the original 3D structure of the scene.”


pose recognition will tell you the location where that image is being seen from in respect to a large scale model. For example, one could take a photo in a city, which could then be used to calculate the coordinates of the person who has taken that photo.” Heikkilä sees this technique playing an important role in the augmented reality applications that are likely to take off with the advent of Google Glass.


Energy-efficient embedded vision systems Vision systems engineering research aims to identify attractive computing approaches, architectures, and algorithms for industrial systems. Professor Olli Silvén explains that solutions from low-level image processing to equipment installation and operating procedures are considered simultaneously. Silvén’s team has demonstrated energy efficiencies that rival those of comparable hardwired solutions. The roots of the CMV’s expertise in this area are in its visual inspection studies from the 1980s. Work in this area now also covers applications intended for


smart environments and


embedded platforms. In the field of energy-efficient embedded


“Photographs usually don’t represent the true colours of objects, the colours you see are a combination of the reflectance that comes from the object as well as the effect of illumination”


The final area of research in this area is


image localisation in the exciting field of augmented


reality. Simultaneous


Localisation and Mapping (SLAM) is a key component of augmented reality applications. The SLAM module reconstructs the 3D structure of a scene while simultaneously estimating the camera position. The CMV is now working on a new SLAM framework that is able to handle both triangulated and non-triangulated features simultaneously. It allows the user to move the camera without restrictions and thus provides more freedom than the current state of the art. As well as this, Heikkilä’s group have working


been on so-called www.projectsmagazine.eu.com pose recognition: “Given an arbitrary image,


computer vision, several variants of the LBP operator have been implemented in multiple mobile and custom processors. The embedded platforms used range from multicore-ARM and mobile GPUs to TTA processors and a hybrid SIMD/MIMD image co-processor. Different implementations have been compared


in terms of computational


performance and energy efficiency, while analysing the different optimisations that can be made on each platform and its different available computing resources. In addition, a software package has been released, providing a valuable tool for other researchers


and computationally developers. intensive Two multimedia


applications - face detection and depth estimation - were implemented and optimised for parallel processing using the Portable computing language (PoCL) implementation of Open Computing Language (OpenCL). So far, the benchmarks have been implemented on desktop CPU and GPU. An initial design of an energy efficient multicore transport triggered architecture (TTA) processor that could achieve the same performance with significantly lower energy consumption has also been implemented, but not yet benchmarked. The Energy Efficient Architectures and


Signal Processing team of CMV has been working on design automation and energy efficient computing for signal processing


applications. A remarkable new opening was the initiation of a joint US-Finnish research project CREAM, together with the Centre for Wireless Communications. During the first project year, the research focus has been on dataflow modelling


and energy-efficient


implementation of a digital pre-distortion filter for wireless mobile transmitters.


Looking to the future The CMV will continue to carry out well- focused, cutting-edge research in the field of machine vision. Plans are in place for the centre to further deepen its collaboration with international and domestic partners, and it is now participating in new European project proposals. Close interaction between basic and applied research has always been a major strength of the research unit, which has seen its scientific output increase significantly in recent years. This will help to maintain its


continued potential for


producing novel innovations and exploiting research results in collaboration with companies and other partners.


★ 83


AT A GLANCE Project Information


Project Title: Centre for Machine Vision Research (CMV)


MAIN CONTACT


Matti Pietikäinen Matti Pietikäinen (IEEE Fellow, IAPR Fellow) is Professor of Computer Science and Engineering and Director of Centre for Machine Vision Research at the University of Oulu. He is world-renowned for his research on computer vision and image analysis. He has authored/ co-authored about 300 refereed publications. His papers have over 20,000 citations in Google Scholar.


Contact: Tel: +358 29 448 2782 Email: mkp@ee.oulu.fi Web: www.cse.oulu.fi/CMV


Page 1  |  Page 2  |  Page 3  |  Page 4  |  Page 5  |  Page 6  |  Page 7  |  Page 8  |  Page 9  |  Page 10  |  Page 11  |  Page 12  |  Page 13  |  Page 14  |  Page 15  |  Page 16  |  Page 17  |  Page 18  |  Page 19  |  Page 20  |  Page 21  |  Page 22  |  Page 23  |  Page 24  |  Page 25  |  Page 26  |  Page 27  |  Page 28  |  Page 29  |  Page 30  |  Page 31  |  Page 32  |  Page 33  |  Page 34  |  Page 35  |  Page 36  |  Page 37  |  Page 38  |  Page 39  |  Page 40  |  Page 41  |  Page 42  |  Page 43  |  Page 44  |  Page 45  |  Page 46  |  Page 47  |  Page 48  |  Page 49  |  Page 50  |  Page 51  |  Page 52  |  Page 53  |  Page 54  |  Page 55  |  Page 56  |  Page 57  |  Page 58  |  Page 59  |  Page 60  |  Page 61  |  Page 62  |  Page 63  |  Page 64  |  Page 65  |  Page 66  |  Page 67  |  Page 68  |  Page 69  |  Page 70  |  Page 71  |  Page 72  |  Page 73  |  Page 74  |  Page 75  |  Page 76  |  Page 77  |  Page 78  |  Page 79  |  Page 80  |  Page 81  |  Page 82  |  Page 83  |  Page 84  |  Page 85  |  Page 86  |  Page 87  |  Page 88  |  Page 89  |  Page 90  |  Page 91  |  Page 92  |  Page 93  |  Page 94  |  Page 95  |  Page 96  |  Page 97  |  Page 98  |  Page 99  |  Page 100  |  Page 101  |  Page 102  |  Page 103  |  Page 104  |  Page 105  |  Page 106  |  Page 107  |  Page 108  |  Page 109  |  Page 110  |  Page 111  |  Page 112