| 1. |
- Aviles, Marcos, et al.
(författare)
-
A co-design methodology for implementing computer vision algorithms for rover navigation onto reconfigurable hardware
- 2011
-
Ingår i: Proceedings of the FPL2011 Workshop on Computer Vision on Low-Power Reconfigurable Architectures. ; , s. 9-10
-
Konferensbidrag (övrigt vetenskapligt/konstnärligt)abstract
- Vision-based robotics applications have been widely studied in the last years. However, up to now solutions that have been proposed were affecting mostly software level. The SPARTAN project focuses in the tight and optimal implementation of computer vision algorithms targeting to rover navigation. For evaluation purposes, these algorithms will be implemented with a co-design methodology onto a Virtex-6 FPGA device.
|
|
| 2. |
- Baudoin, Y., et al.
(författare)
-
View-finder : Robotics assistance to fire-fighting services and crisis management
- 2009
-
Ingår i: Safety, Security & Rescue Robotics (SSRR), 2009 IEEE International Workshop on. - 9781424456291 ; , s. 1-6
-
Konferensbidrag (refereegranskat)abstract
- In the event of an emergency due to a fire or other crisis, a necessary but time consuming pre-requisite, that could delay the real rescue operation, is to establish whether the ground or area can be entered safely by human emergency workers. The objective of the VIEW-FINDER project is to develop robots which have the primary task of gathering data. The robots are equipped with sensors that detect the presence of chemicals and, in parallel, image data is collected and forwarded to an advanced Control station (COC). The robots will be equipped with a wide array of chemical sensors, on-board cameras, Laser and other sensors to enhance scene understanding and reconstruction. At the Base Station (BS) the data is processed and combined with geographical information originating from a web of sources; thus providing the personnel leading the operation with in-situ processed data that can improve decision making. This paper will focus on the Crisis Management Information System that has been developed for improving a Disaster Management Action Plan and for linking the Control Station with a out-site Crisis Management Centre, and on the software tools implemented on the mobile robot gathering data in the outdoor area of the crisis.
|
|
| 3. |
- Chrysostomou, Dimitrios, et al.
(författare)
-
Lighting compensating multiview stereo
- 2011
-
Ingår i: 2011 IEEE International Conference on Imaging Systems and Techniques, IST 2011 - Proceedings. - 9781612848969 ; , s. 176-179
-
Konferensbidrag (refereegranskat)abstract
- In this paper, a method that performs 3D object reconstruction from multiple views of the same scene is presented. This reconstruction method initially produces a basic model, based on the space carving algorithm, that is further refined in a subsequent step. The algorithm is fast, computationally simple and produces accurate representations of the input scenes. In addition, compared to previously presented works the proposed algorithm is able to cope with non uniformly lighted scenes due to the characteristics of the used voxel dissimilarity measure. The proposed algorithm is assessed and the experimental results are presented and discussed.
|
|
| 4. |
- Chrysostomou, Dimitrios, et al.
(författare)
-
Multi-view 3D scene reconstruction using ant colony optimization techniques
- 2012
-
Ingår i: Measurement science and technology. - : IOP Publishing. - 0957-0233 .- 1361-6501. ; 23:11, s. 114002-
-
Tidskriftsartikel (refereegranskat)abstract
- This paper presents a new method performing high-quality 3D object reconstruction of complex shapes derived from multiple, calibrated photographs of the same scene. The novelty of this research is found in two basic elements, namely: (i) a novel voxel dissimilarity measure, which accommodates the elimination of the lighting variations of the models and (ii) the use of an ant colony approach for further refinement of the final 3D models. The proposed reconstruction procedure employs a volumetric method based on a novel projection test for the production of a visual hull. While the presented algorithm shares certain aspects with the space carving algorithm, it is, nevertheless, first enhanced with the lightness compensating image comparison method, and then refined using ant colony optimization. The algorithm is fast, computationally simple and results in accurate representations of the input scenes. In addition, compared to previous publications, the particular nature of the proposed algorithm allows accurate 3D volumetric measurements under demanding lighting environmental conditions, due to the fact that it can cope with uneven light scenes, resulting from the characteristics of the voxel dissimilarity measure applied. Besides, the intelligent behavior of the ant colony framework provides the opportunity to formulate the process as a combinatorial optimization problem, which can then be solved by means of a colony of cooperating artificial ants, resulting in very promising results. The method is validated with several real datasets, along with qualitative comparisons with other state-of-the-art 3D reconstruction techniques, following the Middlebury benchmark.
|
|
| 5. |
- De Cubber, Geert, et al.
(författare)
-
Intelligent robots need intelligent vision : Visual 3D perception
- 2008
-
Konferensbidrag (refereegranskat)abstract
- Contemporary autonomous robots are generally equipped with an abundance of sensors like for example GPS, Laser, ultrasound sensors, etc to be able to navigate in an environment. However, this stands in contrast to the ultimate biological example for these robots: us humans. Indeed, humans seem perfectly capable to navigate in a complex, dynamic environment using primarily vision as a sensing modality. This observation inspired us to investigate visually guided intelligent mobile robots. In order to understand and reason about its environment, an intelligent robot needs to be aware of the three-dimensional status of this environment. The problem with vision, though, is that the perceived image is a two-dimensional projection of the 3D world. Recovering 3D-information has been in the focus of attention of the computer vision community for a few decades now, yet no all-satisfying method has been found so far. Most attention in this area has been on stereo-vision based methods, which use the displacement of objects in two (or more) images. Where stereo vision must be seen as a spatial integration of multiple viewpoints to recover depth, it is also possible to perform a temporal integration. The problem arising in this situation is known as the "Structure from Motion" (SfM) problem and deals with extracting 3-dimensional information about the environment from the motion of its projection onto a two-dimensional surface. In this paper, we investigate the possibilities of stereo and structure from motion approaches. It is not the aim to compare both theories of depth reconstruction with the goal of designating a winner and a loser. Both methods are capable of providing sparse as well as dense 3D reconstructions and both approaches have their merits and defects. The thorough, year-long research in the field indicates that accurate depth perception requires a combination of methods rather than a sole one. In fact, cognitive research has shown that the human brain uses no less than 12 different cues to estimate depth. Therefore, we also finally introduce in a following section a methodology to integrate stereo and structure from motion.
|
|
| 6. |
- De Cubber, Geert, et al.
(författare)
-
Stereo-based terrain traversability analysis for robot navigation
- 2009
-
Ingår i: <em>IARP/EURON Workshop on Robotics for Risky Interventions and Environmental Surveillance</em>.
-
Konferensbidrag (refereegranskat)abstract
- Outdoor mobile robots, which have to navigate autonomously in a totally nstructured environment need to auto-determine the suitability of the terrain around them for traversal. Traversability estimation is a challenging problem, as the traversability is a complex function of both the terrain characteristics, such as slopes, vegetation, rocks, etc and the robot mobility characteristics, i.e. locomotion method, wheel properties, etc. In this paper, we present an approach where a classification of the terrain in the classes “traversable” and “obstacle” is performed using only stereo vision as input data. In a first step, high-quality stereo disparity maps are calculated by a fast and robust algorithm. This stereo algorithm is explained in section 3 of this paper. Using this stereo depth information, the terrain classification is performed, based upon the analysis of the so-called "v-disparity" image which provides a representation of the geometric content of the scene. Using this method, it is possible to detect non-traversable terrain items (obstacles) even in the case of partial occlusion and without any explicit extraction of coherent structures or any a priori knowledge of the environment. The sole algorithm parameter is a single factor which takes into account the robot mobility characteristics. This terrain traversability estimation algorithm is explained in section 4. The stereo disparity mapping and terrain traversability estimation processes are integrated in an autonomous robot control architecture, proving that the algorithms allow real-time robot control. The results of experiments with this robot navigating on rough outdoor terrain are presented in section 5.
|
|
| 7. |
- Fikos, George, et al.
(författare)
-
A 32x32 smart photo-array with minimum-size FGMOS for amplification and FPN reduction
- 2005
-
Ingår i: SiPS 2005. - 0780393341 - 9780780393349 ; , s. 199-203
-
Konferensbidrag (refereegranskat)abstract
- A logarithmic response photoarray, incorporating two minimum-sized floating-gate mosfets (FGMOS) in its basic photocell, is presented. Exploiting the same FGMOS as an analog memory element for Fixed Pattern Noise (FPN) reduction, and as an inherent amplifying element, is, to our knowledge, novel. The above features, favored by the use of small control gate capacitors, lead to area reduction. The circuit behavior is analyzed and experimental results of a 32×32 prototype array implemented in AMS 0.6Όm CMOS technology, are presented and discussed.
|
|
| 8. |
- Fikos, George, et al.
(författare)
-
A compact APS with FPN reduction and focusing criterion using FGMOS photocell
- 2008
-
Ingår i: Sensors and Actuators A-Physical. - : Elsevier BV. - 0924-4247 .- 1873-3069. ; 147:2, s. 419-424
-
Tidskriftsartikel (refereegranskat)abstract
- Prior implementations of CMOS photoarrays with floating-gate MOS (FGMOS), substituted one MOS with a FGMOS in, otherwise, well-established photocell structures. Bipolar manipulation of the floating-gate's charge requires special structures to achieve fixed pattern noise (FPN) suppression. The control capacitor accompanying the FGMOS, needed to be quite larger than the MOS parasitic capacitances, resulting in increased area. Also, output amplification was dealt separately, by additional amplification cells. The proposed logarithmic CMOS photoarray, carefully incorporates two FGMOS in each photocell, favoring the use of minimum control-gate capacitance, achieving area reduction. Unipolar manipulation of floating-gate charge is achieved without special circuitry, preserving FPN suppression. Simultaneously, output amplification is achieved by exploiting the same FGMOS's inherent processing capabilities. A very simple circuit providing a focusing function was also incorporated and successfully tested. Additionally, global normalization towards the average photocurrent, make the circuit ideal preprocessor for image recognition tasks. Experimental results from a 32 × 32 array in AMS 0.6 Όm CMOS technology support the theoretical analysis. © 2008 Elsevier B.V. All rights reserved.
|
|
| 9. |
- Fikos, George, et al.
(författare)
-
A low-voltage, analog power-law function generator
- 2006
-
Ingår i: 2006 IEEE INTERNATIONAL SYMPOSIUM ON CIRCUITS AND SYSTEMS, VOLS 1-11, PROCEEDINGS. - NEW YORK : IEEE. - 0780393902 - 9780780393905 ; , s. 3818-3821
-
Konferensbidrag (refereegranskat)abstract
- A simple low voltage circuit topology able to generate any positive real number power-law function is presented. The proposed circuit exploits BJTs and is based on piecewise linear approximation of the nonlinear function to be generated. An in-depth mathematical analysis is deployed. The instances of a squarer, a cube-law, a square rooting and cube rooting circuit are thoroughly examined through simulation. The obtained results verify the theoretical calculations.
|
|
| 10. |
- Hatzopoulos, Alkis A., et al.
(författare)
-
A built-in current sensor using thin-film transistors
- 2005
-
Ingår i: Second<em> Conference on Microelectronics, Microsystems and Nanotechnology</em>. - : Institute of Physics Publishing (IOPP). ; , s. 289-292
-
Konferensbidrag (refereegranskat)abstract
- A simple current mirror using TFTs with input terminals which are capacitively coupled to the TFT gate, is used in this work, to design a built-in current sensor (BICS). The important feature in this application is that the voltage drop across the sensing TFT device can be reduced to almost zero value, while preserving transistor operation in the saturation region. This makes the proposed BICS appropriate for TFT applications without affecting the circuit operation. It also results in adequate linearity for the current monitoring, making the structure applicable to digital as well as to analog and mixed-signal circuit testing.
|
|
