1. |
- Adamatzky, Andrew, et al.
(författare)
-
East-West paths to unconventional computing
- 2017
-
Ingår i: Progress in Biophysics and Molecular Biology. - : Elsevier BV. - 0079-6107 .- 1873-1732. ; 131, s. 469-493
-
Forskningsöversikt (refereegranskat)abstract
- Unconventional computing is about breaking boundaries in thinking, acting and computing. Typical topics of this non-typical field include, but are not limited to physics of computation, non-classical logics, new complexity measures, novel hardware, mechanical, chemical and quantum computing. Unconventional computing encourages a new style of thinking while practical applications are obtained from uncovering and exploiting principles and mechanisms of information processing in and functional properties of, physical, chemical and living systems; in particular, efficient algorithms are developed, (almost) optimal architectures are designed and working prototypes of future computing devices are manufactured. This article includes idiosyncratic accounts of ‘unconventional computing’ scientists reflecting on their personal experiences, what attracted them to the field, their inspirations and discoveries.
|
|
2. |
- 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.
|
|
3. |
- 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.
|
|
4. |
- Nalpantidis, Lazaros, et al.
(författare)
-
A dense stereo correspondence algorithm for hardware implementation with enhanced disparity selection
- 2008
-
Ingår i: Artificial Intelligence. - Berlin, Heidelberg : Springer Berlin/Heidelberg. - 9783540878803 ; , s. 365-370
-
Konferensbidrag (refereegranskat)abstract
- In this paper an effective, hardware oriented stereo correspondence algorithm, able to produce dense disparity maps of improved fidelity is presented. The proposed algorithm combines rapid execution, simple and straight-forward structure as well as comparably high quality of results. These features render it as an ideal candidate for hardware implementation and for real-time applications. The proposed algorithm utilizes the Absolute Differences (AD) as matching cost and aggregates the results inside support windows, assigning Gaussian distributed weights to the support pixels, based on their Euclidean distance. The resulting Disparity Space Image (DSI) is furthered refined by Cellular Automata (CA) acting in all of the three dimensions of the DSI. The algorithm is applied to typical as well as to self-recorded real-life image sets. The disparity maps obtained are presented and quantitatively examined.
|
|
5. |
- Nalpantidis, Lazaros, et al.
(författare)
-
Computationally effective stereovision SLAM
- 2010
-
Ingår i: 2010 IEEE International Conference on Imaging Systems and Techniques, IST 2010 - Proceedings. - : IEEE. - 9781424464944 ; , s. 458-463
-
Konferensbidrag (refereegranskat)abstract
- In this paper a visual Simultaneous Localization and Mapping (SLAM) algorithm suitable for indoor area measurement applications is proposed. The algorithm is focused on computational effectiveness. The only sensor used is a stereo camera placed onboard a moving robot. The algorithm processes the acquired images calculating the depth of the scenery, detecting occupied areas and progressively building a map of the environment. The stereo vision-based SLAM algorithm embodies a custom-tailored stereo correspondence algorithm, the robust scale and rotation invariant feature detection and matching Speeded Up Robust Features (SURF) method, a computationally effective v-disparity image calculation scheme, a novel map-merging module, as well as a sophisticated Cellular Automata (CA)-based enhancement stage. The proposed algorithm is suitable for autonomously mapping and measuring indoor areas using robots. The algorithm is presented and experimental results for self-captured image sets are provided and analyzed.
|
|
6. |
- Nalpantidis, Lazaros, et al.
(författare)
-
Dense disparity estimation using a hierarchical matching technique from uncalibrated stereo vision
- 2009
-
Ingår i: IST. - NEW YORK : IEEE. - 9781424434831 - 9781424434824 ; , s. 422-426
-
Konferensbidrag (refereegranskat)abstract
- In motion estimation, the sub-pixel matching technique involves the search of sub-sample positions as well as integer-sample positions between the image pairs, choosing the one that gives the best match. Based on this idea, the proposed disparity estimation algorithm performs a 2-D correspondence search using a hierarchical search pattern. The disparity value is then defined using the distance of the matching position. Therefore, the proposed algorithm can process non-rectified stereo image pairs, maintaining the computational load within reasonable levels.
|
|
7. |
- Nalpantidis, Lazaros, et al.
(författare)
-
Efficient hierarchical matching algorithm for processing uncalibrated stereo vision images and its hardware architecture
- 2011
-
Ingår i: IET Image Processing. - : Institution of Engineering and Technology (IET). - 1751-9659 .- 1751-9667. ; 5:5, s. 481-492
-
Tidskriftsartikel (refereegranskat)abstract
- In motion estimation, the sub-pixel matching technique involves the search of sub-sample positions as well as integer-sample positions between the image pairs, choosing the one that gives the best match. Based on this idea, this work proposes an estimation algorithm, which performs a 2-D correspondence search using a hierarchical search pattern. The intermediate results are refined by 3-D cellular automata (CA). The disparity value is then defined using the distance of the matching position. Therefore the proposed algorithm can process uncalibrated and non-rectified stereo image pairs, maintaining the computational load within reasonable levels. Additionally, a hardware architecture of the algorithm is deployed. Its performance has been evaluated on both synthetic and real self-captured image sets. Its attributes, make the proposed method suitable for autonomous outdoor robotic applications.
|
|
8. |
- Nalpantidis, Lazaros, et al.
(författare)
-
Non-probabilistic cellular automata-enhanced stereo vision simultaneous localization and mapping
- 2011
-
Ingår i: Measurement science and technology. - : IOP Publishing. - 0957-0233 .- 1361-6501. ; 22:11, s. 114027-
-
Tidskriftsartikel (refereegranskat)abstract
- In this paper, a visual non-probabilistic simultaneous localization and mapping (SLAM) algorithm suitable for area measurement applications is proposed. The algorithm uses stereo vision images as its only input and processes them calculating the depth of the scenery, detecting occupied areas and progressively building a map of the environment. The stereo vision-based SLAM algorithm embodies a stereo correspondence algorithm that is tolerant to illumination differentiations, the robust scale- and rotation-invariant feature detection and matching speeded-up robust features method, a computationally effective v-disparity image calculation scheme, a novel map-merging module, as well as a sophisticated cellular automata-based enhancement stage. A moving robot equipped with a stereo camera has been used to gather image sequences and the system has autonomously mapped and measured two different indoor areas.
|
|
9. |
- Nalpantidis, Lazaros, et al.
(författare)
-
Review of stereo matching algorithms for 3D vision
- 2007
-
Ingår i: 16th International Symposium on Measurement and Control in Robotics.
-
Konferensbidrag (refereegranskat)abstract
- Stereo vision, resulting in the knowledge of deep information in a scene, is of great importance in the field of machine vision, robotics and image analysis. As a result, in order to address the problem of matching points between two images of a stereo pair several algorithms have been proposed so far. In this paper, an explicit analysis of the existing stereo matching methods, up to date, is presented in full detail. The algorithms found in literature can be grouped into those producing sparse output and those giving a dense result, while the later can be classified as local (area-based) and global (energy- based). The presented algorithms are discussed in terms of speed, accuracy, coverage, time consumption and disparity range. Comparative test results concerning different image sizes as well as different stereo data sets are presented. Furthermore, the usage of advanced computational intelligence techniques such as neural networks and cellular automata in the development and application of such algorithms is also considered. However, due to the fact that the resulting depth calculation is a computationally demanding procedure, most of the presented algorithms perform poorly in real-time applications. Towards this direction, the development of real-time stereo matching algorithms, able to be efficiently implemented in dedicated hardware is of great interest in the contexts of 3D reconstruction, simultaneous localization and mapping (SLAM), virtual reality, robot navigation and control. Some possible implementations of stereo- matching algorithms in hardware for real-time applications are also discussed in details.
|
|
10. |
- Nalpantidis, Lazaros, et al.
(författare)
-
Review of stereo vision algorithms : From software to hardware
- 2008
-
Ingår i: International Journal of Optomechatronics. - : Informa UK Limited. - 1559-9612 .- 1559-9620. ; 2:4, s. 435-462
-
Forskningsöversikt (refereegranskat)abstract
- Stereo vision, resulting in the knowledge of deep information in a scene, is of great importance in the field of machine vision, robotics and image analysis. In this article, an explicit analysis of the existing stereo matching methods, up to date, is presented. The presented algorithms are discussed in terms of speed, accuracy, coverage, time consumption, and disparity range. Towards the direction of real-time operation, the development of stereo matching algorithms, suitable for efficient hardware implementation is highly desirable. Implementations of stereo matching algorithms in hardware for real-time applications are also discussed in details.
|
|