We propose an approach to determine the occurrence of low-parametric qualitative models from images by a hypothesis-and-test approach based on the coincidence of multiple cues, thereby avoiding complete reconstruction...
详细信息
We propose an approach to determine the occurrence of low-parametric qualitative models from images by a hypothesis-and-test approach based on the coincidence of multiple cues, thereby avoiding complete reconstruction...
详细信息
We propose an approach to determine the occurrence of low-parametric qualitative models from images by a hypothesis-and-test approach based on the coincidence of multiple cues, thereby avoiding complete reconstruction of the scene. A system is presented which applies the approach to finding instances of planar surfaces, as it is important in many tasks for mobile or manipulating robots. The system uses monocularly determined L-junctions and binocular disparities. A notable feature of the approach is that it finds the most conspicuous exemplar of the model first. This property seems quite relevant for an agent using vision to guide its behaviors, since the simplest solution becomes available early on.
We stress a systems approach for research in active vision. We also argue that design and analysis of seeing agents should be accompanied by experiments, requiring implementations, i.e. a constructive approach. In par...
详细信息
We stress a systems approach for research in active vision. We also argue that design and analysis of seeing agents should be accompanied by experiments, requiring implementations, i.e. a constructive approach. In particular, we discuss two issues that we have worked with: use and integration of multiple cues and attention.
A co-evolutionary approach for developing programs for controlling a very simple "robot-like" simulated vehicle is presented. The main goal is to find programs that can generalize and solve other similar pro...
详细信息
We present a computational model for attention. It consists of an early parallel stage with preattentive cues followed by a later serial stage, where the cues are integrated. We base the model on disparity image flow ...
详细信息
We present a computational model for attention. It consists of an early parallel stage with preattentive cues followed by a later serial stage, where the cues are integrated. We base the model on disparity image flow and motion. As one of the several possibilities we choose a depth-based criterion to integrate these cues, in such a way that the attention is maintained to the closest moving object. We demonstrate the technique by experiments in which a moving observer selectively mask our different moving objects in real scenes.
HCV is a heuristic attribute-based induction algorithm based on the newly-developed extension matrix approach. By dividing the positive examples (PE) of a specific class in a given example set into intersecting groups...
详细信息
HCV is a heuristic attribute-based induction algorithm based on the newly-developed extension matrix approach. By dividing the positive examples (PE) of a specific class in a given example set into intersecting groups and adopting a set of strategies to find a heuristic conjunctive formula in each group which covers all the group’s positive examples and none of the negative examples (NE), it can find a covering formula in the form of variable-valued logic for PE against NE in low-order polynomial time. The original algorithm performs quite well with those data sets where noise and continuous data are not of major concern. However, its performance decreases when the data sets are noisy and contain continuous attributes. This paper presents noise handling techniques developed and implemented in HCV (Version 2.0), a noise tolerant version of the HCV algorithm, and provides a performance comparison of HCV with other inductive algorithms C4.5 and NewID in noisy and continuous domains.
In a recurrent artificial neural network, the units active in an attractor state typically reach their maximum activity value while the others are quiescent. In contrast, recordings of cortical cell activity in vivo r...
详细信息
In a recurrent artificial neural network, the units active in an attractor state typically reach their maximum activity value while the others are quiescent. In contrast, recordings of cortical cell activity in vivo rarely reveal cells firing at their maximum rate. This discrepancy has been one of the main arguments against using attractor networks as models of cortical associative memory. In this study we show that low-rate sustained after-activity can be obtained in a simulated network of mutually exciting pyramidal cells. This is achieved by assuming that the synapses in the network are of a saturating type. When the application of a monoamine neuromodulator is simulated, after-activity with firing rates around 60?s?1 can be produced. The firing pattern of the network was found to be similar to that of the experimentally most comparable system, the disinhibited hippocampal slice. The results obtained are robust against simulated biological variation and background noise.
作者:
Nordlund, PeterUhlin, Tomas
Department of Numerical Analysis Computing Science Royal Institute of Technology StockholmS-10044 Sweden
We present an integrated system, able to pursue a moving object by controlling a robot-head to maintain the moving object centered in the image. This system runs continuously in time and updates the object localizatio...
详细信息
The approximability of several NP maximization problems is investigated and strong lower bounds for the studied problems are proved. For some of the problems the bounds are the best that can be achieved, unless P = NP...
详细信息
作者:
Fornland, Päir
Department of Numerical Analysis and Computing Science Royal Institute of Technology StockholmS-100 44 Sweden
Autonomous vehicles need a means of detecting obstructions on its path, to avoid collision. In this paper, a novel approach to obstacle detection is presented. A camera moves on a visible ground plane with the optical...
详细信息
暂无评论