作者:
Li, JingmengWei, HuiFudan University
Laboratory of Algorithms for Cognitive Models School of Computer Science Shanghai200438 China Fudan University
Laboratory of Algorithms for Cognitive Models Innovation Center of Calligraphy and Painting Creation Technology MCT School of Computer Science Shanghai200438 China
Perceptual edge grouping is a technique for organizing the cluttered edge pixels into meaningful structures and further serves high-level vision tasks, which has long been a basic and critical task in computer vision....
详细信息
This study presents an enhanced genetic algorithm to generate high-quality, dense disparity maps in low-illumination indoor stereo matching scenarios. The algorithm utilizes a novel biomimetic mutation strategy, dynam...
详细信息
We aim to advance in constructing collaborative agents able to acquire the contents of human vocabulary associated with competitions. Refining the framework and criteria of performance of agents we project the study o...
详细信息
ISBN:
(纸本)9783540728382
We aim to advance in constructing collaborative agents able to acquire the contents of human vocabulary associated with competitions. Refining the framework and criteria of performance of agents we project the study on the class of game tree represented competition problems. For known representative of the class - chess like combinatorial games, we categorize the contents of a comprehensive repository of units of chess vocabulary by formal structures of attributes, goals, strategies, plans, etc. We define Personalized Planning and Integrated Testing algorithms able to elaborate moves in target positions dependent on those categories of chess knowledge. We then demonstrate the effectiveness of the algorithms by experiments in acquisition the solutions of two top Botvinnik's tests - the Reti and Nodareishvili etudes. For min max game tree based search algorithms these etudes appears to be computationally hard due the depth of the required analysis and very dependence on the expert knowledge.
Monocular vision-based navigation is a considerable ability for a home mobile robot. However, due to diverse disturbances, helping robots avoid obstacles, especially nonManhattan obstacles, remains a big challenge. In...
详细信息
Monocular vision-based navigation is a considerable ability for a home mobile robot. However, due to diverse disturbances, helping robots avoid obstacles, especially nonManhattan obstacles, remains a big challenge. In indoor environments, there are many spatial right-corners that are projected into two dimensional projections with special geometric configurations. These projections, which consist of three lines,might enable us to estimate their position and orientation in 3 D scenes. In this paper, we present a method for home robots to avoid non-Manhattan obstacles in indoor environments from a monocular camera. The approach first detects non-Manhattan obstacles. Through analyzing geometric features and constraints,it is possible to estimate posture differences between orientation of the robot and non-Manhattan obstacles. Finally according to the convergence of posture differences, the robot can adjust its orientation to keep pace with the pose of detected non-Manhattan obstacles, making it possible avoid these obstacles by itself. Based on geometric inferences, the proposed approach requires no prior training or any knowledge of the camera’s internal parameters,making it practical for robots navigation. Furthermore, the method is robust to errors in calibration and image noise. We compared the errors from corners of estimated non-Manhattan obstacles against the ground truth. Furthermore, we evaluate the validity of convergence of differences between the robot orientation and the posture of non-Manhattan obstacles. The experimental results showed that our method is capable of avoiding non-Manhattan obstacles, meeting the requirements for indoor robot navigation.
We aim to understand the role and proportion of personalized expertise compared with common, communicable one. To make the studying constructive we concentrate on a particular class of game represented problems and go...
详细信息
ISBN:
(纸本)9781627483315
We aim to understand the role and proportion of personalized expertise compared with common, communicable one. To make the studying constructive we concentrate on a particular class of game represented problems and go in the depth of a typical representative of the class, the chess. We simulate and analyze expert requests to the games storage in a natural language to find winning strategies of the specified types. The correspondence revealed between units of chess vocabulary and winning by zermelo classes of chess positions and strategies argues for a constructive nature of the content of the units, in principle, allowing to simulate them. At the same time it states that any real implementation of those contents, in principle, can be only an approximation to the original winning game tree structures due to a prohibitive complexity of computations required to prove correctness of the vast majority of the contents. Thus, we get a precedent of a measurable specification of human expertise where the learned contents of realities having the same vocabulary, as a rule, are essentially personalized.
The capacity of long-term memory seems to be extremely large, capable of storing information spanning almost a lifetime. Why does it have such a vast capacity? Why are some memories so enduring? What is the actual phy...
详细信息
Visual emergence is the phenomenon in which the visual system obtains a holistic perception after grouping and reorganizing local signals. The picture Dalmatian dog is known for its use in explaining visual emergence....
详细信息
The neural mechanism of memory has a very close relation with the problem of representation in artificial intelligence. In this paper a computational model was proposed to simulate the network of neurons in brain and ...
详细信息
Deep-learning algorithms have an excellent nonlinear fitting ability. However, tiny objects in images do not approach the general properties of the fit, which causes the algorithms to have problems acquiring disparity...
详细信息
Humans promote themselves in the universe, the totality of their realities, while by processing of meanings they enhance the effectiveness and efficiency of the promotion. Humans communicate by explanation and acquisi...
详细信息
ISBN:
(纸本)9781479924622
Humans promote themselves in the universe, the totality of their realities, while by processing of meanings they enhance the effectiveness and efficiency of the promotion. Humans communicate by explanation and acquisition of meanings, while acquire meanings by their understanding and learning. In paper we provide language explanations of meanings on some realities tended to specifications of constructive and adequate models of meaning processing. We discuss constrains on meanings induced by the models and corresponding constrains on cognition of realities as well as provide experimental evidence supporting a viability of the models.
暂无评论