We proposed a spiking neural network (SNN) to detect moving target in video streams and classify them into real categorization in this paper. The proposed SNN uses spike trains to encoding information such as the gray...
详细信息
ISBN:
(纸本)9783642319181;9783642319198
We proposed a spiking neural network (SNN) to detect moving target in video streams and classify them into real categorization in this paper. The proposed SNN uses spike trains to encoding information such as the gray value of pixels or feature parameters of the target, detects moving target by simulating the visual cortex for motion detection in biological system with axonal delays and classify them into different categorizations according to their distance to categorization's centers found by Hebb learning rule. The experimental results show that the proposed SNN is promising in intelligence computation and applicable in general visual surveillance system.
Predicate logic based reasoning approaches provide a means of formally specifying domain knowledge and manipulating symbolic information to explicitly reason about different concepts of interest. Extension of traditio...
详细信息
Predicate logic based reasoning approaches provide a means of formally specifying domain knowledge and manipulating symbolic information to explicitly reason about different concepts of interest. Extension of traditional binary predicate logics with the bilattice formalism permits the handling of uncertainty in reasoning, thereby facilitating their application to computer vision problems. In this paper, we propose using first order predicate logics, extended with a bilattice based uncertainty handling formalism, as a means of formally encoding pattern grammars, to parse a set of image features, and detect the presence of different patterns of interest. detections from low level feature detectors are treated as logical facts and, in conjunction with logical rules, used to drive the reasoning. Positive and negative information from different sources, as well as uncertainties from detections, are integrated within the bilattice framework. We show that this approach can also generate proofs or justifications (in the form of parse trees) for each hypothesis it proposes thus permitting direct analysis of the final solution in linguistic form. Automated logical rule weight learning is an important aspect of the application of such systems in the computer vision domain. We propose a rule weight optimization method which casts the instantiated inference tree as a knowledge-based neural network, interprets rule uncertainties as link weights in the network, and applies a constrained, back-propagation algorithm to converge upon a set of rule weights that give optimal performance within the bilattice framework. Finally, we evaluate the proposed predicate logic based pattern grammar formulation via application to the problems of (a) detecting the presence of humans under partial occlusions and (b) detecting large complex man made structures as viewed in satellite imagery. We also evaluate the optimization approach on real as well as simulated data and show favorable results.
In mobile robot scenarios, it is expected that the robot autonomously navigates through home or office environments and processes objects/landmarks during navigation. Landmark manipulation is identified as one importa...
详细信息
ISBN:
(纸本)9781424470426
In mobile robot scenarios, it is expected that the robot autonomously navigates through home or office environments and processes objects/landmarks during navigation. Landmark manipulation is identified as one important research area in robot navigation systems. We have developed an online robot landmark processing system (RLPS) to detect, classify, and localize different types of landmarks during robot navigation. The RLPS is based on a two-step classification stage which is robust and invariant towards scaling and translations. It provides a good balance between fast processing time and high detection accuracy by combining the strengths of appearance-based and model-based objectclassification techniques. The experimental results showed that the RLPS is more powerful as it recognizes a wide range of landmarks and efficiently handles landmarks with occlusions, viewpoint variances, and illumination changes.
Cílem této bakalářské práce je naprogramovat model hlubokého učení pro vizuální detekci a klasifikaci obecného objektu z průmyslu. Práce je rozdělena do pěti ka...
详细信息
Cílem této bakalářské práce je naprogramovat model hlubokého učení pro vizuální detekci a klasifikaci obecného objektu z průmyslu. Práce je rozdělena do pěti kapitol. První kapitola se zabývá rešerší nejpoužívanějších architektur tohoto typu. Druhá kapitola se zabývá výběrem nejvhodnější architektury pro použití v průmyslu. Ve třetí kapitole je popsán postup vytváření vlastního datasetu. Ve čtvrté kapitole je pak popsán celý proces samotné implementace modelu tak, aby každá dílčí část architektury byla dostatečně vysvětlena a v páté kapitole jsou popsány výsledky. Shrnutí výsledků a doporučené procedury pro případnou implementaci v reálném prostředí jsou k nalezení v závěru této práce.
暂无评论