scholarly journals Adaptive Shape Kernel-Based Mean Shift Tracker in Robot Vision System

2016 ◽  
Vol 2016 ◽  
pp. 1-8 ◽  
Author(s):  
Chunmei Liu ◽  
Yirui Wang ◽  
Shangce Gao
Keyword(s):  
Manifold Learning ◽  
Vision System ◽  
Mean Shift ◽  
Robot Vision ◽  
Shape Space ◽  
Training Data ◽  
Learning Technique ◽  
Adaptive Kernel ◽  
Dimensional Shape ◽  
Low Dimensional

This paper proposes an adaptive shape kernel-based mean shift tracker using a single static camera for the robot vision system. The question that we address in this paper is how to construct such a kernel shape that is adaptive to the object shape. We perform nonlinear manifold learning technique to obtain the low-dimensional shape space which is trained by training data with the same view as the tracking video. The proposed kernel searches the shape in the low-dimensional shape space obtained by nonlinear manifold learning technique and constructs the adaptive kernel shape in the high-dimensional shape space. It can improve mean shift tracker performance to track object position and object contour and avoid the background clutter. In the experimental part, we take the walking human as example to validate that our method is accurate and robust to track human position and describe human contour.

scholarly journals An effective model for quantification of cell 3Dshape in early embryogenesis

2021 ◽  
Author(s):  
Zelin Li ◽  
Jianfeng Cao ◽  
Zhongying Zhao ◽  
Hong Yan
Keyword(s):  
Cell Fate ◽  
Cell Shape ◽  
Developmental Process ◽  
Morphological Changes ◽  
Shape Space ◽  
Effective Model ◽  
Cell Stage ◽  
Cell Shapes ◽  
Dimensional Shape ◽  
Low Dimensional

Abstract Background: The developmental process is featured by fabulous morphogenesis in multicellular organisms. Describing morphological changes quantitatively concretes the way to investigating both intra and inter cell regulations on cell fate. While Caenorhabditis elegans has been used as a model for cell and development studies for a long time, the exploration of how cell shape is precisely controlled keeps obscured by the lack of methods to model morphological features. Currently, in order to characterize the features of cell shape involved in cell migration and differentiation, there is an increasing demand in analyzing cell shape systematically, especially when many works have contributed to cell reconstruction. Results: In this work, Spherical harmonics and Principal component analysis integrated Cell Shape quantification Models (SPCSMs) is proposed to represent cell shapes in a low-dimensional shape space. SPCSMs incorporates a complete pipeline to quantify cell shapes and analyze their morphological phenotypes in three dimensional (3D) reconstructions. Based on the framework, we extract biological patterns in the lineage of C. elegans embryo before 350-cell stage, during which all hypodermis cells deformed like a funnel and can be recognized by this shape pattern. Finally, SPCSMs is compared with two cell shape representation methods, which substantiates the effectiveness and robustness of our method. Conclusion: SPCSMs provides a general method to decribe shapes in low-dimensional shape space with compact parameters. It can quantify the shapes of cells from single-cell resolution images obtained over one-minute intervals, making it possible for the recognition of developmental patterns in cell lineages. SPCSMs is expected to be an effective model for biologists to explore the relationships between the shapes of cells and their fates.

What is wrong with prototypes

1998 ◽  
Vol 21 (4) ◽  
pp. 471-472 ◽  
Author(s):  
Peter Földiák
Keyword(s):  
Shape Space ◽  
Dimensional Shape ◽  
Low Dimensional

Representing objects and concepts as points in low-dimensional shape space defined by distances to other complete object exemplars or prototypes, expressed as single numbers, misses the key advantages of representation in terms of hierarchically constructed, meaningful features of the environment. Generalisation along statistically significant, near-independent, sparse, cooperative features that stand directly for various aspects of a concept is essential.

scholarly journals Serial disparity in the carnivoran backbone unveils a complex adaptive role in metameric evolution

2021 ◽  
Vol 4 (1) ◽  
Author(s):  
Borja Figueirido ◽  
Alberto Martín-Serra ◽  
Alejandro Pérez-Ramos ◽  
David Velasco ◽  
Francisco J. Pastor ◽  
...  
Keyword(s):  
Evolutionary Constraint ◽  
Phenotypic Evolution ◽  
Quantitative Studies ◽  
Thoracolumbar Region ◽  
Complex Adaptive ◽  
Dimensional Shape ◽  
A Chain ◽  
Low Dimensional ◽  
Adaptive Role ◽  
Shape Changes

AbstractOrganisms comprise multiple interacting parts, but few quantitative studies have analysed multi-element systems, limiting understanding of phenotypic evolution. We investigate how disparity of vertebral morphology varies along the axial column of mammalian carnivores — a chain of 27 subunits — and the extent to which morphological variation have been structured by evolutionary constraints and locomotory adaptation. We find that lumbars and posterior thoracics exhibit high individual disparity but low serial differentiation. They are pervasively recruited into locomotory functions and exhibit relaxed evolutionary constraint. More anterior vertebrae also show signals of locomotory adaptation, but nevertheless have low individual disparity and constrained patterns of evolution, characterised by low-dimensional shape changes. Our findings demonstrate the importance of the thoracolumbar region as an innovation enabling evolutionary versatility of mammalian locomotion. Moreover, they underscore the complexity of phenotypic macroevolution of multi-element systems and that the strength of ecomorphological signal does not have a predictable influence on macroevolutionary outcomes.

scholarly journals Industrial Robot Vision System

1983 ◽  
Vol 16 (20) ◽  
pp. 337-341
Author(s):  
V.M. Grishkin ◽  
F.M. Kulakov
Keyword(s):  
Vision System ◽  
Industrial Robot ◽  
Robot Vision

scholarly journals Principled approach to the selection of the embedding dimension of networks

2021 ◽  
Vol 12 (1) ◽  
Author(s):  
Weiwei Gu ◽  
Aditya Tandon ◽  
Yong-Yeol Ahn ◽  
Filippo Radicchi
Keyword(s):  
Real World ◽  
Structural Information ◽  
General Purpose ◽  
Embedding Dimension ◽  
Network Embedding ◽  
Machine Learning Technique ◽  
Learning Technique ◽  
Low Dimensional ◽  
Large Corpus ◽  
Selection Of

AbstractNetwork embedding is a general-purpose machine learning technique that encodes network structure in vector spaces with tunable dimension. Choosing an appropriate embedding dimension – small enough to be efficient and large enough to be effective – is challenging but necessary to generate embeddings applicable to a multitude of tasks. Existing strategies for the selection of the embedding dimension rely on performance maximization in downstream tasks. Here, we propose a principled method such that all structural information of a network is parsimoniously encoded. The method is validated on various embedding algorithms and a large corpus of real-world networks. The embedding dimension selected by our method in real-world networks suggest that efficient encoding in low-dimensional spaces is usually possible.

A Robot Vision System Based on Two-Dimensional Object-Oriented Models

1986 ◽  
Vol 16 (4) ◽  
pp. 582-589 ◽  
Author(s):  
Lorenz A. Schmitt ◽  
William A. Gruver ◽  
Assad Ansari
Keyword(s):  
Vision System ◽  
Robot Vision ◽  
Object Oriented ◽  
Two Dimensional ◽  
Dimensional Object

scholarly journals Nonlocal Estimation of Manifold Structure

2006 ◽  
Vol 18 (10) ◽  
pp. 2509-2528 ◽  
Author(s):  
Yoshua Bengio ◽  
Martin Monperrus ◽  
Hugo Larochelle
Keyword(s):  
Large Class ◽  
Manifold Learning ◽  
Learning Algorithms ◽  
Tangent Plane ◽  
Training Data ◽  
Kernel Learning ◽  
Manifold Structure ◽  
Prediction Function ◽  
Underlying Manifold ◽  
Shared Structure

We claim and present arguments to the effect that a large class of manifold learning algorithms that are essentially local and can be framed as kernel learning algorithms will suffer from the curse of dimensionality, at the dimension of the true underlying manifold. This observation invites an exploration of nonlocal manifold learning algorithms that attempt to discover shared structure in the tangent planes at different positions. A training criterion for such an algorithm is proposed, and experiments estimating a tangent plane prediction function are presented, showing its advantages with respect to local manifold learning algorithms: it is able to generalize very far from training data (on learning handwritten character image rotations), where local nonparametric methods fail.

scholarly journals Generalization-Based Acquisition of Training Data for Motor Primitive Learning by Neural Networks

2021 ◽  
Vol 11 (3) ◽  
pp. 1013
Author(s):  
Zvezdan Lončarević ◽  
Rok Pahič ◽  
Aleš Ude ◽  
Andrej Gams
Keyword(s):  
Neural Networks ◽  
Dimensionality Reduction ◽  
Gaussian Process Regression ◽  
Search Space ◽  
Robot Learning ◽  
Training Data ◽  
Practical Applications ◽  
Latent Space ◽  
Real Robot ◽  
Low Dimensional

Autonomous robot learning in unstructured environments often faces the problem that the dimensionality of the search space is too large for practical applications. Dimensionality reduction techniques have been developed to address this problem and describe motor skills in low-dimensional latent spaces. Most of these techniques require the availability of a sufficiently large database of example task executions to compute the latent space. However, the generation of many example task executions on a real robot is tedious, and prone to errors and equipment failures. The main result of this paper is a new approach for efficient database gathering by performing a small number of task executions with a real robot and applying statistical generalization, e.g., Gaussian process regression, to generate more data. We have shown in our experiments that the data generated this way can be used for dimensionality reduction with autoencoder neural networks. The resulting latent spaces can be exploited to implement robot learning more efficiently. The proposed approach has been evaluated on the problem of robotic throwing at a target. Simulation and real-world results with a humanoid robot TALOS are provided. They confirm the effectiveness of generalization-based database acquisition and the efficiency of learning in a low-dimensional latent space.

Novel Convolutional Restricted Boltzmann Machine manifold learning inspired dynamic user clustering hybrid precoding for millimeter-wave massive multiple-input multiple-output systems

2021 ◽  
Vol 17 (11) ◽  
pp. 155014772110553
Author(s):  
Xiaoping Zhou ◽  
Haichao Liu ◽  
Bin Wang ◽  
Qian Zhang ◽  
Yang Wang
Keyword(s):  
Millimeter Wave ◽  
Manifold Learning ◽  
Multiple Input Multiple Output ◽  
Restricted Boltzmann Machine ◽  
Boltzmann Machine ◽  
Hybrid Precoding ◽  
User Clustering ◽  
Multiple Input ◽  
Input Multiple Output ◽  
Low Dimensional

Millimeter-wave massive multiple-input multiple-output is a key technology in 5G communication system. In particular, the hybrid precoding method has the advantages of being power efficient and less expensive than the full-digital precoding method, so it has attracted more and more attention. The effectiveness of this method in simple systems has been well verified, but its performance is still unknown due to many problems in real communication such as interference from other users and base stations, and users are constantly on the move. In this article, we propose a dynamic user clustering hybrid precoding method in the high-dimensional millimeter-wave multiple-input multiple-output system, which uses low-dimensional manifolds to avoid complicated calculations when there are many antennas. We model each user set as a novel Convolutional Restricted Boltzmann Machine manifold, and the problem is transformed into cluster-oriented multi-manifold learning. The novel Convolutional Restricted Boltzmann Machine manifold learning seeks to learn embedded low-dimensional manifolds through manifold learning in the face of user mobility in clusters. Through proper user clustering, the hybrid precoding is investigated for the sum-rate maximization problem by manifold quasi-conjugate gradient methods. This algorithm avoids the traditional method of processing high-dimensional channel parameters, achieves a high signal-to-noise ratio, and reduces computational complexity. The simulation result table shows that this method can get almost the best summation rate and higher spectral efficiency compared with the traditional method.

Sign in / Sign up

Export Citation Format

Share Document