scholarly journals Vision-Based Indoor Scene Recognition from Time-Series Aerial Images Obtained Using a MAV Mounted Monocular Camera

Drones ◽  
2019 ◽  
Vol 3 (1) ◽  
pp. 22 ◽  
Author(s):  
Hirokazu Madokoro ◽  
Kazuhito Sato ◽  
Nobuhiro Shimoi
Keyword(s):  
Time Series ◽  
Dimensional Space ◽  
Distance Matrix ◽  
Image Features ◽  
Scene Recognition ◽  
Aerial Images ◽  
Self Organizing Maps ◽  
Visual Words ◽  
Indoor Scene ◽  
Flight Route

This paper presents a vision-based indoor scene recognition method from aerial time-series images obtained using a micro air vehicle (MAV). The proposed method comprises two procedures: a codebook feature description procedure, and a recognition procedure using category maps. For the former procedure, codebooks are created automatically as visual words using self-organizing maps (SOMs) after extracting part-based local features using a part-based descriptor from time-series scene images. For the latter procedure, category maps are created using counter propagation networks (CPNs) with the extraction of category boundaries using a unified distance matrix (U-Matrix). Using category maps, topologies of image features are mapped into a low-dimensional space based on competitive and neighborhood learning. We obtained aerial time-series image datasets of five sets for two flight routes: a round flight route and a zigzag flight route. The experimentally obtained results with leave-one-out cross-validation (LOOCV) revealed respective mean recognition accuracies for the round flight datasets (RFDs) and zigzag flight datasets (ZFDs) of 71.7% and 65.5% for 10 zones. The category maps addressed the complexity of scenes because of segmented categories. Although extraction results of category boundaries using U-Matrix were partially discontinuous, we obtained comprehensive category boundaries that segment scenes into several categories.

scholarly journals Identifying Spatiotemporal Patterns in Land Use and Cover Samples from Satellite Image Time Series

2021 ◽  
Vol 13 (5) ◽  
pp. 974
Author(s):  
Lorena Alves Santos ◽  
Karine Ferreira ◽  
Michelle Picoli ◽  
Gilberto Camara ◽  
Raul Zurita-Milla ◽  
...  
Keyword(s):  
Machine Learning ◽  
Land Use ◽  
Time Series ◽  
Satellite Image ◽  
Spatiotemporal Patterns ◽  
Supervised Machine Learning ◽  
Learning Methods ◽  
Self Organizing Maps ◽  
Machine Learning Methods ◽  
Land Use And Cover

The use of satellite image time series analysis and machine learning methods brings new opportunities and challenges for land use and cover changes (LUCC) mapping over large areas. One of these challenges is the need for samples that properly represent the high variability of land used and cover classes over large areas to train supervised machine learning methods and to produce accurate LUCC maps. This paper addresses this challenge and presents a method to identify spatiotemporal patterns in land use and cover samples to infer subclasses through the phenological and spectral information provided by satellite image time series. The proposed method uses self-organizing maps (SOMs) to reduce the data dimensionality creating primary clusters. From these primary clusters, it uses hierarchical clustering to create subclusters that recognize intra-class variability intrinsic to different regions and periods, mainly in large areas and multiple years. To show how the method works, we use MODIS image time series associated to samples of cropland and pasture classes over the Cerrado biome in Brazil. The results prove that the proposed method is suitable for identifying spatiotemporal patterns in land use and cover samples that can be used to infer subclasses, mainly for crop-types.

scholarly journals Spatial and Temporal Spread of the COVID-19 Pandemic Using Self Organizing Neural Networks and a Fuzzy Fractal Approach

2021 ◽  
Vol 13 (15) ◽  
pp. 8295
Author(s):  
Patricia Melin ◽  
Oscar Castillo
Keyword(s):  
Neural Networks ◽  
Time Series ◽  
Temporal Trends ◽  
Main Idea ◽  
Temporal Analysis ◽  
Virus Propagation ◽  
Self Organizing Maps ◽  
Fractal Approach ◽  
The Times ◽  
Self Organizing

In this article, the evolution in both space and time of the COVID-19 pandemic is studied by utilizing a neural network with a self-organizing nature for the spatial analysis of data, and a fuzzy fractal method for capturing the temporal trends of the time series of the countries considered in this study. Self-organizing neural networks possess the capability to cluster countries in the space domain based on their similar characteristics, with respect to their COVID-19 cases. This form enables the finding of countries that have a similar behavior, and thus can benefit from utilizing the same methods in fighting the virus propagation. In order to validate the approach, publicly available datasets of COVID-19 cases worldwide have been used. In addition, a fuzzy fractal approach is utilized for the temporal analysis of the time series of the countries considered in this study. Then, a hybrid combination, using fuzzy rules, of both the self-organizing maps and the fuzzy fractal approach is proposed for efficient coronavirus disease 2019 (COVID-19) forecasting of the countries. Relevant conclusions have emerged from this study that may be of great help in putting forward the best possible strategies in fighting the virus pandemic. Many of the existing works concerned with COVID-19 look at the problem mostly from a temporal viewpoint, which is of course relevant, but we strongly believe that the combination of both aspects of the problem is relevant for improving the forecasting ability. The main idea of this article is combining neural networks with a self-organizing nature for clustering countries with a high similarity and the fuzzy fractal approach for being able to forecast the times series. Simulation results of COVID-19 data from countries around the world show the ability of the proposed approach to first spatially cluster the countries and then to accurately predict in time the COVID-19 data for different countries with a fuzzy fractal approach.

Object Classification of Aerial Images With Bag-of-Visual Words

2010 ◽  
Vol 7 (2) ◽  
pp. 366-370 ◽  
Author(s):  
Sheng Xu ◽  
Tao Fang ◽  
Deren Li ◽  
Shiwei Wang
Keyword(s):  
Object Classification ◽  
Aerial Images ◽  
Bag Of Visual Words ◽  
Visual Words

A New Method for Emulating Self-Organizing Maps for Visualization of Datasets

2018 ◽  
Vol 17 (03) ◽  
pp. 1850014 ◽  
Author(s):  
Macario O. Cordel ◽  
Arnulfo P. Azcarraga
Keyword(s):  
Disaster Response ◽  
Dimensional Space ◽  
Main Idea ◽  
Cost Effective ◽  
Fine Tuning ◽  
Visualization Tool ◽  
Self Organizing Map ◽  
Text Complexity ◽  
Self Organizing Maps ◽  
Self Organizing

Several time-critical problems relying on large amount of data, e.g., business trends, disaster response and disease outbreak, require cost-effective, timely and accurate data summary and visualization, in order to come up with an efficient and effective decision. Self-organizing map (SOM) is a very effective data clustering and visualization tool as it provides intuitive display of data in lower-dimensional space. However, with [Formula: see text] complexity, SOM becomes inappropriate for large datasets. In this paper, we propose a force-directed visualization method that emulates SOMs capability to display the data clusters with [Formula: see text] complexity. The main idea is to perform a force-directed fine-tuning of the 2D representation of data. To demonstrate the efficiency and the vast potential of the proposed method as a fast visualization tool, the methodology is used to do a 2D-projection of the MNIST handwritten digits dataset.

scholarly journals Season- and Trend-aware Symbolic Approximation for Accurate and Efficient Time Series Matching

2021 ◽  
Author(s):  
Lars Kegel ◽  
Claudio Hartmann ◽  
Maik Thiele ◽  
Wolfgang Lehner
Keyword(s):  
Time Series ◽  
State Of The Art ◽  
Dimensional Space ◽  
Symbolic Aggregate Approximation ◽  
Current State ◽  
Optimal Representation ◽  
Symbolic Approximation ◽  
Low Dimensional ◽  
Deterministic Behavior ◽  
Support Time

AbstractProcessing and analyzing time series datasets have become a central issue in many domains requiring data management systems to support time series as a native data type. A core access primitive of time series is matching, which requires efficient algorithms on-top of appropriate representations like the symbolic aggregate approximation (SAX) representing the current state of the art. This technique reduces a time series to a low-dimensional space by segmenting it and discretizing each segment into a small symbolic alphabet. Unfortunately, SAX ignores the deterministic behavior of time series such as cyclical repeating patterns or a trend component affecting all segments, which may lead to a sub-optimal representation accuracy. We therefore introduce a novel season- and a trend-aware symbolic approximation and demonstrate an improved representation accuracy without increasing the memory footprint. Most importantly, our techniques also enable a more efficient time series matching by providing a match up to three orders of magnitude faster than SAX.

scholarly journals Longest time series of glacier mass changes in the Himalaya based on stereo imagery

2010 ◽  
Vol 4 (4) ◽  
pp. 2593-2613 ◽  
Author(s):  
T. Bolch ◽  
T. Pieczonka ◽  
D. I. Benn
Keyword(s):  
Time Series ◽  
Mass Loss ◽  
Mass Balance ◽  
Aerial Images ◽  
Glacier Mass Balance ◽  
Glacier Changes ◽  
Debris Cover ◽  
Stereo Imagery ◽  
Glacier Velocity ◽  
The Himalaya

Abstract. Mass loss of Himalayan glaciers has wide-ranging consequences such as declining water resources, sea level rise and an increasing risk of glacial lake outburst floods (GLOFs). The assessment of the regional and global impact of glacier changes in the Himalaya is, however, hampered by a lack of mass balance data for most of the range. Multi-temporal digital terrain models (DTMs) allow glacier mass balance to be calculated since the availability of stereo imagery. Here we present the longest time series of mass changes in the Himalaya and show the high value of early stereo spy imagery such as Corona (years 1962 and 1970) aerial images and recent high resolution satellite data (Cartosat-1) to calculate a time series of glacier changes south of Mt. Everest, Nepal. We reveal that the glaciers are significantly losing mass with an increasing rate since at least ~1970, despite thick debris cover. The specific mass loss is 0.32 ± 0.08 m w.e. a−1, however, not higher than the global average. The spatial patterns of surface lowering can be explained by variations in debris-cover thickness, glacier velocity, and ice melt due to exposed ice cliffs and ponds.

scholarly journals Hebbian Learning of Recurrent Connections: A Geometrical Perspective

2012 ◽  
Vol 24 (9) ◽  
pp. 2346-2383 ◽  
Author(s):  
Mathieu N. Galtier ◽  
Olivier D. Faugeras ◽  
Paul C. Bressloff
Keyword(s):  
Hebbian Learning ◽  
Dimensional Space ◽  
Equilibrium Points ◽  
Ocular Dominance ◽  
Distance Matrix ◽  
Hopfield Network ◽  
Connectivity Matrix ◽  
Euclidean Distance Matrix ◽  
Fast Analysis ◽  
Recurrent Connections

We show how a Hopfield network with modifiable recurrent connections undergoing slow Hebbian learning can extract the underlying geometry of an input space. First, we use a slow and fast analysis to derive an averaged system whose dynamics derives from an energy function and therefore always converges to equilibrium points. The equilibria reflect the correlation structure of the inputs, a global object extracted through local recurrent interactions only. Second, we use numerical methods to illustrate how learning extracts the hidden geometrical structure of the inputs. Indeed, multidimensional scaling methods make it possible to project the final connectivity matrix onto a Euclidean distance matrix in a high-dimensional space, with the neurons labeled by spatial position within this space. The resulting network structure turns out to be roughly convolutional. The residual of the projection defines the nonconvolutional part of the connectivity, which is minimized in the process. Finally, we show how restricting the dimension of the space where the neurons live gives rise to patterns similar to cortical maps. We motivate this using an energy efficiency argument based on wire length minimization. Finally, we show how this approach leads to the emergence of ocular dominance or orientation columns in primary visual cortex via the self-organization of recurrent rather than feedforward connections. In addition, we establish that the nonconvolutional (or long-range) connectivity is patchy and is co-aligned in the case of orientation learning.

Sign in / Sign up

Export Citation Format

Share Document