Combing rough set and RBF neural network for large-scale ship recognition in optical satellite images

Rapid identification of affected areas and volumes in a large-scale debris flow disaster is important for early-stage recovery and debris management planning. This study introduces a methodology for fusion analysis of optical satellite images and digital elevation model (DEM) for simplified quantification of volumes in a debris flow event. The LiDAR data, the pre- and post-event Sentinel-2 images and the pre-event DEM in Hiroshima, Japan affected by the debris flow disaster on July 2018 are analyzed in this study. Erosion depth by the debris flows is empirically modeled from the pre- and post-event LiDAR-derived DEMs. Erosion areas are detected from the change detection of the satellite images and the DEM-based debris flow propagation analysis by providing predefined sources. The volumes and their pattern are estimated from the detected erosion areas by multiplying the empirical erosion depth. The result of the volume estimations show good agreement with the LiDAR-derived volumes.

Download Full-text

Automatic Gully Detection: Neural Networks and Computer Vision

Remote Sensing ◽

10.3390/rs12111743 ◽

2020 ◽

Vol 12 (11) ◽

pp. 1743

Author(s):

Artur M. Gafurov ◽

Oleg P. Yermolayev

Keyword(s):

Neural Network ◽

Neural Networks ◽

Convolutional Neural Networks ◽

Large Scale ◽

Satellite Images ◽

Gully Erosion ◽

Training Data ◽

Russian Plain ◽

Data Set ◽

High Resolution Satellite Images

Transition from manual (visual) interpretation to fully automated gully detection is an important task for quantitative assessment of modern gully erosion, especially when it comes to large mapping areas. Existing approaches to semi-automated gully detection are based on either object-oriented selection based on multispectral images or gully selection based on a probabilistic model obtained using digital elevation models (DEMs). These approaches cannot be used for the assessment of gully erosion on the territory of the European part of Russia most affected by gully erosion due to the lack of national large-scale DEM and limited resolution of open source multispectral satellite images. An approach based on the use of convolutional neural networks for automated gully detection on the RGB-synthesis of ultra-high resolution satellite images publicly available for the test region of the east of the Russian Plain with intensive basin erosion has been proposed and developed. The Keras library and U-Net architecture of convolutional neural networks were used for training. Preliminary results of application of the trained gully erosion convolutional neural network (GECNN) allow asserting that the algorithm performs well in detecting active gullies, well differentiates gullies from other linear forms of slope erosion — rills and balkas, but so far has errors in detecting complex gully systems. Also, GECNN does not identify a gully in 10% of cases and in another 10% of cases it identifies not a gully. To solve these problems, it is necessary to additionally train the neural network on the enlarged training data set.

Download Full-text

A Rough-Fuzzy RBF Neural Network Based on PSO Algorithm

Advanced Materials Research ◽

10.4028/www.scientific.net/amr.710.617 ◽

2013 ◽

Vol 710 ◽

pp. 617-622

Author(s):

Jing Zhao

Keyword(s):

Neural Network ◽

Knowledge Acquisition ◽

Set Theory ◽

Rough Set ◽

Rough Set Theory ◽

Rbf Neural Network ◽

Pso Algorithm ◽

Training Sample ◽

Network Training ◽

Acquisition Method

A Rough-Fuzzy RBF Neural Network was raised based on PSO Algorithm. In this model,gives a knowledge acquisition method that based on rough set theory,the Rough-Fuzzy RBF neural network are constructed according to the results of the knowledge acquisition,the PSO are used to optimize the network parameters.This paper take number plate for example to conduct a simulation experiment.The results shows that the model can simplify the network training sample,optimize the network structure and enhance the systems study efficiency and the precision.

Download Full-text

Monitoring of the landslide area state on Bureya river in 2018-2019 according to radar and optical satellite images

Исследования Земли из космоса ◽

10.31857/s0205-96142019626-35 ◽

2019 ◽

pp. 26-35

Author(s):

V. G. Bondur ◽

L. N. Zakharova ◽

A. I. Zakharov

Keyword(s):

Optical Sensors ◽

Large Scale ◽

Satellite Images ◽

Satellite System ◽

Small Scale ◽

Landslide Area ◽

Interferometric Technique ◽

Optical Images ◽

Optical Satellite Images ◽

Synthetic Aperture Radars

The monitoring results of the current state of landslide area on the Bureya River in 20182019 are given using images from synthetic aperture radars and optical sensors of Sentinel multi-satellite system. Differential radar interferometry technique allowed to reveal the stability of the landslide surface in the first four months after the landslide and since the end of July 2019. Small-scale dynamics of the surface within the landslide circus was detected. It is shown that the interferometric technique is inapplicable for the observation of the large-scale modifications of the shoreline unlike the optical images where the effects of the collapse of the shoreline fragments and shoreline flooding were clearly observed compared also with radar amplitude images. The ongoing landslide activity within the landslide circus and the coastline collapse area was detected using satellite images. It requires the establishment of continuous monitoring of this and other dangerous landslide zones on Bureya River.

Download Full-text

Tree Crown Delineation Algorithm Based on a Convolutional Neural Network

Remote Sensing ◽

10.3390/rs12081288 ◽

2020 ◽

Vol 12 (8) ◽

pp. 1288 ◽

Cited By ~ 5

Author(s):

José R. G. Braga ◽

Vinícius Peripato ◽

Ricardo Dalagnol ◽

Matheus P. Ferreira ◽

Yuliya Tarabalka ◽

...

Keyword(s):

Neural Network ◽

High Resolution ◽

Convolutional Neural Network ◽

Tropical Forests ◽

Large Scale ◽

Satellite Images ◽

Tree Level ◽

Tree Crown ◽

Individual Tree ◽

High Resolution Satellite Images

Tropical forests concentrate the largest diversity of species on the planet and play a key role in maintaining environmental processes. Due to the importance of those forests, there is growing interest in mapping their components and getting information at an individual tree level to conduct reliable satellite-based forest inventory for biomass and species distribution qualification. Individual tree crown information could be manually gathered from high resolution satellite images; however, to achieve this task at large-scale, an algorithm to identify and delineate each tree crown individually, with high accuracy, is a prerequisite. In this study, we propose the application of a convolutional neural network—Mask R-CNN algorithm—to perform the tree crown detection and delineation. The algorithm uses very high-resolution satellite images from tropical forests. The results obtained are promising—the R e c a l l , P r e c i s i o n , and F 1 score values obtained were were 0.81 , 0.91 , and 0.86 , respectively. In the study site, the total of tree crowns delineated was 59,062 . These results suggest that this algorithm can be used to assist the planning and conduction of forest inventories. As the algorithm is based on a Deep Learning approach, it can be systematically trained and used for other regions.

Download Full-text

Software Design and Implementation of Large-Scale Intelligent Traffic Monitoring System

Applied Mechanics and Materials ◽

10.4028/www.scientific.net/amm.644-650.1351 ◽

2014 ◽

Vol 644-650 ◽

pp. 1351-1354

Author(s):

Jun Ye Wang

Keyword(s):

Neural Network ◽

Monitoring System ◽

Large Scale ◽

Rbf Neural Network ◽

Traffic Monitoring ◽

Monitoring Methods ◽

Monitoring Method ◽

Traffic State ◽

Network Algorithm ◽

Neural Network Algorithm

The design method of large-scale intelligent traffic monitoring system is studied. Traffic monitoring methods have become the core problem of intelligent transportation research field. To this end, this paper proposes an intelligent traffic monitoring method based on clustering RBF neural network algorithm. Fourier coefficient normalization method is used to extract the feature of traffic state, to be as the basis for intelligent traffic monitoring. Using clustering RBF neural network algorithm identify the traffic state effectively, thus to complete the state recognition of intelligent traffic monitoring. Experimental results show that the proposed algorithm performed in intelligent traffic monitoring, can greatly improve the accuracy of monitoring.

Download Full-text

Large-Scale Oil Palm Tree Detection from High-Resolution Satellite Images Using Two-Stage Convolutional Neural Networks

Remote Sensing ◽

10.3390/rs11010011 ◽

2018 ◽

Vol 11 (1) ◽

pp. 11 ◽

Cited By ~ 34

Author(s):

Weijia Li ◽

Runmin Dong ◽

Haohuan Fu ◽

and Le Yu

Keyword(s):

Neural Network ◽

High Resolution ◽

Oil Palm ◽

Large Scale ◽

Satellite Images ◽

Quantitative Detection ◽

Support Vector ◽

Palm Tree ◽

Two Stage ◽

High Resolution Satellite Images

Being an important economic crop that contributes 35% of the total consumption of vegetable oil, remote sensing-based quantitative detection of oil palm trees has long been a key research direction for both agriculture and environmental purposes. While existing methods already demonstrate satisfactory effectiveness for small regions, performing the detection for a large region with satisfactory accuracy is still challenging. In this study, we proposed a two-stage convolutional neural network (TS-CNN)-based oil palm detection method using high-resolution satellite images (i.e. Quickbird) in a large-scale study area of Malaysia. The TS-CNN consists of one CNN for land cover classification and one CNN for object classification. The two CNNs were trained and optimized independently based on 20,000 samples collected through human interpretation. For the large-scale oil palm detection for an area of 55 km2, we proposed an effective workflow that consists of an overlapping partitioning method for large-scale image division, a multi-scale sliding window method for oil palm coordinate prediction, and a minimum distance filter method for post-processing. Our proposed approach achieves a much higher average F1-score of 94.99% in our study area compared with existing oil palm detection methods (87.95%, 81.80%, 80.61%, and 78.35% for single-stage CNN, Support Vector Machine (SVM), Random Forest (RF), and Artificial Neural Network (ANN), respectively), and much fewer confusions with other vegetation and buildings in the whole image detection results.

Download Full-text

Research of Torque Control in Large-Scale Wind Turbine

Advanced Materials Research ◽

10.4028/www.scientific.net/amr.383-390.3479 ◽

2011 ◽

Vol 383-390 ◽

pp. 3479-3485

Author(s):

Wei Li ◽

Jian Xu

Keyword(s):

Neural Network ◽

Wind Turbine ◽

Large Scale ◽

Rbf Neural Network ◽

Dynamic Performance ◽

Good Control ◽

State Equation ◽

Torque Control ◽

Scale Variable ◽

Adaptive Ability

PID torque damper controller was designed and PID parameters were set with RBF neural network for the torque control of large-scale variable speed pitch regulated (VSPR) wind turbine. The system state equation can be extracted by the process of modal linearization using Bladed software, then PID controller was designed, parameters optimized and verification of design test with the control system of 3MW wind turbine was taken finally. The simulation result shows that the damper controller designed reduces driving chain vibration obviously, the adaptive ability and dynamic performance of system is improved with the use of RBF neural network which makes the system with good control quality.

Download Full-text