scholarly journals Automated Method of Road Extraction from Aerial Images Using a Deep Convolutional Neural Network

2019 ◽  
Vol 9 (22) ◽  
pp. 4825 ◽  
Author(s):  
Tamara Alshaikhli ◽  
Wen Liu ◽  
Yoshihisa Maruyama
Keyword(s):  
Traffic Management ◽  
City Planning ◽  
Road Networks ◽  
Good Alternative ◽  
Aerial Images ◽  
Training Dataset ◽  
Automated Method ◽  
Learning Techniques ◽  
Manual Methods ◽  
Road Segmentation

Updating road networks using remote sensing imagery is among the most important topics in city planning, traffic management and disaster management. As a good alternative to manual methods, which are considered to be expensive and time consuming, deep learning techniques provide great improvements in these regards. One of these techniques is the use of deep convolution neural networks (DCNNs). This study presents a road segmentation model consisting of a skip connection of U-net and residual blocks (ResBlocks) in the encoding part and convolution layers (Conv. layer) in the decoding part. Although the model uses fewer residual blocks in the encoding part and fewer convolution layers in the decoding part, it produces better image predictions in comparison with other state-of-the-art models. This model automatically and efficiently extracts road networks from high-resolution aerial imagery in an unexpansive manner using a small training dataset.

scholarly journals Orchard Mapping with Deep Learning Semantic Segmentation

Sensors ◽  
2021 ◽  
Vol 21 (11) ◽  
pp. 3813
Author(s):  
Athanasios Anagnostis ◽  
Aristotelis C. Tagarakis ◽  
Dimitrios Kateris ◽  
Vasileios Moysiadis ◽  
Claus Grøn Sørensen ◽  
...  
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Semantic Segmentation ◽  
Automated Detection ◽  
Aerial Images ◽  
Training Dataset ◽  
Field Boundary ◽  
Different Seasons ◽  
Detection And Localization ◽  
Different Levels

This study aimed to propose an approach for orchard trees segmentation using aerial images based on a deep learning convolutional neural network variant, namely the U-net network. The purpose was the automated detection and localization of the canopy of orchard trees under various conditions (i.e., different seasons, different tree ages, different levels of weed coverage). The implemented dataset was composed of images from three different walnut orchards. The achieved variability of the dataset resulted in obtaining images that fell under seven different use cases. The best-trained model achieved 91%, 90%, and 87% accuracy for training, validation, and testing, respectively. The trained model was also tested on never-before-seen orthomosaic images or orchards based on two methods (oversampling and undersampling) in order to tackle issues with out-of-the-field boundary transparent pixels from the image. Even though the training dataset did not contain orthomosaic images, it achieved performance levels that reached up to 99%, demonstrating the robustness of the proposed approach.

scholarly journals EXPLORING ALS AND DIM DATA FOR SEMANTIC SEGMENTATION USING CNNS

2018 ◽  
Vol XLII-1 ◽  
pp. 347-354 ◽  
Author(s):  
F. Politz ◽  
M. Sester
Keyword(s):  
Point Cloud ◽  
Laser Scanning ◽  
Semantic Segmentation ◽  
Point Clouds ◽  
Good Alternative ◽  
Aerial Images ◽  
Learning Approaches ◽  
Advantages And Disadvantages ◽  
Sensing Applications ◽  
High Level

<p><strong>Abstract.</strong> Over the past years, the algorithms for dense image matching (DIM) to obtain point clouds from aerial images improved significantly. Consequently, DIM point clouds are now a good alternative to the established Airborne Laser Scanning (ALS) point clouds for remote sensing applications. In order to derive high-level applications such as digital terrain models or city models, each point within a point cloud must be assigned a class label. Usually, ALS and DIM are labelled with different classifiers due to their varying characteristics. In this work, we explore both point cloud types in a fully convolutional encoder-decoder network, which learns to classify ALS as well as DIM point clouds. As input, we project the point clouds onto a 2D image raster plane and calculate the minimal, average and maximal height values for each raster cell. The network then differentiates between the classes ground, non-ground, building and no data. We test our network in six training setups using only one point cloud type, both point clouds as well as several transfer-learning approaches. We quantitatively and qualitatively compare all results and discuss the advantages and disadvantages of all setups. The best network achieves an overall accuracy of 96<span class="thinspace"></span>% in an ALS and 83<span class="thinspace"></span>% in a DIM test set.</p>

scholarly journals Intelligent Neural Network Schemes for Multi-Class Classification

2019 ◽  
Vol 9 (19) ◽  
pp. 4036 ◽  
Author(s):  
You ◽  
Wu ◽  
Lee ◽  
Liu
Keyword(s):  
Neural Network ◽  
Clustering Algorithm ◽  
Classification Problem ◽  
Machine Learning Techniques ◽  
Training Dataset ◽  
Reduction Techniques ◽  
Learning Techniques ◽  
Benchmark Datasets ◽  
Dimensionality Reduction Techniques ◽  
Multi Class Classification

Multi-class classification is a very important technique in engineering applications, e.g., mechanical systems, mechanics and design innovations, applied materials in nanotechnologies, etc. A large amount of research is done for single-label classification where objects are associated with a single category. However, in many application domains, an object can belong to two or more categories, and multi-label classification is needed. Traditionally, statistical methods were used; recently, machine learning techniques, in particular neural networks, have been proposed to solve the multi-class classification problem. In this paper, we develop radial basis function (RBF)-based neural network schemes for single-label and multi-label classification, respectively. The number of hidden nodes and the parameters involved with the basis functions are determined automatically by applying an iterative self-constructing clustering algorithm to the given training dataset, and biases and weights are derived optimally by least squares. Dimensionality reduction techniques are adopted and integrated to help reduce the overfitting problem associated with the RBF networks. Experimental results from benchmark datasets are presented to show the effectiveness of the proposed schemes.

Semisupervised sentiment analysis method for online text reviews

2020 ◽  
pp. 016555152091003
Author(s):  
Gyeong Taek Lee ◽  
Chang Ouk Kim ◽  
Min Song
Keyword(s):  
Unsupervised Learning ◽  
Sentiment Analysis ◽  
Supervised Learning ◽  
Model Space ◽  
Training Dataset ◽  
Learning Approach ◽  
Learning Models ◽  
Text Data ◽  
Learning Techniques ◽  
Sentiment Dictionary

Sentiment analysis plays an important role in understanding individual opinions expressed in websites such as social media and product review sites. The common approaches to sentiment analysis use the sentiments carried by words that express opinions and are based on either supervised or unsupervised learning techniques. The unsupervised learning approach builds a word-sentiment dictionary, but it requires lengthy time periods and high costs to build a reliable dictionary. The supervised learning approach uses machine learning models to learn the sentiment scores of words; however, training a classifier model requires large amounts of labelled text data to achieve a good performance. In this article, we propose a semisupervised approach that performs well despite having only small amounts of labelled data available for training. The proposed method builds a base sentiment dictionary from a small training dataset using a lasso-based ensemble model with minimal human effort. The scores of words not in the training dataset are estimated using an adaptive instance-based learning model. In a pretrained word2vec model space, the sentiment values of the words in the dictionary are propagated to the words that did not exist in the training dataset. Through two experiments, we demonstrate that the performance of the proposed method is comparable to that of supervised learning models trained on large datasets.

scholarly journals Traffic management system for smart road networks reserved for self-driving cars

2020 ◽  
Vol 14 (9) ◽  
pp. 1013-1024
Author(s):  
Angela Di Febbraro ◽  
Federico Gallo ◽  
Davide Giglio ◽  
Nicola Sacco
Keyword(s):  
Traffic Management ◽  
Management System ◽  
Road Networks ◽  
Traffic Management System ◽  
Self Driving Cars

scholarly journals Progressive Full Data Convolutional Neural Networks for Line Extraction from Anime-Style Illustrations

2019 ◽  
Vol 10 (1) ◽  
pp. 41
Author(s):  
Yuchen Xin ◽  
Hon-Cheng Wong ◽  
Sio-Long Lo ◽  
Junliang Li
Keyword(s):  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Training Dataset ◽  
Full Data ◽  
Line Drawings ◽  
Line Extraction ◽  
Learning Techniques ◽  
Target Extraction ◽  
The Common ◽  
Output Quantity

Anime-style comics are popular world-wide and an important industry in Asia. However, the output quantity and quality control of art workers have become the biggest obstacle to industrialization, and it is time consuming to produce new manga without the help of an intelligence assisted tool. As deep learning techniques have achieved great successes in different areas, it is worth exploring them to develop algorithms and systems for computational manga. Extracting line drawings from finished illustrations is one of the main tasks in drawing a manuscript and also a crucial task in the common painting process. However, traditional filters such as Sobel, Laplace, and Canny cannot output good results and require manual adjustments of the parameters. In order to address these problems, in this paper, we propose progressive full data convolutional neural networks for extracting lines from anime-style illustrations. Experimental results show that our progressive full data convolutional neural networks not only can learn as much as processing methods for the detailed regions, but also can accomplish the target extraction work with only a small training dataset.

scholarly journals Machine Learning Generalisation across Different 3D Architectural Heritage

2020 ◽  
Vol 9 (6) ◽  
pp. 379 ◽  
Author(s):  
Eleonora Grilli ◽  
Fabio Remondino
Keyword(s):  
Machine Learning ◽  
Point Cloud ◽  
Machine Learning Techniques ◽  
Training Dataset ◽  
High Complexity ◽  
Architectural Heritage ◽  
Learning Techniques ◽  
Machine Learning Model ◽  
Point Cloud Classification

The use of machine learning techniques for point cloud classification has been investigated extensively in the last decade in the geospatial community, while in the cultural heritage field it has only recently started to be explored. The high complexity and heterogeneity of 3D heritage data, the diversity of the possible scenarios, and the different classification purposes that each case study might present, makes it difficult to realise a large training dataset for learning purposes. An important practical issue that has not been explored yet, is the application of a single machine learning model across large and different architectural datasets. This paper tackles this issue presenting a methodology able to successfully generalise to unseen scenarios a random forest model trained on a specific dataset. This is achieved looking for the best features suitable to identify the classes of interest (e.g., wall, windows, roof and columns).

scholarly journals Automated Method for Delineating Harvested Stands Based on Harvester Location Data

2020 ◽  
Vol 12 (17) ◽  
pp. 2754
Author(s):  
Timo Melkas ◽  
Kirsi Riekki ◽  
Juha-Antti Sorsa
Keyword(s):  
Forest Inventory ◽  
Large Scale ◽  
Field Measurements ◽  
Detailed Comparison ◽  
Satellite System ◽  
Comparison Method ◽  
Aerial Images ◽  
Location Data ◽  
Automated Method ◽  
Good Stand

The data produced by cut-to-length harvesters provide new large-scale data source for event-based update of national forest stand inventory by Finnish Forest Centre. This study aimed to automate geoprocessing, which generates delineations of operated areas from harvester location data. Automated algorithms were developed and tested with a dataset of 455 harvested objects, recorded during harvestings. In automated stand delineation, the location points are clustered, the stand points are identified and external strip roads are separated. Then, stand polygons are produced. To validate the results, automatic delineations were compared to 57 observed delineations from field measurements and aerial images. A detailed comparison method was developed to study the correspondence. Stand polygonization parameter was adjusted and areal correspondence with 1% error on average was obtained for stands over 0.75 ha. Good stand shape agreement was observed. Overall, the automated method worked well, and the operative stand delineations were found suitable for updating the forest inventory data. To modify the operative stands towards forest inventory stands, a balancing algorithm is introduced to create a solid, unique stand boundary between overlapping stands. This algorithm is beneficial for upkeep of stand networks. In addition, the Global Navigation Satellite System (GNSS) accuracy of the harvesters was examined and estimated numerically.

Sign in / Sign up

Export Citation Format

Share Document