scholarly journals INVESTIGATIONS ON FEATURE SIMILARITY AND THE IMPACT OF TRAINING DATA FOR LAND COVER CLASSIFICATION

2021 ◽  
Vol V-3-2021 ◽  
pp. 181-189
Author(s):  
M. Voelsen ◽  
D. Lobo Torres ◽  
R. Q. Feitosa ◽  
F. Rottensteiner ◽  
C. Heipke
Keyword(s):  
Land Cover ◽  
Feature Space ◽  
Land Cover Classification ◽  
Classification Performance ◽  
Training Data ◽  
Label Noise ◽  
Feature Vectors ◽  
Real World Datasets ◽  
Imbalanced Class Distribution ◽  
The Impact

Abstract. Fully convolutional neural networks (FCN) are successfully used for pixel-wise land cover classification - the task of identifying the physical material of the Earth’s surface for every pixel in an image. The acquisition of large training datasets is challenging, especially in remote sensing, but necessary for a FCN to perform well. One way to circumvent manual labelling is the usage of existing databases, which usually contain a certain amount of label noise when combined with another data source. As a first part of this work, we investigate the impact of training data on a FCN. We experiment with different amounts of training data, varying w.r.t. the covered area, the available acquisition dates and the amount of label noise. We conclude that the more data is used for training, the better is the generalization performance of the model, and the FCN is able to mitigate the effect of label noise to a high degree. Another challenge is the imbalanced class distribution in most real-world datasets, which can cause the classifier to focus on the majority classes, leading to poor classification performance for minority classes. To tackle this problem, in this paper, we use the cosine similarity loss to force feature vectors of the same class to be close to each other in feature space. Our experiments show that the cosine loss helps to obtain more similar feature vectors, but the similarity of the cluster centers also increases.

scholarly journals CHARACTERISTICS OF THE DEGREE OF GRADE IN GRADE-ADDED ROUGH SET FOR LAND COVER CLASSIFICATION

2019 ◽  
Vol XLII-3/W7 ◽  
pp. 19-24
Author(s):  
Y. Ishii ◽  
K. Iwao ◽  
T. Kinoshita
Keyword(s):  
Land Cover ◽  
Rough Set ◽  
Classification Scheme ◽  
Feature Space ◽  
Land Cover Classification ◽  
Training Data ◽  
Aerial Images ◽  
Boundary Line ◽  
Membership Degree ◽  
By Products

<p><strong>Abstract.</strong> This paper aims to clarify the meaning of the membership which is produced as by-products of land cover classification by Grade-added rough set (GRS). A new land cover classification method by using GRS was developed. The classification scheme of GRS which calculates membership (degree of grade) for each class is similar to those of MLC and SVM. But there are two things that are not clear. One is a meaning of the membership of GRS and the other is a reason why the larger membership in GRS employed works well. In this study, aerial images were used to visualize the relation of membership between GRS and existing classifiers, MLC and SVM. Furthermore, a model experiment in two-dimensional feature space was conducted. From these experiments, it was found that the meaning of degree of grade is a distance from a nearest training data of other class. That is, the meaning of membership of GRS is similar to that of SVM, because SVM also calculates a distance from boundary line which is determined by support vectors, while the meaning of membership of MLC is a distance from a centroid of own class. Also it was found that what the distance from the closest other class is given as the degree of grade implies that the higher the grade, the higher the certainty. In this research we could clarify some of the features of land cover classification using GRS.</p>

scholarly journals INVESTIGATIONS ON SKIP-CONNECTIONS WITH AN ADDITIONAL COSINE SIMILARITY LOSS FOR LAND COVER CLASSIFICATION

2020 ◽  
Vol V-3-2020 ◽  
pp. 339-346
Author(s):  
C. Yang ◽  
F. Rottensteiner ◽  
C. Heipke
Keyword(s):  
Land Cover ◽  
Spatial Resolution ◽  
Feature Space ◽  
Land Cover Classification ◽  
Classification Performance ◽  
Cosine Similarity ◽  
Aerial Images ◽  
Layer By Layer ◽  
Feature Maps ◽  
Standard Task

Abstract. Pixel-based land cover classification of aerial images is a standard task in remote sensing, whose goal is to identify the physical material of the earth’s surface. Recently, most of the well-performing methods rely on encoder-decoder structure based convolutional neural networks (CNN). In the encoder part, many successive convolution and pooling operations are applied to obtain features at a lower spatial resolution, and in the decoder part these features are up-sampled gradually and layer by layer, in order to make predictions in the original spatial resolution. However, the loss of spatial resolution caused by pooling affects the final classification performance negatively, which is compensated by skip-connections between corresponding features in the encoder and the decoder. The most popular ways to combine features are element-wise addition of feature maps and 1x1 convolution. In this work, we investigate skip-connections. We argue that not every skip-connections are equally important. Therefore, we conducted experiments designed to find out which skip-connections are important. Moreover, we propose a new cosine similarity loss function to utilize the relationship of the features of the pixels belonging to the same category inside one mini-batch, i.e. these features should be close in feature space. Our experiments show that the new cosine similarity loss does help the classification. We evaluated our methods using the Vaihingen and Potsdam dataset of the ISPRS 2D semantic labelling challenge and achieved an overall accuracy of 91.1% for both test sites.

scholarly journals The Performance of Post-Fall Detection Using the Cross-Dataset: Feature Vectors, Classifiers and Processing Conditions

Sensors ◽  
2021 ◽  
Vol 21 (14) ◽  
pp. 4638
Author(s):  
Bummo Koo ◽  
Jongman Kim ◽  
Yejin Nam ◽  
Youngho Kim
Keyword(s):  
Time Series ◽  
Fall Detection ◽  
Discrete Data ◽  
Classification Performance ◽  
Training Data ◽  
Processing Conditions ◽  
Feature Vectors ◽  
External Data ◽  
Public Dataset ◽  
The Cross

In this study, algorithms to detect post-falls were evaluated using the cross-dataset according to feature vectors (time-series and discrete data), classifiers (ANN and SVM), and four different processing conditions (normalization, equalization, increase in the number of training data, and additional training with external data). Three-axis acceleration and angular velocity data were obtained from 30 healthy male subjects by attaching an IMU to the middle of the left and right anterior superior iliac spines (ASIS). Internal and external tests were performed using our lab dataset and SisFall public dataset, respectively. The results showed that ANN and SVM were suitable for the time-series and discrete data, respectively. The classification performance generally decreased, and thus, specific feature vectors from the raw data were necessary when untrained motions were tested using a public dataset. Normalization made SVM and ANN more and less effective, respectively. Equalization increased the sensitivity, even though it did not improve the overall performance. The increase in the number of training data also improved the classification performance. Machine learning was vulnerable to untrained motions, and data of various movements were needed for the training.

scholarly journals IMPLEMENTATION OF THE MARKOV RANDOM FIELD FOR URBAN LAND COVER CLASSIFICATION OF UAV VHIR DATA

2016 ◽  
Vol 3 (2) ◽  
pp. 127
Author(s):  
Jati Pratomo ◽  
Triyoga Widiastomo
Keyword(s):  
Land Cover ◽  
Random Field ◽  
Markov Random Field ◽  
Optimal Parameter ◽  
Land Cover Classification ◽  
Urban Land ◽  
Urban Land Cover ◽  
Markov Random ◽  
Atmospheric Variations ◽  
The Impact

The usage of Unmanned Aerial Vehicle (UAV) has grown rapidly in various fields, such as urban planning, search and rescue, and surveillance. Capturing images from UAV has many advantages compared with satellite imagery. For instance, higher spatial resolution and less impact from atmospheric variations can be obtained. However, there are difficulties in classifying urban features, due to the complexity of the urban land covers. The usage of Maximum Likelihood Classification (MLC) has limitations since it is based on the assumption of the normal distribution of pixel values, where, in fact, urban features are not normally distributed. There are advantages in using the Markov Random Field (MRF) for urban land cover classification as it assumes that neighboring pixels have a higher probability to be classified in the same class rather than a different class. This research aimed to determine the impact of the smoothness (λ) and the updating temperature (Tupd) on the accuracy result (κ) in MRF. We used a UAV VHIR sized 587 square meters, with six-centimetre resolution, taken in Bogor Regency, Indonesia. The result showed that the kappa value (κ) increases proportionally with the smoothness (λ) until it reaches the maximum (κ), then the value drops. The usage of higher (Tupd) has resulted in better (κ) although it also led to a higher Standard Deviations (SD). Using the most optimal parameter, MRF resulted in slightly higher (κ) compared with MLC.

scholarly journals ASSESSING LIDAR TRAINING DATA QUANTITIES FOR CLASSIFICATION MODELS

2021 ◽  
Vol XLVI-4/W4-2021 ◽  
pp. 101-106
Author(s):  
O. Majgaonkar ◽  
K. Panchal ◽  
D. Laefer ◽  
M. Stanley ◽  
Y. Zaki
Keyword(s):  
Point Cloud ◽  
Classification Performance ◽  
Training Data ◽  
Lidar Data ◽  
Data Sets ◽  
Classification Models ◽  
Fundamental Properties ◽  
Point Cloud Classification ◽  
The Impact ◽  
Insight Into

Abstract. Classifying objects within aerial Light Detection and Ranging (LiDAR) data is an essential task to which machine learning (ML) is applied increasingly. ML has been shown to be more effective on LiDAR than imagery for classification, but most efforts have focused on imagery because of the challenges presented by LiDAR data. LiDAR datasets are of higher dimensionality, discontinuous, heterogenous, spatially incomplete, and often scarce. As such, there has been little examination into the fundamental properties of the training data required for acceptable performance of classification models tailored for LiDAR data. The quantity of training data is one such crucial property, because training on different sizes of data provides insight into a model’s performance with differing data sets. This paper assesses the impact of training data size on the accuracy of PointNet, a widely used ML approach for point cloud classification. Subsets of ModelNet ranging from 40 to 9,843 objects were validated on a test set of 400 objects. Accuracy improved logarithmically; decelerating from 45 objects onwards, it slowed significantly at a training size of 2,000 objects, corresponding to 20,000,000 points. This work contributes to the theoretical foundation for development of LiDAR-focused models by establishing a learning curve, suggesting the minimum quantity of manually labelled data necessary for satisfactory classification performance and providing a path for further analysis of the effects of modifying training data characteristics.

scholarly journals Land Cover Classification from fused DSM and UAV Images Using Convolutional Neural Networks

2019 ◽  
Vol 11 (12) ◽  
pp. 1461 ◽  
Author(s):  
Husam A. H. Al-Najjar ◽  
Bahareh Kalantar ◽  
Biswajeet Pradhan ◽  
Vahideh Saeidi ◽  
Alfian Abdul Halin ◽  
...  
Keyword(s):  
Neural Networks ◽  
Land Cover ◽  
Convolutional Neural Networks ◽  
Land Cover Classification ◽  
Training Data ◽  
Surface Model ◽  
Kappa Index ◽  
Diverse Range ◽  
Average Accuracy ◽  
Uav Images

In recent years, remote sensing researchers have investigated the use of different modalities (or combinations of modalities) for classification tasks. Such modalities can be extracted via a diverse range of sensors and images. Currently, there are no (or only a few) studies that have been done to increase the land cover classification accuracy via unmanned aerial vehicle (UAV)–digital surface model (DSM) fused datasets. Therefore, this study looks at improving the accuracy of these datasets by exploiting convolutional neural networks (CNNs). In this work, we focus on the fusion of DSM and UAV images for land use/land cover mapping via classification into seven classes: bare land, buildings, dense vegetation/trees, grassland, paved roads, shadows, and water bodies. Specifically, we investigated the effectiveness of the two datasets with the aim of inspecting whether the fused DSM yields remarkable outcomes for land cover classification. The datasets were: (i) only orthomosaic image data (Red, Green and Blue channel data), and (ii) a fusion of the orthomosaic image and DSM data, where the final classification was performed using a CNN. CNN, as a classification method, is promising due to hierarchical learning structure, regulating and weight sharing with respect to training data, generalization, optimization and parameters reduction, automatic feature extraction and robust discrimination ability with high performance. The experimental results show that a CNN trained on the fused dataset obtains better results with Kappa index of ~0.98, an average accuracy of 0.97 and final overall accuracy of 0.98. Comparing accuracies between the CNN with DSM result and the CNN without DSM result for the overall accuracy, average accuracy and Kappa index revealed an improvement of 1.2%, 1.8% and 1.5%, respectively. Accordingly, adding the heights of features such as buildings and trees improved the differentiation between vegetation specifically where plants were dense.

scholarly journals Time-Series Model-Adjusted Percentile Features: Improved Percentile Features for Land-Cover Classification Based on Landsat Data

2020 ◽  
Vol 12 (18) ◽  
pp. 3091
Author(s):  
Shuai Xie ◽  
Liangyun Liu ◽  
Jiangning Yang
Keyword(s):  
Time Series ◽  
Land Cover ◽  
Time Series Data ◽  
Land Cover Classification ◽  
Time Series Model ◽  
Training Data ◽  
Series Data ◽  
Landsat Data ◽  
Data Sampling ◽  
Continuous Change

Percentile features derived from Landsat time-series data are widely adopted in land-cover classification. However, the temporal distribution of Landsat valid observations is highly uneven across different pixels due to the gaps resulting from clouds, cloud shadows, snow, and the scan line corrector (SLC)-off problem. In addition, when applying percentile features, land-cover change in time-series data is usually not considered. In this paper, an improved percentile called the time-series model (TSM)-adjusted percentile is proposed for land-cover classification based on Landsat data. The Landsat data were first modeled using three different time-series models, and the land-cover changes were continuously monitored using the continuous change detection (CCD) algorithm. The TSM-adjusted percentiles for stable pixels were then derived from the synthetic time-series data without gaps. Finally, the TSM-adjusted percentiles were used for generating supervised random forest classifications. The proposed methods were implemented on Landsat time-series data of three study areas. The classification results were compared with those obtained using the original percentiles derived from the original time-series data with gaps. The results show that the land-cover classifications obtained using the proposed TSM-adjusted percentiles have significantly higher overall accuracies than those obtained using the original percentiles. The proposed method was more effective for forest types with obvious phenological characteristics and with fewer valid observations. In addition, it was also robust to the training data sampling strategy. Overall, the methods proposed in this work can provide accurate characterization of land cover and improve the overall classification accuracy based on such metrics. The findings are promising for percentile-based land cover classification using Landsat time series data, especially in the areas with frequent cloud coverage.

scholarly journals Uncertainty Analysis of Object-Based Land-Cover Classification Using Sentinel-2 Time-Series Data

2020 ◽  
Vol 12 (22) ◽  
pp. 3798
Author(s):  
Lei Ma ◽  
Michael Schmitt ◽  
Xiaoxiang Zhu
Keyword(s):  
Time Series ◽  
Land Cover ◽  
Time Series Data ◽  
Land Cover Classification ◽  
Series Data ◽  
Spectral Bands ◽  
Object Based ◽  
Spatio Temporal ◽  
Optical Satellite Images ◽  
The Impact

Recently, time-series from optical satellite data have been frequently used in object-based land-cover classification. This poses a significant challenge to object-based image analysis (OBIA) owing to the presence of complex spatio-temporal information in the time-series data. This study evaluates object-based land-cover classification in the northern suburbs of Munich using time-series from optical Sentinel data. Using a random forest classifier as the backbone, experiments were designed to analyze the impact of the segmentation scale, features (including spectral and temporal features), categories, frequency, and acquisition timing of optical satellite images. Based on our analyses, the following findings are reported: (1) Optical Sentinel images acquired over four seasons can make a significant contribution to the classification of agricultural areas, even though this contribution varies between spectral bands for the same period. (2) The use of time-series data alleviates the issue of identifying the “optimal” segmentation scale. The finding of this study can provide a more comprehensive understanding of the effects of classification uncertainty on object-based dense multi-temporal image classification.

Sign in / Sign up

Export Citation Format

Share Document