The success of deep learning in visual recognition tasks has driven advancements in multiple fields of research. Particularly, increasing attention has been drawn towards its application in agriculture. Nevertheless, while visual pattern recognition on farmlands carries enormous economic values, little progress has been made to merge computer vision and crop sciences due to the lack of suitable agricultural image datasets. Meanwhile, problems in agriculture also pose new challenges in computer vision. For example, semantic segmentation of aerial farmland images requires inference over extremely large-size images with extreme annotation sparsity. These challenges are not present in most of the common object datasets, and we show that they are more challenging than many other aerial image datasets. To encourage research in computer vision for agriculture, we present Agriculture-Vision: a large-scale aerial farmland image dataset for semantic segmentation of agricultural patterns. We collected 94,986 high-quality aerial images from 3,432 farmlands across the US, where each image consists of RGB and Near-infrared (NIR) channels with resolution as high as 10 cm per pixel. We annotate nine types of field anomaly patterns that are most important to farmers. As a pilot study of aerial agricultural semantic segmentation, we perform comprehensive experiments using popular semantic segmentation models; we also propose an effective model designed for aerial agricultural pattern recognition. Our experiments demonstrate several challenges Agriculture-Vision poses to both the computer vision and agriculture communities. Future versions of this dataset will include even more aerial images, anomaly patterns and image channels.

/pdf/agriculture-vision-a-large-aerial-image-database-for-3155zvp41u.pdf

Agriculture-Vision: A Large Aerial Image Database for Agricultural Pattern Analysis

Land-use and land-cover (LULC) classification using remote sensing imagery plays a vital role in many environment modeling and land-use inventories. In this study, a hybrid feature optimization algorithm along with a deep learning classifier is proposed to improve the performance of LULC classification, helping to predict wildlife habitat, deteriorating environmental quality, haphazard elements, etc. LULC classification is assessed using Sat 4, Sat 6 and Eurosat datasets. After the selection of remote-sensing images, normalization and histogram equalization methods are used to improve the quality of the images. Then, a hybrid optimization is accomplished by using the local Gabor binary pattern histogram sequence (LGBPHS), the histogram of oriented gradient (HOG) and Haralick texture features, for the feature extraction from the selected images. The benefits of this hybrid optimization are a high discriminative power and invariance to color and grayscale images. Next, a human group-based particle swarm optimization (PSO) algorithm is applied to select the optimal features, whose benefits are a fast convergence rate and ease of implementation. After selecting the optimal feature values, a long short-term memory (LSTM) network is utilized to classify the LULC classes. Experimental results showed that the human group-based PSO algorithm with a LSTM classifier effectively well differentiates the LULC classes in terms of classification accuracy, recall and precision. A maximum improvement of 6.03% on Sat 4 and 7.17% on Sat 6 in LULC classification is reached when the proposed human group-based PSO with LSTM is compared to individual LSTM, PSO with LSTM, and Human Group Optimization (HGO) with LSTM. Moreover, an improvement of 2.56% in accuracy is achieved, compared to the existing models, GoogleNet, Visual Geometric Group (VGG), AlexNet, ConvNet, when the proposed method is applied.

/pdf/land-use-and-land-cover-classification-using-a-human-group-2282454xr7.pdf

Land-Use and Land-Cover Classification Using a Human Group-Based Particle Swarm Optimization Algorithm with an LSTM Classifier on Hybrid Pre-Processing Remote-Sensing Images

Multispectral LiDAR (Light Detection And Ranging) is characterized of the completeness and consistency of its spectrum and spatial geometric data, which provides a new data source for land-cover classification In recent years, the convolutional neural network (CNN), compared with traditional machine learning methods, has made a series of breakthroughs in image classification, object detection, and image semantic segmentation due to its stronger feature learning and feature expression abilities However, traditional CNN models suffer from some issues, such as a large number of layers, leading to higher computational cost To address this problem, we propose a CNN-based multi-spectral LiDAR land-cover classification framework and analyze its optimal parameters to improve classification accuracy This framework starts with the preprocessing of multi-spectral 3D LiDAR data into 2D images Next, a CNN model is constructed with seven fundamental functional layers, and its hyper-parameters are comprehensively discussed and optimized The constructed CNN model with the optimized hyper-parameters was tested on the Titan multi-spectral LiDAR data, which include three wavelengths of 532 nm, 1064 nm, and 1550 nm Extensive experiments demonstrated that the constructed CNN with the optimized hyper-parameters is feasible for multi-spectral LiDAR land-cover classification tasks Compared with the classical CNN models (ie, AlexNet, VGG16 and ResNet50) and our previous studies, our constructed CNN model with the optimized hyper-parameters is superior in computational performance and classification accuracies

Land-cover classification of multispectral LiDAR data using CNN with optimized hyper-parameters

Autonomous damage recognition in visual inspection of laminated composite structures using deep learning

The success of deep learning in visual recognition tasks has driven advancements in multiple fields of research. Particularly, increasing attention has been drawn towards its application in agriculture. Nevertheless, while visual pattern recognition on farmlands carries enormous economic values, little progress has been made to merge computer vision and crop sciences due to the lack of suitable agricultural image datasets. Meanwhile, problems in agriculture also pose new challenges in computer vision. For example, semantic segmentation of aerial farmland images requires inference over extremely large-size images with extreme annotation sparsity. These challenges are not present in most of the common object datasets, and we show that they are more challenging than many other aerial image datasets. To encourage research in computer vision for agriculture, we present Agriculture-Vision: a large-scale aerial farmland image dataset for semantic segmentation of agricultural patterns. We collected 94,986 high-quality aerial images from 3,432 farmlands across the US, where each image consists of RGB and Near-infrared (NIR) channels with resolution as high as 10 cm per pixel. We annotate nine types of field anomaly patterns that are most important to farmers. As a pilot study of aerial agricultural semantic segmentation, we perform comprehensive experiments using popular semantic segmentation models; we also propose an effective model designed for aerial agricultural pattern recognition. Our experiments demonstrate several challenges Agriculture-Vision poses to both the computer vision and agriculture communities. Future versions of this dataset will include even more aerial images, anomaly patterns and image channels. More information at this https URL.

Classification of remotely sensed data requires the modelling of suitable image processing algorithms. The rise of machine learning systems upgraded the viability of satellite image applications. Using Convolutional Neural Networks (CNN), benchmark classification exactness can be accomplished for land cover grouping. Motivated by the concept of Normalized Difference Vegetation Index (NDVI), this paper utilizes only the red and near infrared (NIR) band information for classifying the publicly available SAT-4 and SAT-6 datasets. This is done, since NDVI computation requires only the two band (red and NIR) information and the classes involved in the dataset are types of vegetation. In this work, new deep learning architectures for three different networks (AlexNet, ConvNet, VGG) were proposed by hypertuning the network and the input as two band data. The modified architectures with the two band information along with reduced number of filters were trained and tested model manages to classify the images into different classes. The proposed architectures are compared against the existing architectures in terms of accuracy, precision and trainable parameters. The proposed architecture is found to perform equally efficient by retaining high accuracy with less number of trainable parameters, when compared against the the performance of benchmark deep learning architectures for satellite image classification.

Deep learning architectures for land cover classification using red and near-infrared satellite images

Deep AlexNet with Reduced Number of Trainable Parameters for Satellite Image Classification

The advent of neural networks has led to the development of image classification algorithms that are applied to different fields In order to recover the vital spatial factor parameters, for example, land cover and land utilization, image grouping is most important in remote sensing Recently, benchmark classification accuracy was achieved using convolutional neural networks (CNNs) for land cover classification The most well-known tool which indicates the presence of green vegetation from multispectral pictures is the Normalized Difference Vegetation Index (NDVI) This chaper utilizes the success of the NDVI for effective classification of a new satellite dataset, SAT-4, where the classes involved are types of vegetation As NDVI calculations require only two bands of information, it takes advantage of both RED- and NIR-band information to classify different land cover The number and size of filters affect the number of parameters in convolutional networks Restricting the aggregate number of trainable parameters reduces the complexity of the function and accordingly decreases overfitting The ConvNet Architecture with two band information, along with a reduced number of filters, was trained, and high-level features obtained from a tested model managed to classify different land cover classes in the dataset The proposed architecture, results in the total reduction of trainable parameters, while retaining high accuracy, when compared with existing architecture, which uses four bands

Anju Unnikrishnan

Papers

Deep learning architectures for land cover classification using red and near-infrared satellite images

Deep AlexNet with Reduced Number of Trainable Parameters for Satellite Image Classification

A two-band convolutional neural network for satellite image classification