scholarly journals Global-scale object detection using satellite imagery

2014 ◽  
Vol XL-3 ◽  
pp. 107-113 ◽  
Author(s):  
R. Hamid ◽  
S. O'Hara ◽  
M. Tabb
Keyword(s):  
Satellite Imagery ◽  
Large Scale ◽  
Global Scale ◽  
Feature Representation ◽  
Training Data ◽  
Crowd Sourcing ◽  
Multiple Objects ◽  
Sensing Applications ◽  
Efficient Extraction ◽  
Remote Sensing Applications

In recent years, there has been a substantial increase in the availability of high-resolution commercial satellite imagery, enabling a variety of new remote-sensing applications. One of the main challenges for these applications is the accurate and efficient extraction of semantic information from satellite imagery. In this work, we investigate an important instance of this class of challenges which involves automatic detection of multiple objects in satellite images. We present a system for large-scale object training and detection, leveraging recent advances in feature representation and aggregation within the bag-of-words paradigm. Given the scale of the problem, one of the key challenges in learning object detectors is the acquisition and curation of labeled training data. We present a crowd-sourcing based framework that allows efficient acquisition of labeled training data, along with an iterative mechanism to overcome the label noise introduced by the crowd during the labeling process. To show the competence of the presented scheme, we show detection results over several object-classes using training data captured from close to 200 cities and tested over multiple geographic locations.

scholarly journals Modeling with the crowd: Optimizing the human-machine partnership with Zooniverse

2019 ◽  
Vol 15 (S341) ◽  
pp. 99-103 ◽  
Author(s):  
Hugh Dickinson ◽  
Lucy Fortson ◽  
Claudia Scarlata ◽  
Melanie Beck ◽  
Mike Walmsley
Keyword(s):  
Large Scale ◽  
Training Data ◽  
Object Localization ◽  
Crowd Sourcing ◽  
Morphological Classification ◽  
Binary Responses ◽  
Automatic Image Processing ◽  
Daunting Challenge ◽  
Computational Analyses ◽  
Bayesian Aggregation

AbstractLSST and Euclid must address the daunting challenge of analyzing the unprecedented volumes of imaging and spectroscopic data that these next-generation instruments will generate. A promising approach to overcoming this challenge involves rapid, automatic image processing using appropriately trained Deep Learning (DL) algorithms. However, reliable application of DL requires large, accurately labeled samples of training data. Galaxy Zoo Express (GZX) is a recent experiment that simulated using Bayesian inference to dynamically aggregate binary responses provided by citizen scientists via the Zooniverse crowd-sourcing platform in real time. The GZX approach enables collaboration between human and machine classifiers and provides rapidly generated, reliably labeled datasets, thereby enabling online training of accurate machine classifiers. We present selected results from GZX and show how the Bayesian aggregation engine it uses can be extended to efficiently provide object-localization and bounding-box annotations of two-dimensional data with quantified reliability. DL algorithms that are trained using these annotations will facilitate numerous panchromatic data modeling tasks including morphological classification and substructure detection in direct imaging, as well as decontamination and emission line identification for slitless spectroscopy. Effectively combining the speed of modern computational analyses with the human capacity to extrapolate from few examples will be critical if the potential of forthcoming large-scale surveys is to be realized.

scholarly journals Urban sprawl into the Niagara Region: the effect of urban encroachment on agriculture seen through the use of remote sensing applications and landscape metrics

2021 ◽  
Author(s):  
Jessica Leigh-Anne Carvalho
Keyword(s):  
Satellite Imagery ◽  
Urban Sprawl ◽  
Landscape Metrics ◽  
Agricultural Land ◽  
Agricultural Practices ◽  
Detection Methods ◽  
Land Uses ◽  
Sensing Applications ◽  
Remote Sensing Applications ◽  
Landsat 5 Tm

The Niagara Region contains land that is ideal for agricultural practices. This thesis strives to illuminate whether or not urban growth in the Niagara Region is a detriment to agricultural land use. Using Landsat 5 TM and 8 OLI-TIRS satellite imagery, spatial statistics, called landscape metrics, will be utilized to determine growth and loss of urban and agriculture land uses. Satellite imagery will be classified based on researched methods in order to create land class maps. These maps will then be utilized for landscape metrics using the Patch Analyst extension for ArcMap. Change detection methods will also be observed. The above methods will be done for the overall landscape of the Niagara Region. This study will find that agriculture in the Niagara Region is changing and endeavors to highlight how urban sprawl is part of the cause. Fragmentation will be discussed as part of the issues due to urban sprawl.

scholarly journals Urban sprawl into the Niagara Region: the effect of urban encroachment on agriculture seen through the use of remote sensing applications and landscape metrics

2021 ◽  
Author(s):  
Jessica Leigh-Anne Carvalho
Keyword(s):  
Satellite Imagery ◽  
Urban Sprawl ◽  
Landscape Metrics ◽  
Agricultural Land ◽  
Agricultural Practices ◽  
Detection Methods ◽  
Land Uses ◽  
Sensing Applications ◽  
Remote Sensing Applications ◽  
Landsat 5 Tm

The Niagara Region contains land that is ideal for agricultural practices. This thesis strives to illuminate whether or not urban growth in the Niagara Region is a detriment to agricultural land use. Using Landsat 5 TM and 8 OLI-TIRS satellite imagery, spatial statistics, called landscape metrics, will be utilized to determine growth and loss of urban and agriculture land uses. Satellite imagery will be classified based on researched methods in order to create land class maps. These maps will then be utilized for landscape metrics using the Patch Analyst extension for ArcMap. Change detection methods will also be observed. The above methods will be done for the overall landscape of the Niagara Region. This study will find that agriculture in the Niagara Region is changing and endeavors to highlight how urban sprawl is part of the cause. Fragmentation will be discussed as part of the issues due to urban sprawl.

scholarly journals A REVIEW ON SPATIAL QUALITY ASSESSMENT METHODS FOR EVALUATION OF PAN-SHARPENED SATELLITE IMAGERY

2019 ◽  
Vol XLII-4/W18 ◽  
pp. 255-261
Author(s):  
F. Dadras Javan ◽  
F. Samadzadegan ◽  
S. Mehravar ◽  
A. Toosi
Keyword(s):  
Remote Sensing ◽  
Quality Assessment ◽  
Satellite Imagery ◽  
Urban Areas ◽  
Large Scale ◽  
Spatial Distortion ◽  
Sensing Applications ◽  
Fused Image ◽  
Spatial Quality

Abstract. Nowadays, high-resolution fused satellite imagery is widely used in multiple remote sensing applications. Although the spectral quality of pan-sharpened images plays an important role in many applications, spatial quality becomes more important in numerous cases. The high spatial quality of the fused image is essential for extraction, identification and reconstruction of significant image objects, and will result in producing high-quality large scale maps especially in the urban areas. This paper introduces the most sensitive and effective methods in detecting the spatial distortion of fused images by implementing a number of spatial quality assessment indices that are utilized in the field of remote sensing and image processing. In this regard, in order to recognize the ability of quality assessment indices for detecting the spatial distortion quantity of fused images, input images of the fusion process are affected by some intentional spatial distortions based on non-registration error. The capabilities of the investigated metrics are evaluated on four different fused images derived from Ikonos and WorldView-2 initial images. Achieved results obviously explicate that two methods namely Edge Variance Distortion and the spatial component of QNR metric called Ds are more sensitive and responsive to the imported errors.

scholarly journals Tree Kernels for Semantic Role Labeling

2008 ◽  
Vol 34 (2) ◽  
pp. 193-224 ◽  
Author(s):  
Alessandro Moschitti ◽  
Daniele Pighin ◽  
Roberto Basili
Keyword(s):  
Language Processing ◽  
Large Scale ◽  
Kernel Functions ◽  
Feature Representation ◽  
Training Data ◽  
Support Vector ◽  
Feature Engineering ◽  
Semantic Role ◽  
Learning Approaches ◽  
Semantic Role Labeling

The availability of large scale data sets of manually annotated predicate-argument structures has recently favored the use of machine learning approaches to the design of automated semantic role labeling (SRL) systems. The main research in this area relates to the design choices for feature representation and for effective decompositions of the task in different learning models. Regarding the former choice, structural properties of full syntactic parses are largely employed as they represent ways to encode different principles suggested by the linking theory between syntax and semantics. The latter choice relates to several learning schemes over global views of the parses. For example, re-ranking stages operating over alternative predicate-argument sequences of the same sentence have shown to be very effective. In this article, we propose several kernel functions to model parse tree properties in kernel-based machines, for example, perceptrons or support vector machines. In particular, we define different kinds of tree kernels as general approaches to feature engineering in SRL. Moreover, we extensively experiment with such kernels to investigate their contribution to individual stages of an SRL architecture both in isolation and in combination with other traditional manually coded features. The results for boundary recognition, classification, and re-ranking stages provide systematic evidence about the significant impact of tree kernels on the overall accuracy, especially when the amount of training data is small. As a conclusive result, tree kernels allow for a general and easily portable feature engineering method which is applicable to a large family of natural language processing tasks.

scholarly journals Mapping Large-Scale Plateau Forest in Sanjiangyuan Using High-Resolution Satellite Imagery and Few-Shot Learning

2022 ◽  
Vol 14 (2) ◽  
pp. 388
Author(s):  
Zhihao Wei ◽  
Kebin Jia ◽  
Xiaowei Jia ◽  
Pengyu Liu ◽  
Ying Ma ◽  
...  
Keyword(s):  
High Resolution ◽  
Satellite Imagery ◽  
Large Scale ◽  
Ground Truth ◽  
Fine Tuning ◽  
Forest Monitoring ◽  
Learning Method ◽  
Ground Truth Data ◽  
Sensing Applications ◽  
High Resolution Satellite Imagery

Monitoring the extent of plateau forests has drawn much attention from governments given the fact that the plateau forests play a key role in global carbon circulation. Despite the recent advances in the remote-sensing applications of satellite imagery over large regions, accurate mapping of plateau forest remains challenging due to limited ground truth information and high uncertainties in their spatial distribution. In this paper, we aim to generate a better segmentation map for plateau forests using high-resolution satellite imagery with limited ground-truth data. We present the first 2 m spatial resolution large-scale plateau forest dataset of Sanjiangyuan National Nature Reserve, including 38,708 plateau forest imagery samples and 1187 handmade accurate plateau forest ground truth masks. We then propose an few-shot learning method for mapping plateau forests. The proposed method is conducted in two stages, including unsupervised feature extraction by leveraging domain knowledge, and model fine-tuning using limited ground truth data. The proposed few-shot learning method reached an F1-score of 84.23%, and outperformed the state-of-the-art object segmentation methods. The result proves the proposed few-shot learning model could help large-scale plateau forest monitoring. The dataset proposed in this paper will soon be available online for the public.

scholarly journals SmokeNet: Satellite Smoke Scene Detection Using Convolutional Neural Network with Spatial and Channel-Wise Attention

2019 ◽  
Vol 11 (14) ◽  
pp. 1702 ◽  
Author(s):  
Rui Ba ◽  
Chen Chen ◽  
Jing Yuan ◽  
Weiguo Song ◽  
Siuming Lo
Keyword(s):  
Neural Network ◽  
Satellite Imagery ◽  
Large Scale ◽  
State Of The Art ◽  
Kappa Coefficient ◽  
Feature Representation ◽  
Detection Methods ◽  
Smoke Detection ◽  
Training Images ◽  
Moderate Resolution Imaging Spectroradiometer

A variety of environmental analysis applications have been advanced by the use of satellite remote sensing. Smoke detection based on satellite imagery is imperative for wildfire detection and monitoring. However, the commonly used smoke detection methods mainly focus on smoke discrimination from a few specific classes, which reduces their applicability in different regions of various classes. To this end, in this paper, we present a new large-scale satellite imagery smoke detection benchmark based on Moderate Resolution Imaging Spectroradiometer (MODIS) data, namely USTC_SmokeRS, consisting of 6225 satellite images from six classes (i.e., cloud, dust, haze, land, seaside, and smoke) and covering various areas/regions over the world. To build a baseline for smoke detection in satellite imagery, we evaluate several state-of-the-art deep learning-based image classification models. Moreover, we propose a new convolution neural network (CNN) model, SmokeNet, which incorporates spatial and channel-wise attention in CNN to enhance feature representation for scene classification. The experimental results of our method using different proportions (16%, 32%, 48%, and 64%) of training images reveal that our model outperforms other approaches with higher accuracy and Kappa coefficient. Specifically, the proposed SmokeNet model trained with 64% training images achieves the best accuracy of 92.75% and Kappa coefficient of 0.9130. The model trained with 16% training images can also improve the classification accuracy and Kappa coefficient by at least 4.99% and 0.06, respectively, over the state-of-the-art models.

UAV Remote Sensing Applications in Large-scale Mapping in the Hilly Region of Tibetan Plateau

2015 ◽  
Vol 8 (3) ◽  
pp. 279-286
Author(s):  
Xue Tianyun ◽  
Tian Xiaocheng ◽  
Yang Defang ◽  
Xiong Yonghe ◽  
Yan Hongliang
Keyword(s):  
Remote Sensing ◽  
Tibetan Plateau ◽  
Large Scale ◽  
Sensing Applications ◽  
Hilly Region ◽  
Remote Sensing Applications

scholarly journals A Review of Free Optical Satellite Imagery for Watershed-Scale Landscape Analysis

2018 ◽  
Vol 2 (2) ◽  
Author(s):  
Alexandre Bevington ◽  
Hunter Gleason ◽  
Xavier Giroux-Bougard ◽  
J. Tyler De Jong
Keyword(s):  
Remote Sensing ◽  
Environmental Change ◽  
Satellite Imagery ◽  
Reference Materials ◽  
Landscape Analysis ◽  
Western Canada ◽  
Watershed Scale ◽  
Sensing Applications ◽  
Remote Sensing Applications ◽  
Basic Concepts

Watershed-scale landscape analysis includes many disciplines, including ecological, hydrological, and geographical sciences. The recent proliferation of free optical satellite imagery (FOSI) has changed the possibilities for the monitoring of environmental change at local and global scales. Many reviews exist for discipline-specific remote sensing applications; however, this article seeks to highlight the rapidly growing archive of FOSI and applied tools that can be used by all levels of users. Herein, ten techniques and eight applications of FOSI are reviewed, along with the specifications and limitations of various sources of FOSI. Although this review focuses on Western Canada, the democratization of FOSI is globally relevant, and the objective is to explain basic concepts via figures and reference materials to help summarize this rapidly changing field.

Sign in / Sign up

Export Citation Format

Share Document