Texture based information extraction from high resolution images using object based classification approach

2014 ◽  
Author(s):  
Kuldeep ◽  
P. K. Garg
Keyword(s):  
High Resolution ◽  
Information Extraction ◽  
Classification Approach ◽  
Object Based ◽  
High Resolution Images

scholarly journals Mask R-CNN and OBIA Fusion Improves the Segmentation of Scattered Vegetation in Very High-Resolution Optical Sensors

Sensors ◽  
2021 ◽  
Vol 21 (1) ◽  
pp. 320
Author(s):  
Emilio Guirado ◽  
Javier Blanco-Sacristán ◽  
Emilio Rodríguez-Caballero ◽  
Siham Tabik ◽  
Domingo Alcaraz-Segura ◽  
...  
Keyword(s):  
High Resolution ◽  
Optical Sensors ◽  
Biotic Interactions ◽  
Relevant Information ◽  
Vegetation Monitoring ◽  
Object Based Image Analysis ◽  
Object Based ◽  
Segmentation Methods ◽  
High Resolution Images ◽  
Very High

Vegetation generally appears scattered in drylands. Its structure, composition and spatial patterns are key controls of biotic interactions, water, and nutrient cycles. Applying segmentation methods to very high-resolution images for monitoring changes in vegetation cover can provide relevant information for dryland conservation ecology. For this reason, improving segmentation methods and understanding the effect of spatial resolution on segmentation results is key to improve dryland vegetation monitoring. We explored and analyzed the accuracy of Object-Based Image Analysis (OBIA) and Mask Region-based Convolutional Neural Networks (Mask R-CNN) and the fusion of both methods in the segmentation of scattered vegetation in a dryland ecosystem. As a case study, we mapped Ziziphus lotus, the dominant shrub of a habitat of conservation priority in one of the driest areas of Europe. Our results show for the first time that the fusion of the results from OBIA and Mask R-CNN increases the accuracy of the segmentation of scattered shrubs up to 25% compared to both methods separately. Hence, by fusing OBIA and Mask R-CNNs on very high-resolution images, the improved segmentation accuracy of vegetation mapping would lead to more precise and sensitive monitoring of changes in biodiversity and ecosystem services in drylands.

scholarly journals CNN BASED DETECTION OF BUILDING ROOFS FROM HIGH RESOLUTION SATELLITE IMAGES

2020 ◽  
Vol XLII-3/W10 ◽  
pp. 187-192
Author(s):  
L. Hang ◽  
G. Y. Cai
Keyword(s):  
High Resolution ◽  
Residential Building ◽  
Training Image ◽  
Training Dataset ◽  
Classification Approach ◽  
Object Based ◽  
High Resolution Satellite Images ◽  
Different Types ◽  
Model Training ◽  
Very High

Abstract. The detection and reconstruction of building have attracted more attention in the community of remote sensing and computer vision. Light detection and ranging (LiDAR) has been proved to be a good way to extract building roofs, while we have to face the problem of data shortage for most of the time. In this paper, we tried to extract the building roofs from very high resolution (VHR) images of Chinese satellite Gaofen-2 by employing convolutional neural network (CNN). It has been proved that the CNN is of a higher capability of recognizing detailed features which may not be classified out by object-based classification approach. Several major steps are concerned in this study, such as generation of training dataset, model training, image segmentation and building roofs recognition. First, urban objects such as trees, roads, squares and buildings were classified based on random forest algorithm by an object-oriented classification approach, the building regions were separated from other classes at the aid of visually interpretation and correction; Next, different types of building roofs mainly categorized by color and size information were trained using the trained CNN. Finally, the industrial and residential building roofs have been recognized individually and the results have been validated individually. The assessment results prove effectiveness of the proposed method with approximately 91% and 88% of quality rates in detection industrial and residential building roofs, respectively. Which means that the CNN approach is prospecting in detecting buildings with a very higher accuracy.

Spectral information extraction from very high resolution images through multiresolution fusion

2004 ◽  
Author(s):  
Luciano Alparone ◽  
Bruno Aiazzi ◽  
Stefano Baronti ◽  
Andrea Garzelli ◽  
Filippo Nencini ◽  
...  
Keyword(s):  
High Resolution ◽  
Information Extraction ◽  
Spectral Information ◽  
High Resolution Images ◽  
Very High

scholarly journals SAR Image Segmentation Using Morphological Attribute Profiles

2014 ◽  
Vol XL-3 ◽  
pp. 39-44 ◽  
Author(s):  
M. Boldt ◽  
A. Thiele ◽  
K. Schulz ◽  
S. Hinz
Keyword(s):  
Image Segmentation ◽  
High Resolution ◽  
Region Growing ◽  
Object Based Image Analysis ◽  
Sar Image Segmentation ◽  
High Resolution Imagery ◽  
Object Based ◽  
High Resolution Images ◽  
Novel Method ◽  
Image Set

In the last years, the spatial resolution of remote sensing sensors and imagery has continuously improved. Focusing on spaceborne Synthetic Aperture Radar (SAR) sensors, the satellites of the current generation (TerraSAR-X, COSMO-SykMed) are able to acquire images with sub-meter resolution. Indeed, high resolution imagery is visually much better interpretable, but most of the established pixel-based analysis methods have become more or less impracticable since, in high resolution images, self-sufficient objects (vehicle, building) are represented by a large number of pixels. Methods dealing with Object-Based Image Analysis (OBIA) provide help. Objects (segments) are groupings of pixels resulting from image segmentation algorithms based on homogeneity criteria. The image set is represented by image segments, which allows the development of rule-based analysis schemes. For example, segments can be described or categorized by their local neighborhood in a context-based manner. <br><br> In this paper, a novel method for the segmentation of high resolution SAR images is presented. It is based on the calculation of morphological differential attribute profiles (DAP) which are analyzed pixel-wise in a region growing procedure. The method distinguishes between heterogeneous and homogeneous image content and delivers a precise segmentation result.

scholarly journals Object-Based Features for House Detection from RGB High-Resolution Images

2018 ◽  
Vol 10 (3) ◽  
pp. 451 ◽  
Author(s):  
Renxi Chen ◽  
Xinhui Li ◽  
Jonathan Li
Keyword(s):  
High Resolution ◽  
Object Based ◽  
High Resolution Images

Modeling strawberry biomass and leaf area using object-based analysis of high-resolution images

2020 ◽  
Vol 163 ◽  
pp. 171-186 ◽  
Author(s):  
Zhen Guan ◽  
Amr Abd-Elrahman ◽  
Zhen Fan ◽  
Vance M. Whitaker ◽  
Benjamin Wilkinson
Keyword(s):  
High Resolution ◽  
Leaf Area ◽  
Object Based ◽  
High Resolution Images

Time series of high-resolution images enhances efforts to monitor post-fire condition and recovery, Waldo Canyon fire, Colorado, USA

2018 ◽  
Vol 27 (10) ◽  
pp. 699 ◽  
Author(s):  
Melanie K. Vanderhoof ◽  
Clifton Burt ◽  
Todd J. Hawbaker
Keyword(s):  
Time Series ◽  
High Resolution ◽  
Vegetation Index ◽  
Burn Severity ◽  
Vegetation Recovery ◽  
Burned Area ◽  
Object Based ◽  
Fire Condition ◽  
Normalised Difference Vegetation Index ◽  
High Resolution Images

Interpretations of post-fire condition and rates of vegetation recovery can influence management priorities, actions and perception of latent risks from landslides and floods. In this study, we used the Waldo Canyon fire (2012, Colorado Springs, Colorado, USA) as a case study to explore how a time series (2011–2016) of high-resolution images can be used to delineate burn extent and severity, as well as quantify post-fire vegetation recovery. We applied an object-based approach to map burn severity and vegetation recovery using Worldview-2, Worldview-3 and QuickBird-2 imagery. The burned area was classified as 51% high, 20% moderate and 29% low burn-severity. Across the burn extent, the shrub cover class showed a rapid recovery, resprouting vigorously within 1 year, whereas 4 years post-fire, areas previously dominated by conifers were divided approximately equally between being classified as dominated by quaking aspen saplings with herbaceous species in the understorey or minimally recovered. Relative to using a pixel-based Normalised Difference Vegetation Index (NDVI), our object-based approach showed higher rates of revegetation. High-resolution imagery can provide an effective means to monitor post-fire site conditions and complement more prevalent efforts with moderate- and coarse-resolution sensors.

Sign in / Sign up

Export Citation Format

Share Document