Automated Recognition of Vegetation and Water Bodies on the Territory of Megacities in Satellite Images of Visible and Ir Bands

Mozgovoy, D. K.; Hnatushenko, Volodymyr; Vasyliev, Volodymyr V.

doi:10.5194/isprs-annals-iv-3-167-2018

Cited by 18 publications

(5 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The metrics that were used for the quantifying accuracy of the automatic classification are the following [11,12] [12]. The kappa (κ) coefficient measures the agreement between classification and ground truth pixels.…”

Section: Choice Of the Accuracy Assessment Methods The Evaluation Ofmentioning

confidence: 99%

See 1 more Smart Citation

All-weather monitoring of oil and gas production areas using satellite data

Hnatushenko¹,

Mozgovoy²,

Hnatushenko³

et al. 2019

NVNGU

View full text Add to dashboard Cite

Purpose. Development and testing of an information technology for automated processing of mediumresolution satellite im ages acquired at different times for allweather monitoring of oil and gas production areas. methodology. The information technology implies the use of two algorithms. The algorithm for automated recognition of new oil extraction sites is based on computing the normalized difference index (NDI) of temporal changes for a given pair of satellite images in visible and nearIR bands acquired at different times and selected spectral cannels with subsequent multithreshold binarization. The algorithm for automated recognition of large metal objects uses bipolarized Cband radar images from Sentinel1A/B satellites. findings. The proposed information technology made it possible to automatically detect the new oil extraction sites and rec ognition of large metal objects. The overall recognition accuracy, averaged for 20 test areas, was from 87 to 91 % with the kappa coefficient ranging from 0.82 to 0.85. For cloudcovered areas the big metal objects (an extraction units, automotive equipment for oil transportation, etc.) were recognized using SAR imagery from Sentinel1A/B satellites only. originality. Unlike the existing methods for detection of anthropogenic changes of the Earth's surface by satellite images, the proposed information technology uses immediate calculation of the normalized difference index of temporal changes NDI for a given pair of satellite images acquired at different times, which considerably reduces requirements to the computing power while ensuring higher accuracy of the allocation of the boundaries of new oil production sites. Allweather monitoring is provided using radar data. Practical value. Owing to high degree of automation, the developed technology can be implemented as a geoinformation web service for allweather uptothedate monitoring of oil extraction areas. This web service can be used to determine the area of fields, control production activity and estimate oil production, supervise development and production activities and assess anthro pogenic load in oil production areas.

show abstract

Section: Choice Of the Accuracy Assessment Methods The Evaluation Ofmentioning

confidence: 99%

“…The kappa (κ) coefficient measures the agreement between classification and ground truth pixels. A kappa value of 1 rep resents perfect agreement while a value of 0 represents no agreement [12] , ,…”

Section: Choice Of the Accuracy Assessment Methods The Evaluation Ofmentioning

confidence: 99%

All-weather monitoring of oil and gas production areas using satellite data

Hnatushenko¹,

Mozgovoy²,

Hnatushenko³

et al. 2019

NVNGU

View full text Add to dashboard Cite

show abstract

“…The data set is provided as a raster, with a ground sampling resolution of 0.5 meters. The imagery contains four bands, with reflectance information in the red, green, blue and a near-infrared bands, (Mozgovoy et al, 2018).…”

Section: Superviewmentioning

confidence: 99%

Probabilistic Vegetation Transitions in Dunes by Combining Spectral and Lidar Data

Kathmann

Natijne

Lindenbergh

2022

Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

Abstract. Monitoring the status of the vegetation is required for nature conservation. This monitoring task is time consuming as kilometers of area have to be investigated and classified. To make this task more manageable, remote sensing is used. The acquisition of airplane remote sensing data is dependent on weather conditions and permission to fly in the busy airspace above the Netherlands. These conditions make it difficult to get a new, dedicated acquisition every year. Therefore, alternatives for this dependency on dedicated airplane surveys are needed. One alternative is the use of optical satellite imagery, as this type of data has improved rapidly in the last decade both in terms of resolution and revisit time. For this study, 0.5 m resolution satellite imagery from the Superview satellite is combined with geometric height data from the Dutch national airborne LiDAR elevation data set AHN. Goal is to classify vegetation into three different classes: sand, grass and trees, apply this classification to multiple epochs, and analyze class transition patterns. Three different classification methods were compared: nearest centroid, random forest and neural network. We show that outcomes of all three methods can be interpreted as class probabilities, but also that these probabilities have different properties for each method. The classification is implemented for 11 different epochs on the Meijendel en Berkheide dunal area on the Dutch coast. We show that mixed probabilities (i.e. between two classes) agree well with class transition processes, and conclude that a shallow neural network combined with pure training samples applied on four different bands (RGB + relative DSM height) produces satisfactory results for the analysis of vegetation transitions with accuracies close to 100%.

show abstract

“…Суть исследований заключалась в проведении автоматизированного распознавания расти тельности и водных объектов на территории ме гаполисов по спутниковым снимкам сверхвысо кого пространственного разрешения видимого и ИК диапазонов и сравнения полученных ре зультатов с результатами визуального дешифри рования [9,10]…”

Section: методология исследованийunclassified

Operational satellite monitoring vegetation and water objects in the territory of cities

Mozgovoy¹

2018

UJRS

View full text Add to dashboard Cite

A technique for the operational monitoring of vegetation and water objects in the territory of cities by satellite images of ultrahigh spatial resolution of the visible and IR ranges is proposed. In the process of processing multispectral images from the satellite DubaiSat-2, vector layers of recognized vegetation and water objects were obtained. The analysis of the results of the automated processing of satellite images showed a sufficiently high accuracy of distinguishing the boundaries of recognized objects and a good separation of classes. The developed methodology allows to significantly increase the efficiency and reliability of updating maps of large cities while reducing financial costs. Due to the high degree of automation, the proposed methodology can be implemented in the form of a geoinformation web service, functioning in the interests of a wide range of users.

show abstract

Automated Recognition of Vegetation and Water Bodies on the Territory of Megacities in Satellite Images of Visible and Ir Bands

Cited by 18 publications

References 13 publications

All-weather monitoring of oil and gas production areas using satellite data

All-weather monitoring of oil and gas production areas using satellite data

Probabilistic Vegetation Transitions in Dunes by Combining Spectral and Lidar Data

Operational satellite monitoring vegetation and water objects in the territory of cities

Contact Info

Product

Resources

About