Object-based Method for Identifying New Constructions around Water Reservoirs: Preliminary Results

Hamidishad, Nayereh; César, Roberto M.

doi:10.5753/sibgrapi.est.2019.8322

Cited by 2 publications

(3 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…4 Over the last decades, the RS community has undertaken considerable efforts to promote the use of OB technology for land cover/use mapping. 5,6 In contrast with pixel-based methods, OB classification methods are less sensitive to the spectral variance within the objects. They can use both object features and spatial relations between the objects.…”

Section: Introductionmentioning

confidence: 99%

“…With the increase in the spatial resolution of satellite images resulting from improvements in RS systems, a single pixel does not adequately capture the characteristics of target objects, leading to a reduction in the classification accuracy using pixel-based methods 4 . Over the last decades, the RS community has undertaken considerable efforts to promote the use of OB technology for land cover/use mapping 5 , 6 . In contrast with pixel-based methods, OB classification methods are less sensitive to the spectral variance within the objects.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Man-made object segmentation around reservoirs by an end-to-end two-phase deep learning-based workflow

Hamidishad,

Cesar

2024

J. Appl. Rem. Sens.

View full text Add to dashboard Cite

Constructions around them can negatively impact their water quality. Such constructions can be detected by segmenting man-made objects around reservoirs in the remote sensing (RS) images. Deep learning (DL) has attracted considerable attention in recent years as a method for segmenting the RS imagery into different land covers/uses and has achieved remarkable success. We develop an approach based on DL and image processing techniques for man-made object segmentation around the reservoirs. In order to segment man-made objects around the reservoirs in an end-to-end procedure, segmenting reservoirs and identifying the region of interest (RoI) around them are essential. In the proposed two-phase workflow, the reservoir is initially segmented using a DL model, and a postprocessing stage is proposed to remove errors, such as floating vegetation in the generated reservoir map. In the second phase, the RoI around the reservoir (RoIaR) is extracted using the proposed image processing techniques. Finally, the man-made objects in the RoIaR are segmented using a DL model. To illustrate the proposed approach, our task of interest is segmenting man-made objects around some of the most important reservoirs in Brazil. Therefore, we trained the proposed workflow using collected Google Earth images of eight reservoirs in Brazil over two different years. The U-Net-based and SegNet-based architectures are trained to segment the reservoirs. To segment man-made objects in the RoIaR, we trained and evaluated four architectures: U-Net, feature pyramid network, LinkNet, and pyramid scene parsing network. Although the collected data are highly diverse (for example, they belong to different states, seasons, resolutions, etc.), we achieved good performances in both phases. The F 1 -score of phase-1 and phase-2 highest performance models in segmenting test sets are 96.53% and 90.32%, respectively. Furthermore, applying the proposed postprocessing to the output of reservoir segmentation improves the precision in all studied reservoirs except two cases. We validated the prepared workflow with a reservoir dataset outside the training reservoirs. The F 1 -scores of the phase-1 segmentation stage, postprocessing stage, and phase-2 segmentation stage are 92.54%, 94.68%, and 88.11%, respectively, which show high generalization ability of the prepared workflow.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Man-made object segmentation around reservoirs by an end-to-end two-phase deep learning-based workflow

Hamidishad,

Cesar

2024

J. Appl. Rem. Sens.

View full text Add to dashboard Cite

show abstract

“…The content described in this chapter is based on the publication Hamidishad and Marcondes Cesar Jr [2019].…”

Section: Dl-based Rs Segmentationmentioning

confidence: 99%

Two-phase methods to segment man-made objects around reservoirs

Hamidishad¹

View full text Add to dashboard Cite

I am also thankful to Professor Jurandir Itizo Yanagihara from PME/Poli for working in collaboration and for permission to use his laboratory. I would like to thank CAPES and FAPESP for their support during my Ph.D.Words can not express my gratitude to my Mother. I am deeply indebted to her and also to my father and sister, who I could not terminate this journey without them. Thanks and apology from the depth of my heart to my little son, Mostafa, for spending the hours that was owned to him on working on my thesis. Finally, my profound thanks go to my spouse, Ali, for his encouragement, understanding, and consistent support.

show abstract

Object-based Method for Identifying New Constructions around Water Reservoirs: Preliminary Results

Cited by 2 publications

References 14 publications

Man-made object segmentation around reservoirs by an end-to-end two-phase deep learning-based workflow

Man-made object segmentation around reservoirs by an end-to-end two-phase deep learning-based workflow

Two-phase methods to segment man-made objects around reservoirs

Contact Info

Product

Resources

About