DETECTION OF HOUSING AND AGRICULTURE AREAS ON DRY-RIVERBEDS FOR THE - - PowerPoint PPT Presentation

detection of housing and agriculture areas on dry
SMART_READER_LITE
LIVE PREVIEW

DETECTION OF HOUSING AND AGRICULTURE AREAS ON DRY-RIVERBEDS FOR THE - - PowerPoint PPT Presentation

DETECTION OF HOUSING AND AGRICULTURE AREAS ON DRY-RIVERBEDS FOR THE EVALUATION OF RISK BY LANDSLIDES USING LOW-RESOLUTION SATELLITE IMAGERY BASED ON DEEP LEARNING. Brian Cerrn*, Cristopher Bazan*, Alberto Coronado Intelligent Systems


slide-1
SLIDE 1

DETECTION OF HOUSING AND AGRICULTURE AREAS ON DRY-RIVERBEDS FOR THE EVALUATION OF RISK BY LANDSLIDES USING LOW-RESOLUTION SATELLITE IMAGERY BASED ON DEEP LEARNING.

Intelligent Systems Laboratory, Universidad Nacional de Ingeniería

Brian Cerrón*, Cristopher Bazan*, Alberto Coronado

slide-2
SLIDE 2

Motivation

Img s/c: http://www.minedu.gob.pe/fenomeno-el-nino/, https://www.bbc.com/mundo/noticiahttps://www.bbc.com/mundo/noticias-america-latina-39259721s-america-latina-39259721

El Niño

slide-3
SLIDE 3

Urban planning and Land Use

Img s/c: Image from Villacorta Chambi et al. Peligros geologicos en el ´ area de Lima Metropolitana y la regi ´ on Callao N ´

  • 59(Lima:Instituto Geologico, Minero y Metal ´ urgico,2015),

http://verdenoticias.org/index.php/blog-noticias-cambio-climatico/1937-peru-entre-huaicos-y-sequias

slide-4
SLIDE 4

Workflow

Perspective Task 1 Task 2

* Dry riverbed * Inhabited land * Agriculture land * Residential * Human settlement * Industrial

Residual U-Net Unet Overlap of results

slide-5
SLIDE 5

Dataset

  • RGB Images of 5000x5000 pixels taken by

RapidEye satellite (Planet Labs)

  • Each image has been sliced in 100 chips

with overlapping Task 1:

slide-6
SLIDE 6

Task 2:

slide-7
SLIDE 7

Training and Results

Unet Deep Unet Res Unet Adadelta Adam (0.001) NAdam Adam (0.0005)

slide-8
SLIDE 8

Experimental results for Task 2 Experimental results for Task 1

slide-9
SLIDE 9

Conclusions and future work

Housing areas lying on dry riverbeds with significant potential risk are shown as low susceptibility areas by the official susceptibility map Apply post processing techniques such as Jaccard Index. Explore other architectures :

  • Mask R-CNN
  • Yolact