Large scale detailed mapping of dengue vector breeding sites from geo-tagged images - Mahidol Channel มหิดล แชนแนล : ศูนย์รวมความรู้ทั้งศาสตร์และศิลป์ของมหาวิทยาลัยมหิดล
Large scale detailed mapping of dengue vector breeding sites from geo-tagged images

เวลา : 5.05 นาที

Large-Scale detailed mapping of dengue vector breeding sites from geo-tagged images, targeted environmental and ecosystem management remain crucial in control of dengue. However, providing detailed environmental information on a large scale to effectively target dengue control efforts remains a challenge. An important piece of such information is the extent of the presence of potential dengue vector breeding sites, which consist primarily of open containers such as ceramic jars, buckets, old tires, and flowerpots.  In this project we have implemented a pipeline to detect outdoor open containers which constitute potential dengue vector breeding sites from geotagged images and to create highly detailed container density maps at unprecedented scale.

The research team have implemented the approach using Google Street View images which have the advantage of broad coverage and of often being two to three years old which allows correlation analyses of container counts against historical data from manual surveys.  
 Our initial implementation detects containers comprising eight of the most common breeding sites in the images using convolutional neural network transfer learning. Over a test set of images the object recognition algorithm has an accuracy of 0.91 in terms of F-score. Container density counts are generated and displayed on a decision support dashboard. Analyses of the approach have been carried out over three provinces in Thailand.

For the impact, the container counts obtained agree well with container counts from available manual surveys.  Multi-variate linear regression relating densities of the eight container types to larval survey data shows good prediction of larval index values with an R-squared of 0.674. 



YouTube | Mahidol World
Facebook | http://www.facebook.com/mahidolchannel
Mahidol University มหาวิทยาลัยมหิดล | https://www.mahidol.ac.th/th
Website | https://channel.mahidol.ac.th/
Faculty of ICT, Mahidol University | https://www.ict.mahidol.ac.th/en/



Contact Us

มหาวิทยาลัยมหิดล
999 ถนนพุทธมลฑลสาย 4
ต.ศาลายา อ.พุทธมลฑล
จ.นครปฐม 73170
โทร : 0 2849 6000

E-Mail :
info@mahidolchannel.com

Social

Copyright ® 2012
Mahidol University
All rights reserved