International Journal of Advanced Trends in Computer Science and Engineering.
World Academy of Research in Science and Engineering.
Vol. 8.
2019.
P. 2236-2239
Forest Areas Segmentation on Aerial Images by Deep Learning
The aim of this research is to create a deep learning algorithm for automated forest areas segmentation on high-resolution aerial images. Loss values and Dice coefficient, which compares results of algorithms with real masks, was used to measure the quality of developed model. On the whole this paper demonstrates how convolutional neural network implemented on modern GPUs can be applied for the detection of forests on satellite images. © 2019 IEEE.
Authors
Khryashchev V.1
,
Pavlov V.1
,
Ostrovskaya A.
2
,
Larionov R.1
Conference proceedings
Publisher
Institute of Electrical and Electronics Engineers Inc.
Language
English
Status
Published
Number
8884406
Year
2019
Organizations
- 1 P.G. Demidov Yaroslavl State University, Yaroslavl, Russian Federation
- 2 People's Friendship University of Russia, Moscow, Russian Federation
Keywords
aerial images; computer vision; forest area detection; image segmentation
Date of creation
24.12.2019
Date of change
24.12.2019
Share
Other records
MODIFICATION OF U-NET NEURAL NETWORK IN THE TASK OF MULTICHANNEL SATELLITE IMAGES SEGMENTATION
Article
2019 IEEE East-West Design and Test Symposium, EWDTS 2019.
Institute of Electrical and Electronics Engineers Inc..
2019.