Ted: Tree delineation with reduced dimensions using entropy and deep learning

RN Anjani, CH Sarvani, K Kalyan Deep, P Aravinda Kumar, Sitiraju Srinivasa Rao
Proceedings of the 15th Asian Conference on Machine Learning, PMLR 222:44-57, 2024.

Abstract

Trees play a very important role in maintaining the ecosystem. To automate the process of extracting trees from Remote Sensing data and counting thereby, we have used Cartosat-2S merged products @ 0.6m as input. Vegetation indices such as NDVI, and EVI can retrieve the Vegetation class which contains trees and their look-alikes (such as grass, fields, and shrubs) having the same spectral signatures \em{i.e.}, high reflectance in NIR band, and high absorption in Red band. Extraction of only Trees is not possible with these indices. In this paper we present a novel method for tree delineation from its look-alikes using AIML, concentrating more on preparation of input datasets efficiently. Based on the Spectral Separability analysis, only Red and NIR bands from the satellite imagery are utilized in the proposed method to separate Vegetation from the background classes (such as water, bare soil, terrain, and built-up). In addition to the two bands from satellite imagery entropy layer is computed from the NIR band and utilized as the third band to delineate trees from their look-alikes. Deep Neural Networks have the capability of learning complex patterns that can separate trees and their look-alikes. However, the performance is boosted when the entropy layer is added to the input image. The proposed method showed better performance when utilizing 3 bands Red, NIR, and Entropy bands compared to 4 bands i.e. Red, Green, Blue, and NIR bands. The proposed method obtains a precision of 96%, a recall of 90%, and an F1-score of 93% even with a relatively smaller training dataset. The study is performed on the data collected from various locations of the Indian state Rajasthan.

Cite this Paper

BibTeX
@InProceedings{pmlr-v222-anjani24a, title = {{Ted}: {T}ree delineation with reduced dimensions using entropy and deep learning}, author = {Anjani, RN and Sarvani, CH and Kalyan Deep, K and Aravinda Kumar, P and Srinivasa Rao, Sitiraju}, booktitle = {Proceedings of the 15th Asian Conference on Machine Learning}, pages = {44--57}, year = {2024}, editor = {Yanıkoğlu, Berrin and Buntine, Wray}, volume = {222}, series = {Proceedings of Machine Learning Research}, month = {11--14 Nov}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v222/anjani24a/anjani24a.pdf}, url = {https://proceedings.mlr.press/v222/anjani24a.html}, abstract = {Trees play a very important role in maintaining the ecosystem. To automate the process of extracting trees from Remote Sensing data and counting thereby, we have used Cartosat-2S merged products @ 0.6m as input. Vegetation indices such as NDVI, and EVI can retrieve the Vegetation class which contains trees and their look-alikes (such as grass, fields, and shrubs) having the same spectral signatures \em{i.e.}, high reflectance in NIR band, and high absorption in Red band. Extraction of only Trees is not possible with these indices. In this paper we present a novel method for tree delineation from its look-alikes using AIML, concentrating more on preparation of input datasets efficiently. Based on the Spectral Separability analysis, only Red and NIR bands from the satellite imagery are utilized in the proposed method to separate Vegetation from the background classes (such as water, bare soil, terrain, and built-up). In addition to the two bands from satellite imagery entropy layer is computed from the NIR band and utilized as the third band to delineate trees from their look-alikes. Deep Neural Networks have the capability of learning complex patterns that can separate trees and their look-alikes. However, the performance is boosted when the entropy layer is added to the input image. The proposed method showed better performance when utilizing 3 bands Red, NIR, and Entropy bands compared to 4 bands i.e. Red, Green, Blue, and NIR bands. The proposed method obtains a precision of 96%, a recall of 90%, and an F1-score of 93% even with a relatively smaller training dataset. The study is performed on the data collected from various locations of the Indian state Rajasthan.} }
Endnote
%0 Conference Paper %T Ted: Tree delineation with reduced dimensions using entropy and deep learning %A RN Anjani %A CH Sarvani %A K Kalyan Deep %A P Aravinda Kumar %A Sitiraju Srinivasa Rao %B Proceedings of the 15th Asian Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2024 %E Berrin Yanıkoğlu %E Wray Buntine %F pmlr-v222-anjani24a %I PMLR %P 44--57 %U https://proceedings.mlr.press/v222/anjani24a.html %V 222 %X Trees play a very important role in maintaining the ecosystem. To automate the process of extracting trees from Remote Sensing data and counting thereby, we have used Cartosat-2S merged products @ 0.6m as input. Vegetation indices such as NDVI, and EVI can retrieve the Vegetation class which contains trees and their look-alikes (such as grass, fields, and shrubs) having the same spectral signatures \em{i.e.}, high reflectance in NIR band, and high absorption in Red band. Extraction of only Trees is not possible with these indices. In this paper we present a novel method for tree delineation from its look-alikes using AIML, concentrating more on preparation of input datasets efficiently. Based on the Spectral Separability analysis, only Red and NIR bands from the satellite imagery are utilized in the proposed method to separate Vegetation from the background classes (such as water, bare soil, terrain, and built-up). In addition to the two bands from satellite imagery entropy layer is computed from the NIR band and utilized as the third band to delineate trees from their look-alikes. Deep Neural Networks have the capability of learning complex patterns that can separate trees and their look-alikes. However, the performance is boosted when the entropy layer is added to the input image. The proposed method showed better performance when utilizing 3 bands Red, NIR, and Entropy bands compared to 4 bands i.e. Red, Green, Blue, and NIR bands. The proposed method obtains a precision of 96%, a recall of 90%, and an F1-score of 93% even with a relatively smaller training dataset. The study is performed on the data collected from various locations of the Indian state Rajasthan.
APA
Anjani, R., Sarvani, C., Kalyan Deep, K., Aravinda Kumar, P. & Srinivasa Rao, S.. (2024). Ted: Tree delineation with reduced dimensions using entropy and deep learning. Proceedings of the 15th Asian Conference on Machine Learning, in Proceedings of Machine Learning Research 222:44-57 Available from https://proceedings.mlr.press/v222/anjani24a.html.

Related Material