MangoGAN: a general adversarial network-based deep learning architecture for mango tree crown detection

Kestur, R and Kulkarni, A and Bhaskar, R and Sreenivasa, P and Dhanya Sri, D and Choudhary, A and Balaji Prabhu, BV and Anand, G and Narasipura, O (2022) MangoGAN: a general adversarial network-based deep learning architecture for mango tree crown detection. In: Journal of Applied Remote Sensing, 16 (1).

PDF jou_app_rem_sen_16-1_2022 .pdf - Published Version Restricted to Registered users only Download (6MB) | Request a copy

Abstract

We present MangoGAN, a general adversarial network (GAN)-based deep learning semantic segmentation model for the detection of mango tree crowns in remotely sensed aerial images. The aerial images are acquired by low-altitude remote sensing carried out using a quadrotor unmanned aerial vehicle in a mango orchard. Aerial images are acquired with a vision spectrum optical sensor, also popularly known as RGB images as the payload. MangoGAN is trained on 1430 images patches of size 240 � 240 pixels. The testing was carried out on 160 images. Results are analyzed using the precision, recall, F1 parameters derived from contingency matrix and by visualization using Gradcam method. The performance of the MangoGAN is compared with peer architectures trained on the same data. MangoGAN outperforms its peer architectures © 2022 Society of Photo-Optical Instrumentation Engineers (SPIE).

Item Type:	Journal Article
Publication:	Journal of Applied Remote Sensing
Publisher:	SPIE
Additional Information:	The copyright for this article belongs to SPIE
Keywords:	Antennas; Deep learning; Forestry; Image acquisition; Network architecture; Remote sensing; Semantic Web; Semantics, Adversarial networks; Aerial images; Deep learning; General adversarial network; Low altitude remote sensing; Low altitudes; Remote-sensing; Semantic segmentation; Tree crown detection; Tree crowns, Semantic Segmentation
Department/Centre:	Division of Mechanical Sciences > Aerospace Engineering(Formerly Aeronautical Engineering)
Date Deposited:	19 May 2022 05:58
Last Modified:	19 May 2022 05:58
URI:	https://eprints.iisc.ac.in/id/eprint/72020

Actions (login required)

View Item