English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

This work presents a method for semantic segmentation of mango trees in highresolution aerial imagery, and, a novel method for individual crown detectionof mango trees using segmentation output. Mango Tree Net, a fully convolutionalneural network (FCN), is trained using supervised learning to perform semanticsegmentation of mango trees in imagery acquired using an unmanned aerialvehicle (UAV). The proposed network is retrained to separatetouching/overlapping tree crowns in segmentation output. Contour basedconnected object detection is performed on the segmentation output fromretrained network. Bounding boxes are drawn on the original images usingcoordinates of connected objects to achieve individual crown detection. Thetraining dataset consists of 8,824 image patches of size 240 x 240. Theapproach is tested for performance on segmentation and individual crowndetection tasks using test datasets containing 36 and 4 images respectively.The performance is analyzed using standard metrics precision, recall, f1-scoreand accuracy. Results obtained demonstrate the robustness of the proposedmethods despite variations in factors such as scale, occlusion, lightingconditions and surrounding vegetation.

Mango Tree Net -- A fully convolutional network for semantic segmentation and individual crown detection of mango trees