Geospatial Applications in Inventory of Horticulture Plantations

Ravishankar, H. M.; Trivedi, Shivam; Subramoniam, Suresh; Ahamed, J. Mohammed; Nagashree, T. R.; Manjula, V. B.; Hebbar, Rajat; Jha, C. S.; Dadhwal, V. K.

doi:10.1007/978-3-030-98981-1_12

Cited by 2 publications

(1 citation statement)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…India is one of the largest producers of coconut, with an annual production of 13 billion nuts and 1.78 million hectares of dedicated plantation land. The four southern states of Kerala, Tamil Nadu, Karnataka, and Andhra Pradesh are the major coconut-producing states which account for more than 90% of area and production in the country (Ravishankar et al 2022). The high demand for coconut and its products, such as coconut oil, tender coconut water, coconut bre ropes, and food products, has led to this signi cant production.…”

mentioning

confidence: 99%

“Demarcation and Mapping of a Tree Species Using VHRS Data and Deep learning methods”

Biju,

Trivedi,

Hebbar

et al. 2023

Preprint

Self Cite

View full text Add to dashboard Cite

Coconut holds significant importance in India as a vital source of oil for consumption, particularly due to the high demand for coconut oil. As a result, there has been a rapid expansion of oil coconut tree plantations. Coconut cultivation is widespread, spanning across 90 plus countries, making it one of the majorly grown plantations globally. India, being one of the top producers of coconuts, annually yields 13 billion nuts, utilizing approximately 1.78 million hectares of land for coconut plantations. The primary aim of this study is to assess the accuracy of detecting coconut trees using advanced deep learning techniques applied to high-resolution remote sensing images. The process of tree counting serves two essential purposes. Firstly, it provides an estimate of the number of trees within the plantation, enabling farmers to plan irrigation and fertilization processes more effectively. Secondly, this information is crucial for evaluating the estimated production and determining the value of the field. Deep learning serves as a fundamental framework for accurately detecting trees in high-resolution remote sensing images. Cutting-edge software packages like ArcGIS Pro incorporate deep learning tools that utilize pattern recognition concepts to identify objects in such images. The study reveals the detection of 11,325 coconut trees in the village using deep learning approaches, achieving an accuracy of 87.4%. The findings demonstrate that deep learning techniques offer improved object interpretation. Additionally, the assessment of plantation density in the village suggests that moderately dense coconut plantations occupy a larger area (82.74 hectares) compared to other types of plantations.

show abstract

mentioning

confidence: 99%