Object oriented classification of high resolution data for inventory of horticultural crops

Abstract

ABSTRACT:High resolution satellite images are associated with large variance and thus, per pixel classifiers often result in poor accuracy especially in delineation of horticultural crops. In this context, object oriented techniques are powerful and promising methods for classification. In the present study, a semi-automatic object oriented feature extraction model has been used for delineation of horticultural fruit and plantation crops using Erdas Objective Imagine. Multi-resolution data from Resourcesat LISS-IV and Cartosat-1 have been used as source data in the feature extraction model. Spectral and textural information along with NDVI were used as inputs for generation of Spectral Feature Probability (SFP) layers using sample training pixels. The SFP layers were then converted into raster objects using threshold and clump function resulting in pixel probability layer. A set of raster and vector operators was employed in the subsequent steps for generating thematic layer in the vector format. This semi-automatic feature extraction model was employed for classification of major fruit and plantations crops viz., mango, banana, citrus, coffee and coconut grown under different agro-climatic conditions. In general, the classification accuracy of about 75-80 per cent was achieved for these crops using object based classification alone and the same was further improved using minimal visual editing of misclassified areas. A comparison of on-screen visual interpretation with object oriented approach showed good agreement. It was observed that old and mature plantations were classified more accurately while young and recently planted ones (3years or less) showed poor classification accuracy due to mixed spectral signature, wider spacing and poor stands of plantations. The results indicated the potential use of object oriented approach for classification of high resolution data for delineation of horticultural fruit and plantation crops. The present methodology is applicable at local levels and future development is focused on up-scaling the methodology for generation of fruit and plantation crop maps at regional and national level which is important for creation of database for overall horticultural crop development.

Drought and Human Impacts on Land Use and Land Cover Change in a Vietnamese Coastal Area

“…To classify the image data, we applied object-based image classification method, which is commonly applied for high-resolution images [20,21]. This method is based on distinctive characteristics of each object, such as color, shape, size, and relationships to others to define LULC [22][23][24]. As mentioned in the Introduction, there are two categorized systems used to classify LULC types at two detailed levels, Table 2 describes those two systems and identities of land types.…”

Crop Inventory of Orchard Crops in India Using Remotely Sensed Data

“…Object based classification has an advantage that treat whole orchard field as a single segment that overcome the limitation of the pixel based classification that treats soil exposed in space between to two plant canopies as separate class (Hebbar et al 2014, Roy et al 2018. The methodology framework and step-wise flowchart for object based classification is as shown in Figure 3.…”

Comparison of citrus orchard inventory using LISS-III and LISS-IV data

“…High resolution imagery has substantial impact in finding or mapping horticulture crops. According to a study delineated citrus orchard area using object based classification over LISS-IV and Cartosat merged product with 80-90 % accuracy [10]. Also Aerial photography and vediography have been found useful for tree inventory in the Merritt Island National Wildlife Refuge citrus groves [11].…”