Oil Palm Counting and Age Estimation from WorldView-3 Imagery and LiDAR Data Using an Integrated OBIA Height Model and Regression Analysis

Abstract

The current study proposes a new method for oil palm age estimation and counting from Worldview-3 satellite image and light detection and range (LiDAR) airborne imagery. A support vector machine algorithm (SVM) of object-based image analysis (OBIA) was implemented for oil palm counting. The sensitivity analysis was conducted on four SVM kernel types with associated segmentation parameters to obtain the optimal crown coverage delineation. Extracting tree’s crown was integrated with height model and multiregression methods to accurately estimate the age of trees. The multiregression model with multikernel sizes was examined to achieve the most optimized model for age estimation. Applied models were trained and examined over five different oil palm plantations. The results of oil palm counting had an overall accuracy of 98.80%, while the overall accuracy of age estimation showed 84.91%, over all blocks. The relationship between tree’s height and age was significant which supports the polynomial regression function (PRF) model with a 3×3 kernel size for under 10–12-year-old oil palm trees, while exponential regression function (ERF) is more fitted for older trees (i.e., 22 years old). Overall, recent remote sensing dataset and machine learning techniques are useful in monitoring and detecting oil palm plantation to maximize productivity.

An integrated fluvial and flash pluvial model using 2D high-resolution sub-grid and particle swarm optimization-based random forest approaches in GIS

“…5g). This parameter was estimated using an empirical equation called Soil Conservation Service curve number method [37,38]:…”

Assessment of land cover and land use change impact on soil loss in a tropical catchment by using multitemporal SPOT‐5 satellite images and Revised Universal Soil Loss Equation model

“…Pixel-and object-based image classifications are two popular techniques extensively employed to remote-sensing imagery (Blaschke, 2010). With the availability of high-resolution imagery, object-based approaches are recommended for accurate and robust classifications (Corcoran & Winstanley, 2008;Rizeei, Shafri, Mohamoud, Pradhan, & Kalantar, 2018).…”

Urban Mapping Accuracy Enhancement in High-Rise Built-Up Areas Deployed by 3D-Orthorectification Correction from WorldView-3 and LiDAR Imageries

“…Very-high-resolution (VHR) remote sensing images are recent spatial datasets used to build the digital Earth from where the digitized information from earth features can be extracted. They can be broadly utilised in different areas or subjects, such as land use modelling, agriculture, natural hazard, urban planning and forestry [3][4][5]. Such datasets are specifically applied in disaster emergency monitoring (soil erosion and urban flash flooding), monitoring of land cover and settlement monitoring [6][7][8][9][10].…”

“…Thus, the use of VHR image processing methods in numerous applications have persistently received attention [11,12]. Several studies have investigated the multiple applications of recent VHR imagery [3,4,13,14]. Nevertheless, an accurate and operational image processing technique that can identify and retrieve beneficial information from processed imagery automatically and quickly is yet to be achieved [15].…”