COUPLING LIDAR DATA AND LANDSAT 8 OLI IN DELINEATING CORN PLANTATIONS IN BUTUAN CITY, PHILIPPINES Michelle V. Japitana, James Earl D. Cubillas and Arnold G. Apdohan Phil-LiDAR 2.B.14 Project, College of Engineering and Information Technology, Caraga State University, Butuan City, Philippines, Email: michelle.japitana@gmail.com Email: jamesearl_cubillas@yahoo.com Email: arnoldapdohan@gmail.com KEY WORDS: Corn, Landsat, OBIA ABSTRACT: This paper illustrates the classification of corn in the LiDAR data using Landsat indices as features. The Landsat data are calibrated in order to have a noise free reflectance image. Preliminary field in-situ spectral measurements were carried out in order to determine the unique reflectance values of corn in Butuan City, Philippines. In-situ spectral response measurement was done using Ocean OpticsTM VIS-NIR Spectrometer with spectral range from 350 nm to 1000 nm. The computed average reflectance values of corn samples would then be used in order to derive specific values for the Enhance Vegetation Index (EVI) and Green Ratio of corns within the study area. When RGB aerial images are unavailable, classification using LiDAR data only can proved to be futile. However, the Green Ratio and EVI from the transformed Landsat image could be the key features to classify any entities in the image. This paper highlights the classification of a certain class of vegetation objects having a height of 0.5 to 2 meters in the LiDAR nDSM. This class was referred to as class “Medium Elevation” in this paper. Subclasses of this class are class “Corn” and class “Shrub”. Segmentation was based on LiDAR nDSM and Intensity images. Samples were then collected for each of the two classes. A Supervised learning algorithm called SVM (Support Vector Machine) was used to classify entities in the image. The SVM model was constructed using the LiDAR derivatives (nDSM, DSM intensity), Green Ratio, and EVI as features. High overall accuracies were obtained for the classification of corn and shrub in both the train (91.08%) and test site (91.52%). With this, moderate resolution image like Landsat can indeed compliment other remotely sensed data like LiDAR. Specific band ratios derived from the spectral signature of corn, and features like the Green Ratio and Enhanced Vegetation Index can prove to be reliable features in discriminating corn from other vegetation species. 1. INTRODUCTION Corn is the second most important crop in the Philippines. About 14 million Filipinos prefer white corn as their main staple and yellow corn accounts for about 50% of livestock mixed feeds. Some 600,000 farm households depend on corn as a major source of livelihood, in addition to transport services, traders, processors and agricultural input suppliers who directly benefit from corn production, processing, marketing and distribution (www.da.gov.ph, 2012). Since the importance of corn in the region could give livelihood and sort of needs of the people, a detailed map by means of remote sensing is needed to locate the corn species and analyze the location, growth, and its adaptability. There is limited (or none at all) spatial data that can describe or give information on the extent and production trends in the region. Most of the available agricultural crops profiles and statistics are based on interviews that comprise data that were not supported with appropriate spatial measurements. Recently, a new approached called OBIA – Object based image analysis, has been gaining a large amount of attention in the remote sensing community. When methods become contextual they allow for the utilization of “surrounding” information and attributes. The workflows are usually highly customizable or adaptive allowing for the inclusion of human semantics and hierarchical networks (Blaschke, Johansen, & Tiede, 2011). Among the machine learning algorithms, Support Vector Machine has recently received a lot of attention and the number of works utilizing this technique has increased exponentially. The basic concept behind SVM is to search for a balance between the regularization term and the training errors (Chang & Lin, 2001). The most important characteristic is SVM’s ability to generalize well from a limited amount and/or quality of training data. Compared to other methods like artificial neural networks, SVMs can yield comparable accuracy using a much smaller training sample size (Mountrakis, Im, & Ogole, 2009). Recent work of (Japitana, et al., 2014) has developed SVM optimized model, when tested against a different scene resulted to good classification accuracy. Multispectral sensors for remote sensing are designed to capture the reflected energy from various objects on the ground in the visible and the infrared wavelengths of the electromagnetic (EM) spectrum of the sun. Some of the sensor ranges extend all the way into the thermal spectral range, whereas most of the commercial sensors today primarily capture data in the visible and near-infrared regions of the EM spectrum (Navulur, 2007). Moreover, Remote Sensing techniques can lead an accurate inventory by collecting and processing in-situ spectral data (Santillan,