Connie Ko

York University · Department of Geography

The goal for our paper is to classify tree genera using airborne Light Detection and Ranging (LiDAR) data with Convolution Neural Network (CNN) – Multi-task Network (MTN) implementation. Unlike Single-task Network (STN) where only one task is assigned to the learning outcome, MTN is a deep learning architect for learning a main task (classification...

This chapter provides an introduction and overview of using light detection and ranging (LiDAR) in forest applications. The first section explains the principles and basic terminology for LiDAR and introduces the use of LiDAR on three different platforms (spaceborne, airborne, and terrestrial) for forest applications. The second section discusses a...

Intensity values from LiDAR data refer to the reflected energy recorded from the target, this relative measurement can be useful for object identification or feature extraction. Usually, this value is recorded by the manufacturer and scaled to integer values depending on the number of bits used to store values. However, this value needs to be corre...

Recent research into improving the effectiveness of forest inventory management using airborne LiDAR data has focused on developing advanced theories in data analytics. Furthermore, supervised learning as a predictive model for classifying tree genera (and species, where possible) has been gaining popularity in order to minimize this labor-intensiv...

This paper presents a hybrid ensemble method that is comprised of a sequential and a parallel architecture for the classification of tree genus using LiDAR (Light Detection and Ranging) data. The two classifiers use different sets of features: (1) features derived from geometric information, and (2) features derived from vertical profiles using Ran...

The detection of unknown class in a classification system is essential and often a common problem. This situation arises when the number of classes in the training sample is less than the number of classes in the population. For supervised classifications, training samples are required and the selection (or method of selection) of training sample (...

Categorical recognition of a tree's genus is known to be valuable information for the effective management of forest inventories. In this paper, we present a method for learning a discriminative model using Random Forests to classify individual trees into three genera: pine, poplar, and maple. We believe that both internal and external geometric ch...

Maps of tree genera are useful in applications including forest inventory, urban planning, and the maintenance of utility transmission line infrastructure. We present a case study of using high density airborne LiDAR data for tree genera mapping along the right of way (ROW) of a utility transmission line corridor. Our goal was to identify single tr...

We present a sensitivity analysis of the effect that LiDAR point density has on tree genus classification. Tree genus is classified by using two sets of features within the Random Forest classifier; the two sets of features are 1) descriptors related to the geometric information of the trees and 2) descriptors related to the vertical profile of LiD...

We present a comparative study between two different approaches for tree genera classification using descriptors derived from tree geometry and those derived from the vertical profile analysis of LiDAR point data. The different methods provide two perspectives for processing LiDAR point clouds for tree genera identification. The geometric perspecti...

Maps of tree genera are useful in applications including forest inventory, urban planning, and the maintenance of utility transmission line infrastructure. We present a case study of using high density airborne LiDAR data for tree genera mapping along the right of way (ROW) of a utility transmission line corridor. Our goal was to identify single tr...

Los mapas de géneros de árboles son útiles para el inventario forestal, planificación urbana y el mantenimiento de la infraestructura de líneas de transmisión. Se presenta un estudio de caso de uso de datos LiDAR de alta densidad para el mapeo de géneros de árboles a lo largo del derecho de paso (ROW) de un corredor de línea de transmisión. El obje...

We present a methodology to classify individual trees into a given list of species obtained by field surveying using airborne LiDAR data; targeted species include birch, maple, oak, poplar, white pine and jack pine at a study site northeast of Sault Ste Marie, Ontario, Canada. The average density of the LiDAR data is 40 points per m 2 and was acqui...

This project has two main purposes; the first is to perform deciduous-coniferous classification for 65 trees by using the leaf-on single flight LiDAR data. It was done by looking at the geometrical properties of the crown shapes (spherical, conical or cylindrical), these shapes were developed by a rule-driven method Lindenmayer Systems (L systems)....

This paper introduces two parsimonious models for predicting runoff for ungauged basins from the observed river flow data in gauged basins and precipitation data from rain gauging stations in the same area. The models assume the runoff is related to the precipitation subject to variance of drainage basins. The runoff can be modeled as a function of...

The spatial pattern of storm runoff volume is of interest in many environmental concerns and storm runoff is an important component in the hydrologic cycle because of its relationship to issues such as flooding and water quality. The isolation of the groundwater component allows the net effect of meteorology to stream flow rate. Hence, the time lag...

The production of storm runoff volume is an integrated results from many environmental processes and is usually taken into consideration when making decisions related landscape planning and water management projects, especially waste treatment. It also affects the ecological systems, pollutant loads transportation, flooding and many other environme...

The spatial pattern of storm runoff volume is of interest in many environmental concerns and storm runoff is an important component in the hydrologic cycle because of its relationship to issues such as flooding and water quality. The isolation of the groundwater component allows the net effect of meteorology to stream flow rate. Hence, the time lag...

Typescript. Thesis (M.Sc.)--York University, 2004. Graduate Programme in Includes bibliographical references (leaves 152-169). Microfiche. System requirements for Internet version: Adobe Acrobat reader.