Browsing by Author "Yuen, P."
Now showing 1 - 5 of 5
Results Per Page
Sort Options
Item Open Access Classification techniques for hyperspectral remote sensing(2011-09-19) Kam, F.; Yuen, P.This study concerns with classification techniques in high dimensional space such as that of Hyperspectral Imaging (HSI) data sets, with objectives of understanding the strength and weakness of various classifiers and at the same time to study how their performances can be assessed particularly when there is an absence of ground truth target map in the data set. The thesis summaries the work that carried out during the course of this study and it encompasses a brief survey of machine learning and classification theories, an outline of the HSI instrumentations, data sets that collected in the study and classification analysis. It is found that the supervised classifiers such as the Maximum Likelihood (QD) and the Mahalanobis Distance (FD) classifiers, especially when they are coupled with techniques like Regularised Discriminant Analysis (RDA) or leave-one-out covariance estimations (LOOC), have demonstrated excellent performances comparable to that of the more complicated and computational costly classifiers like the Support Vector Machine (SVM). This work has also revealed that separability measures such as the Total Transformed Divergence (TTD) and Total Jeffries-Matusita Distance (TJM) can be an invaluable method for assessing the goodness of classification in principle. However, the present methods for the evaluation of the separability measures are insufficient for achieving this goal and further work in this area is needed. This study has also confirmed the effectiveness for using RDA and LOOC techniques for a better estimation of the covariance when the sample size is small, ie when the sample size per class to band ratio is less than 100. Through team work this study has contributed partially a number of publications in the area of hyperspectral imaging and machine visions.Item Open Access Enhanced target detection in CCTV network system using colour constancy(2016-06-02) Soori, U.; Yuen, P.The focus of this research is to study how targets can be more faithfully detected in a multi-camera CCTV network system using spectral feature for the detection. The objective of the work is to develop colour constancy (CC) methodology to help maintain the spectral feature of the scene into a constant stable state irrespective of variable illuminations and camera calibration issues. Unlike previous work in the field of target detection, two versions of CC algorithms have been developed during the course of this work which are capable to maintain colour constancy for every image pixel in the scene: 1) a method termed as Enhanced Luminance Reflectance CC (ELRCC) which consists of a pixel-wise sigmoid function for an adaptive dynamic range compression, 2) Enhanced Target Detection and Recognition Colour Constancy (ETDCC) algorithm which employs a bidirectional pixel-wise non-linear transfer PWNLTF function, a centre-surround luminance enhancement and a Grey Edge white balancing routine. The effectiveness of target detections for all developed CC algorithms have been validated using multi-camera ‘Imagery Library for Intelligent Detection Systems’ (iLIDS), ‘Performance Evaluation of Tracking and Surveillance’ (PETS) and ‘Ground Truth Colour Chart’ (GTCC) datasets. It is shown that the developed CC algorithms have enhanced target detection efficiency by over 175% compared with that without CC enhancement. The contribution of this research has been one journal paper published in the Optical Engineering together with 3 conference papers in the subject of research.Item Open Access Hyperspectral imaging for the remote sensing of blood oxygenation and emotions(2012-08-22) Chen, T.; Yuen, P.This PhD project is a basic research and it concerns with how human’s physiological features, such as tissue oxygen saturation (StO2), can be captured from a stand-off distance and then to understand how this remotely acquired physiological feature can be deployed for biomedical and other applications. This work utilises Hyperspectral Imaging (HSI) within the diffuse optical scattering framework, to assess the StO2 in a contactless remote sensing manner. The assessment involves a detailed investigation about the wavelength dependence of diffuse optical scattering from the skin as well as body tissues, under various forms of optical absorption models. It is concluded that the threechromophore extended Beer Lambert Law model is better suited for assessing the palm and facial tissue oxygenations, especially when spectral data in the wavelengths region of [516-580]nm is used for the analysis. A first attempt of using the facial StO2 to detect and to classify people’s emotional state is initiated in this project. The objective of this work is to understand how strong emotions, such as distress that caused by mental or physical stimulations, can be detected using physiological feature such as StO2. Based on data collected from ~20 participants, it is found that the forehead StO2 is elevated upon the onset of strong emotions that triggered by mental stimulation. The StO2 pattern in the facial region upon strong emotions that are initiated by physical stimulations is quite complicated, and further work is needed for a better understanding of the interplays between bodily physique, individual’s health condition and blood transfusion control mechanism. Most of this work has already been published and future research to follow up when the author returns back to China is highlighted.Item Open Access Illumination invariance and shadow compensation on hyperspectral images(2014-11-07) Ibrahim, I.; Yuen, P.To obtain intrinsic reflectance of the scene by hyperspectral imaging systems has been a scientific and engineering challenge. Factors such as illumination variations, atmospheric effects and viewing geometries are common artefacts which modulate the way of light reflections from the object into the sensor and that they are needed to be corrected. Some of these factors induce highly scattered and diffuse irradiance which can artificially modify the intrinsic spectral reflectance of the surface, such as that in the shadows. This research is attempted to compensate the shadows in the hyperspectral imagery. In this study, three methods known as the Diffuse Irradiance Compensation (DIC), Linear Regression (LR) and spectro-polarimetry technique (SP) have been proposed to compensate the shadow effect. These methods have various degrees of shadow compensation capabilities, and their pros and cons are elucidated within the context of their classification performances over several data sets recorded within and outside of the laboratory. The spectro-polarimetry (SP) technique has been found to be the most versatile and powerful method for shadow compensation, and it has achieved over 90% of classification accuracy for the scenes with ~30% of shadow areas.Item Open Access Remote sensing of strong emotions using electro-optical imaging technique(2013-10-08) Hong, K.; Yuen, P.This thesis reports a summary of the PhD programme for the assessment of person‘s emotional anxiety using Electro-optical technology. The thesis focuses mainly on the understanding of fundamental properties of physiological responses to emotional anxiety and how they can be captured by using Electro-optical (EO) imaging methods such as hyperspectral imaging (HSI) and thermal imaging (TI) techniques. The thesis summarises three main areas of work that have been undertaken by the author in the programme: (a) Experimental set up including HSI system and data acquisition software design and implementation, (b) fundamental understanding of physiological responses to emotional anxiety from the EO perspective and (c) the development of a novel remote sensing technique for the assessment of emotions without the requirement of base line information. One of our main results is to provide evidence to prove that the mean temperature in the periorbital region remains the same within 0.2°C during emotional anxiety. Furthermore, we have shown that it is the high temperature pixels within the periorbital, which increases in numbers by a huge amount after 2 minutes of the onset of anxiety. We have also developed techniques to allow the assessment anxiety without the need of base line information. The method has been tested using a sample size of about 40 subjects, and achieved promising result. Technologies for the remote sensing of heart beat rate has been in great demand, this study also involves the development of heart beat detection using TI system. Moreover, we have also attempted for the first time to sense glucose concentration from the blood sample in-vivo using HSI technique remotely.