Browsing by Author "James, David B."
Now showing 1 - 9 of 9
Results Per Page
Sort Options
Item Open Access Application of spectral and spatial indices for specific class identification in Airborne Prism EXperiment (APEX) imaging spectrometer data for improved land cover classification(SPIE, 2016-09) Kallepalli, Akhil; Kumar, Arvind; Khoshelham, K.; James, David B.Hyperspectral remote sensing's ability to capture spectral information of targets in very narrow bandwidths gives rise to many intrinsic applications. However, the major limiting disadvantage to its applicability is its dimensionality, known as the Hughes Phenomenon. Traditional classification and image processing approaches fail to process data along many contiguous bands due to inadequate training samples. Another challenge of successful classification is to deal with the real world scenario of mixed pixels i.e. presence of more than one class within a single pixel. An attempt has been made to deal with the problems of dimensionality and mixed pixels, with an objective to improve the accuracy of class identification. In this paper, we discuss the application of indices to cope with the disadvantage of the dimensionality of the Airborne Prism EXperiment (APEX) hyperspectral Open Science Dataset (OSD) and to improve the classification accuracy using the Possibilistic c–Means (PCM) algorithm. This was used for the formulation of spectral and spatial indices to describe the information in the dataset in a lesser dimensionality. This reduced dimensionality is used for classification, attempting to improve the accuracy of determination of specific classes. Spectral indices are compiled from the spectral signatures of the target and spatial indices have been defined using texture analysis over defined neighbourhoods. The classification of 20 classes of varying spatial distributions was considered in order to evaluate the applicability of spectral and spatial indices in the extraction of specific class information. The classification of the dataset was performed in two stages; spectral and a combination of spectral and spatial indices individually as input for the PCM classifier. In addition to the reduction of entropy, while considering a spectral-spatial indices approach, an overall classification accuracy of 80.50% was achieved, against 65% (spectral indices only) and 59.50% (optimally determined principal componentsItem Open Access CHIMES: An enhanced end-to-end Cranfield hyperspectral image modelling and evaluation system(2020-02) Zahidi, Usman A.; Yuen, Peter W. T.; James, David B.Hyperspectral remote sensing enables establishing semantics from an image by providing spectral details used for differentiating materials. The airborne/satellite setup for remote sensing are typically expensive in terms of time and cost-effectiveness. It is therefore important to predict performance of such systems as a precursor. Hyperspectral scene simulation is a technique which allows the detailed spatial and spectral information of a natural scene to be reconstructed without the need for expensive and time-consuming airborne/spaceborne image acquisition systems. It helps in predicting the potential performance of airborne/satellite systems, moreover, it enables varying atmospheric conditions, estimating degradation in sensor performance to provide better uncertainty analysis and traceability, performance analysis of data processing algorithms and counter-measures/camouflage assessment in military applications. Digital Imaging Remote Sensing Image Generation (DIRSIG) developed by Rochester Institute of Technology and Camoflauge Electro-Optic Simulator (CameoSim) by Lockheed Martin are the two earliest research and commercial products, respectively, that incorporate hyperspectral rendering for accurate physicsbased radiance estimation. Although CameoSim is a well-established Scene simulator, however it does not support volumetric scattering and localised adjacency model. DIRSIG has provided support form these features in newly developed version called DIRSIG5. Due to export control restriction it is typically not possible to access these simulators, hence motivates development of inhouse scene simulator. This thesis summarises the research which constitutes part of the deliverable under the DSTL R-Cloud project for the establishment of an in-house HSI scene simulator, which is known as the Cranfield Hyperspectral Image Modelling and Evaluation System (CHIMES). CHIMES is a physicsbased rendering enabled simulator and the main concept follows directly the radiative transfer (RT) big equation, with some components adopted from DIRSIG and CameoSim etc. The goal of the present research has been set and the work has been progressed in the following manner: • The establishment of CHIMES from scratch; • Validation of CHIMES through direct comparison with commercial-off-the-shelf (COTS) simulator such as CameoSim (CS); • Enhancement of CHIMES over the COTS simulator (e.g. CS) to include automatic in-scene atmospheric parametrisation, localised adjacency-effect model and volumetric scattering to achieve a more realistic scene simulation particularly for the rugged terrain; • To propose methods on how difficult issues such as shadows can be mitigated in scene simulation. This thesis summarises the work performed as according to the above 4 objectives with main results as follows: • CHIMES has been shown to reproduce the scene simulation performed by a COTS simulator (e.g. CameoSim) under various atmospheric conditions. • An automatic atmosphere parameterisation search algorithm has been shown to be effective to allow the simulation of the scene without the need of repeated trial and error atmospheric parameter adjustments. • Two adjacency models: the Background One-Spectra Adjacency Effect Model (BOAEM) and the Texture-Spectra Incorporated Adjacency Effect Model (TIAEM) have been developed under this work. The BOAEM is somewhat similar to that adopted in CS with a distinctive feature of volumetric scattering, however, the TIAEM is a terrain dependence adjacency which is much more sophisticated. It has been shown that at high altitude scene, TIAEM performs better than the BOAEM by 6.0% and by 10.0% better than CameoSim particularly in the 2D geometric simulation, in terms of `1-norm error. In the lower altitude scene, BOAEM performs better than both TIAEM and CameoSim by 22.0% and 16%. In a 3D scene (i.e. terrain with Digital Elevation Model (DEM)) with sensor at lower altitude CameoSim error raises by 5 times compared to GT. BOAEM still performs better than TIAEM by a similar 22% `1-norm error. • A means for assessing the shadowed pixels of the scene has been proposed and the validation of the model requires more comprehensive ground truth (GT) data which will be performed in the future research. Most of the above results have been published in three journal papers as part of the contributions towards the HSI research communityItem Open Access Deep learning for automatic target recognition with real and synthetic infrared maritime imagery(SPIE, 2020-09-20) Westlake, Samuel T.; Volonakis, Timothy N.; Jackman, James; James, David B.; Sherriff, AndySupervised deep learning algorithms are re-defining the state-of-the-art for object detection and classification. However, training these algorithms requires extensive datasets that are typically expensive and time-consuming to collect. In the field of defence and security, this can become impractical when data is of a sensitive nature, such as infrared imagery of military vessels. Consequently, algorithm development and training are often conducted in synthetic environments, but this brings into question the generalisability of the solution to real world data. In this paper we investigate training deep learning algorithms for infrared automatic target recognition without using real-world infrared data. A large synthetic dataset of infrared images of maritime vessels in the long wave infrared waveband was generated using target-missile engagement simulation software and ten high-fidelity computer-aided design models. Multiple approaches to training a YOLOv3 architecture were explored and subsequently evaluated using a video sequence of real-world infrared data. Experiments demonstrated that supplementing the training data with a small sample of semi-labelled pseudo-IR imagery caused a marked improvement in performance. Despite the absence of real infrared training data, high average precision and recall scores of 99% and 93% respectively were achieved on our real-world test data. To further the development and benchmarking of automatic target recognition algorithms this paper also contributes our dataset of photo-realistic synthetic infrared images.Item Open Access Digital shoreline analysis system-based change detection along the highly eroding Krishna–Godavari delta front(SPIE, 2017-08-24) Kallepalli, Akhil; Kakani, N. R.; James, David B.; Richardson, Mark A.Coastal regions are highly vulnerable to rising sea levels due to global warming. Previous Intergovernmental Panel on Climate Change (2013) predictions of 26 to 82 cm global sea level rise are now considered conservative. Subsequent investigations predict much higher levels which would displace 10% of the world’s population living less than 10 m above sea level. Remote sensing and GIS technologies form the mainstay of models on coastal retreat and inundation to future sea-level rise. This study estimates the varying trends along the Krishna–Godavari (K–G) delta region. The rate of shoreline shift along the 330-km long K–G delta coast was estimated using satellite images between 1977 and 2008. With reference to a selected baseline from along an inland position, end point rate and net shoreline movement were calculated using a GIS-based digital shoreline analysis system. The results indicated a net loss of about 42.1 km 2 area during this 31-year period, which is in agreement with previous literature. Considering the nature of landforms and EPR, the future hazard line (or coastline) is predicted for the area; the predication indicates a net erosion of about 57.6 km 2 along the K–G delta coast by 2050 AD.Item Open Access Implications of spectral and spatial features to improve the identification of specific classes(SPIE, 2019-01-14) Kallepalli, Akhil; Kumar, Anil; Khoshelham, Kourosh; James, David B.; Richardson, Mark A.Dimensionality is one of the greatest challenges when deciphering hyperspectral imaging data. Although the multiband nature of the data is beneficial, algorithms are faced with a high computational load and statistical incompatibility due to the insufficient number of training samples. This is a hurdle to downstream applications. The combination of dimensionality and the real-world scenario of mixed pixels makes the identification and classification of imaging data challenging. Here, we address the complications of dimensionality using specific spectral indices from band combinations and spatial indices from texture measures for classification to better identify the classes. We classified spectral and combined spatial–spectral data and calculated measures of accuracy and entropy. A reduction in entropy and an overall accuracy of 80.50% was achieved when using the spectral–spatial input, compared with 65% for the spectral indices alone and 59.50% for the optimally determined principal components.Item Open Access Multi-modal assessment of light transport through biological tissue(2020-02) Kallepalli, Akhil; James, David B.; Richardson, Mark A.The advent of biomedical optics and understanding of light transport through tissues has gathered enormous popularity since the works of Britton Chance, Steven Jacques and Valery Tuchin. Understanding light transport has allowed diagnoses, and in vivo and noncontact assessment of tissue. This thesis provides an interdisciplinary approach to using various modalities for optically interacting with biological tissue. The methods focus on lowcost, non-contact, non-invasive and/or simple methods to assess biological tissue. Ultrasound imaging, which is a key radiological imaging tool in today’s hospitals, is combined with powerful ray tracing tools to provide a quantitative assessment of tissue. The thesis discusses four individual studies, linked through either their methods or applications. Specifically, the biological tissues that light interacts within this thesis are skin and its layers, muscle, bone and blood. Skin-safe lasers are used in the studies to interact with participants through simulations and experiments. Through the course of this research, I investigate the optical compatibility of human skin with synthetic skin samples known as human skin equivalents (HSEs)1 . The result is a novel assessment combining tissue engineering and biomedical optics. Secondly, a simulated analysis of light interaction with a two-layer model was subsequently analysed in a study to look for anaemic blood condition markers in the reflectance and fluence of photons. This study resulted in a unique assessment of light transport through two-layer models. The models accommodate melanin and haemoglobin concentrations in the layers of the skin, thereby accounting for all skin types and healthy and anaemic blood perfusion in the dermal layer. In a third study, the understanding and consideration of the influence of melanin and haemoglobin in the skin layers are extended to developing full-finger models. The full-finger models are based on high-frequency ultrasound image data2 . The optical models were assessed in visible and near-infrared wavelengths using Monte Carlo simulations. This provides a method to assess tissue damage before treatments such as photodynamic therapy. Finally, an image processing exercise to identify and monitor vascular activity was undertaken in the fourth study of this thesis. The vascular activity was imaged and monitored using a simple transmission-based experimental strategy and off-theshelf equipment. Vascular activity analogous to heart rate was successfully monitored for the participants of the study, accounting for motion of the finger in a non-contact experimental and processing workflowItem Open Access Optical investigation of three-dimensional human skin equivalents: a pilot study(Wiley-VCH Verlag, 2019-10-08) Kallepalli, Akhil; McCall, Blake; James, David B.; Junaid, Sarah; Halls, James; Richardson, Mark A.Human skin equivalents (HSEs) are three‐dimensional living models of human skin that are prepared in vitro by seeding cells onto an appropriate scaffold. They recreate the structure and biological behaviour of real skin, allowing the investigation of processes such as keratinocyte differentiation and interactions between the dermal and epidermal layers. However, for wider applications, their optical and mechanical properties should also replicate those of real skin. We therefore conducted a pilot study to investigate the optical properties of HSEs. We compared Monte Carlo simulations of (1) real human skin and (2) two‐layer optical models of HSEs with (3) experimental measurements of transmittance through HSE samples. The skin layers were described using a hybrid collection of optical attenuation coefficients. A linear relationship was observed between the simulations and experiments. For samples thinner than 0.5 mm, an exponential increase in detected power was observed due to fewer instances of absorption and scattering.Item Open Access Target recognitions in multiple camera CCTV using colour constancy(Spie -- the Int Soc for Optical Engineering, 2013-06-28T00:00:00Z) Soori, Umair; Yuen, Peter W. T.; Ibrahim, Izzati; Han, Ji Wen; Hong, Kan; Chen, Wentao; Merfort, Christian; James, David B.; Richardson, Mark A.People tracking using colour feature in crowded scene through CCTV network have been a popular and at the same time a very difficult topic in computer vision. It is mainly because of the difficulty for the acquisition of intrinsic signatures of targets from a single view of the scene. Many factors, such as variable illumination conditions and viewing angles, will induce illusive modification of intrinsic signatures of targets. The objective of this paper is to verify if colour constancy (CC) approach really helps people tracking in CCTV network system. We have testified a number of CC algorithms together with various colour descriptors, to assess the efficiencies of people recognitions from real multi-camera i-LIDS data set via Receiver Operating Characteristics (ROC). It is found that when CC is applied together with some form of colour restoration mechanisms such as colour transfer, the recognition performance can be improved by at least a factor of two. An elementary luminance based CC coupled with a pixel based colour transfer algorithm, together with experimental results are reported in the present paper.Item Open Access An ultrasonography-based approach for tissue modelling to inform photo-therapy treatment strategies(Wiley, 2022-01-19) Kallepalli, Akhill; Halls, James; James, David B.; Richardson, Mark A.Currently, diagnostic medicine uses a multitude of tools ranging from ionising radiation to histology analysis. With advances in piezoelectric crystal technology, high-frequency ultrasound imaging has developed to achieve comparatively high resolution without the drawbacks of ionising radiation. This research proposes a low-cost, non-invasive and real-time protocol for informing photo-therapy procedures using ultrasound imaging. We combine currently available ultrasound procedures with Monte Carlo methods for assessing light transport and photo-energy deposition in the tissue. The measurements from high-resolution ultrasound scans are used as input for optical simulations. Consequently, this provides a pipeline that will inform medical practitioners for better therapy strategy planning. While validating known inferences of light transport through biological tissue, our results highlight the range of information such as temporal monitoring and energy deposition at varying depths. This process also retains the flexibility of testing various wavelengths for individual-specific geometries and anatomy.