Real-Time Automatic Object Classification and Tracking using Genetic Programming and NVIDIA R CUDA TM

Genetic Programming (GP) is a widely used methodology for solving various computational problems. GP's problem solving ability is usually hindered by its long execution times. In this thesis, GP is applied toward real-time computer vision. In particular, object classification and tracking using a parallel GP system is discussed. First, a study of suitable GP languages for object classification is presented. Two main GP approaches for visual pattern classification, namely the block-classifiers and the pixel-classifiers, were studied. Results showed that the pixel-classifiers generally performed better. Using these results, a suitable language was selected for the real-time implementation. Synthetic video data was used in the experiments. The goal of the experiments was to evolve a unique classifier for each texture pattern that existed in the video. The experiments revealed that the system was capable of correctly tracking the textures in the video. The performance of the system was on-par with real-time requirements.

Larval habitat associations with human land uses, roads, rivers, and land cover for Anopheles albimanus, A. pseudopunctipennis, and A. punctimacula (Diptera: Culicidae) in coastal and highland Ecuador

Larval habitat for three highland Anopheles species: Anopheles albimanus Wiedemann, Anopheles pseudopunctipennis Theobald, and Anopheles punctimacula Dyar and Knab was related to human land uses, rivers, roads, and remotely sensed land cover classifications in the western Ecuadorian Andes. Of the five commonly observed human land uses, cattle pasture (n = 30) provided potentially suitable habitat for A. punctimacula and A. albimanus in less than 14% of sites, and was related in a principal components analysis (PCA) to the presence of macrophyte vegetation, greater surface area, clarity, and algae cover. Empty lots (n = 30) were related in the PCA to incident sunlight and provided potential habitat for A. pseudopunctipennis and A. albimanus in less than 14% of sites. The other land uses surveyed (banana, sugarcane, and mixed tree plantations; n = 28, 21, 25, respectively) provided very little standing water that could potentially be used for larval habitat. River edges and eddies (n = 41) were associated with greater clarity, depth, temperature, and algae cover, which provide potentially suitable habitat for A. albimanus in 58% of sites and A. pseudopunctipennis in 29% of sites. Road-associated water bodies (n = 38) provided potential habitat for A. punctimacula in 44% of sites and A. albimanus in 26% of sites surveyed. Species collection localities were compared to land cover classifications using Geographic Information Systems software. All three mosquito species were associated more often with the category “closed/open broadleaved evergreen and/or semi-deciduous forests” than expected (P ≤ 0.01 in all cases), given such a habitat’s abundance. This study provides evidence that specific human land uses create habitat for potential malaria vectors in highland regions of the Andes.

Hyperspectral Mineral Identification using SVM and SOM

Remote sensing techniques involving hyperspectral imagery have applications in a number of sciences that study some aspects of the surface of the planet. The analysis of hyperspectral images is complex because of the large amount of information involved and the noise within that data. Investigating images with regard to identify minerals, rocks, vegetation and other materials is an application of hyperspectral remote sensing in the earth sciences. This thesis evaluates the performance of two classification and clustering techniques on hyperspectral images for mineral identification. Support Vector Machines (SVM) and Self-Organizing Maps (SOM) are applied as classification and clustering techniques, respectively. Principal Component Analysis (PCA) is used to prepare the data to be analyzed. The purpose of using PCA is to reduce the amount of data that needs to be processed by identifying the most important components within the data. A well-studied dataset from Cuprite, Nevada and a dataset of more complex data from Baffin Island were used to assess the performance of these techniques. The main goal of this research study is to evaluate the advantage of training a classifier based on a small amount of data compared to an unsupervised method. Determining the effect of feature extraction on the accuracy of the clustering and classification method is another goal of this research. This thesis concludes that using PCA increases the learning accuracy, and especially so in classification. SVM classifies Cuprite data with a high precision and the SOM challenges SVM on datasets with high level of noise (like Baffin Island).