27 resultados para 04090302 TM-55
em Brock University, Canada
Resumo:
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.
Resumo:
Domain boundaries observed between the fine grained and coarse grained sediment. The coarse grained sediment contains lineations.
Resumo:
Fine grained sediment, quite structure-less.
Resumo:
Dark brown sediment with clasts ranging from small to large. The grains are sub-angular. Two main domains can be seen. Both are coarse grained, but one contains larger grains and potentially more clay material. Lineations are present throughout the sample in multiple directions. Minor rotation around a few larger clasts can be seen, as well as comet structures.
Resumo:
Coarse grained sample with sub-angular to sub-rounded clasts ranging from small-large in size. Rotation structures, grain crushing and lineations were seen throughout the sample.
Resumo:
Coarse grained sample with clasts ranging from small to medium. Clast shape ranges from angular to sub-angular. Lineations and rotation structures seen. Clay material and fine grained domains (darker colour) also seen.
Resumo:
Coarse grained sample with clay stained domains. Grains range from small to medium in size and are sub-angular. Lineations, weathered grains, and minor grain stacking.
Resumo:
Dark brown sediment with clasts that range from small to large. The clast shape ranges from sub-angular to sub-rounded. Lineations are abundant in this sample. Edge-to-edge grain crushing can also be seen. Darker organic rich domains are also present throughout the sample.
Resumo:
This is a coarse grained sample with some very fine grained domains throughout the sample. The clast shape and size range from small to large, as well as angular to sub-rounded. Grain crushing is the most prevalent in this sample. It also contains some rotation structures and minor necking structures. Lineations and grain stacking can also be seen.
Resumo:
Two main domains can be seen in this sample. One is coarse grained with clasts ranging from small to medium in size. The other is very fine grained, and a very dark brown, potentially influenced by organic material. Grain crushing and lineations can be seen in the coarser domain.
Resumo:
Coarse grained sample with inclusions of finer grained sediment. Clasts are small to large in size and angular to sub-rounded in shape. Grain crushing is abundant in this sample, and lineations and minor grain stacks can also be seen.
Resumo:
Dark brown sediment with mainly small clasts. The clasts range from sub-angular to sub-rounded. Lineations are abundant throughout the sample. Comet structures are also present throughout the sample. Minor amounts of grain crushing and stacking can also be seen.
Resumo:
Dark grey sediment with clasts that are large in size. The shape of the clasts range from angular to sub-rounded. Grain stacking can be seen throughout the sample. Minor amounts of rotation structures can also be seen.
Resumo:
Light brown sediment with clasts ranging from small to large. The clasts range from angular to sub-rounded. Rotation structures are common, along with grain crushing.