Change detection is amongst the most effective critical examination methods used in remote sensing technology. In this research, new methods are proposed for building and vegetation change detection using only LiDAR data without using any other remotely sensed data. Two LiDAR datasets from 2009 and 2013 will be used in this research. These datasets are provided by the City of Surrey. A Parcel map which shows parcels in the study area will be also used in this research because the objective of this research is detecting changes based on parcels. Different methods are applied to detect changes in buildings and vegetation respectively. Three attributes of object –slope, building volume, and building height are derived and used in this study. Changes in buildings are not only detected but also categorized based on their attributes. In addition, vegetation change detection is performed based on parcels. The output shows parcels with a change of vegetation. Accuracy assessment is done by using measures of completeness, correctness, and quality of extracted regions. Accuracy assessments suggest that building change detection is performed with better results.

Over 9 million new cases of tuberculosis (TB) were reported worldwide in 2013. While the TB rate is much lower in the US, its uneven distribution and associated explanatory variables require interrogation in order to determine effective strategies for intervention and control. However, paucity of case data at fine geographic scales precludes such research. This research, using zip code level data from 837 confirmed TB cases in Tarrant County obtained from Texas Department of State Health Services, explores and attempts to explain the spatial patterns of TB and related risk markers within a framework of place vulnerability. Readily available census data is then used to characterize the spatial variations in TB risk. The resulting model will enable estimations of the geographic differences in TB case variables using this readily available census data instead of time-consuming and expensive individual data collection.