Live cell imaging technologies have advanced enormously over the past decade. However, in most cases, analysis remains a painstaking, tedious and largely manual task, limiting the quantity and quality of resulting data. Here, we describe (i) the development of computational methods that detects and quantifies changes in the location of objects of interest in living cells and (ii) the application of this software to the analysis of populations of GFP-labeled microtubules (MTs). More specifically, we developed image enhancement techniques to automatically track and quantify the growing and shortening behavior of populations of MTs in living cells. Our new method improves dramatically upon the currently available means to analyze MT behavior. Through automated detection of all visible MTs in a fluorescence image stack in a visible cellular region (>100 MTs), each stack produces considerably more usable data in considerably less time while removing possible unintentional operator bias. Additionally, our technique preserves intact, ordered event histories of MT populations, possibly elucidating novel MT population behaviors which cannot be described by single event frequencies and average rates calculated from parsed data sets. Finally, global analysis of MT populations could reveal regional, behavioral specificities and MT population interrelations, possibly integral to specialized processes such as cell division and neuronal outgrowth. Taken together, this highly exportable technique improves our ability to address existing questions while making it possible to use statistics to ask novel questions regarding the behavior of MT populations (and other objects of interest) that have not been approachable previously.