Applications in numerous domains require accurate, robust, and high-performance computer vision techniques to support a broad range of video analysis tasks. These algorithms must handle diverse, complicated, and cluttered backgrounds while accommodating variations, such as changes in illumination or location, throughout the environments in which the application is deployed. At the same time, these applications demand that computer vision algorithms provide not only relevant, actionable information, but that they do so in a timely manner—i.e., the algorithms must operate in real-time. This requirement for high performance dictates optimization at every level. SURVICE currently capitalizes on mobile GPU chipsets, coupled with our experience as a GPU Research Center, to provide numerous perception capabilities across multiple domains.