Gabriel Brostow oversees a number of students at UCL’s Computer Science department in the area of computer vision and computer graphic applications and together with them pursues a “Smart Capture” agenda. Dr. Brostow describes Smart Capture thusly:
To me, smart capture of visual data (usually video) means having or finding satisfying answers to these questions about a system, whether interactive or fully automated:
- Does the system know the intended purpose of the data being captured?
- Can the system assess its own accuracy?
- Does the system compare new inputs to old ones?
Browstow and those who work with him have applied this ethos to a range of practical problems in areas such as film special effects and action analysis of animals. Brostow’s breadth of previous research illuminates the diverse scope which focusing on Smart Capture permits. In particular finding ways to detect independent motion in crowds could be an increasingly important area if recent interest in Crowd Computing Interaction gathers pace. Meanwhile virtual tuition software benefits from the insights that can be garnered by adhering to ‘Smart Capture’ principles (see “Presenting Movement in a Computer-Based Dance Tutor”, International Journal of Human-Computer Interaction, 15(3), 2003, for more).
Resarch Interests: film and photo special effects (computational photography), action analysis (of people, animals, and cells), and authoring systems (for architecture, animation, presentations)