Inhalte

Current computer vision methods aim at processing an entire image at once. Prior work however has shown that the approach “one image at once” might not be the most effective. Instead, biological vision explores a scene while consecutively fixating on different regions in the scene. How does such active scene exploration lead to an improved understanding of objects and their relative locations? In this research group we will revise existing computer vision strategies for depth perception based on frame-based videos and event camera data. We then take ideas from biological vision to build a system that sequentially explores a scene to gain depth information (distance between observer and object) similar to the human visual system.

Kontakt

p.bideau@tu-berlin.de

Link zum Vorlesungsverzeichnis

https://moseskonto.tu-berlin.de/moses/verzeichnis/veranstaltungen/label.html?semester=70&feature=VERZEICHNIS&extended=false&search=true&veranstaltungslabel=40