Towards Automated Learning of Object Detectors

Recognizing arbitrary objects in images or video sequences is a difficult task for a computer vision system. We work towards automated learning of object detectors from video sequences (without user interaction). Our system uses object motion as an important cue to detect independently moving objects in the input sequence. The largest object is always taken as the teaching input, i.e. the object to be extracted. We use Cartesian Genetic Programming to evolve image processing routines which deliver the maximum output at the same position where the detected object is located. The graphics processor (GPU) is used to speed up the image processing. Our system is a step towards automated learning of object detectors. 1 Motivation A human observer has no problems in identifying different objects in an image. How do humans learn to recognize different objects in an image? Enabling a computer vision system to perform this feat is a daunting task. However, we try to work towards this goal. An id...

• Type: Conference
• Year: 2010
• Where: EVOW
• Authors: Marc Ebner
• Keywords: Artificial Intelligence, EVOW 2010, Image Processing, Object Detectors, User Interaction