PT Unknown
AU Karel Paleček
   David Geronimo
   Frederic Lerasle
TI Pre-attention cues for person detection
BT Cognitive Behavioural Systems, COST 2102 International Training School
PY 2012
BP 225
EP 235
DI 10.1007/978-3-642-34584-5_19
AB Current state-of-the-art person detectors have been proven reliable and achieve very good detection rates. However, the performance is often far from real time, which limits their use to low resolution images only. In this paper, we deal with candidate window generation problem for person detection, i.e. we want to reduce the computational complexity of a person detector by reducing the number of regions that has to be evaluated. We base our work on Alexe’s paper [1], which introduced several pre-attention cues for generic object detection. We evaluate these cues in the context of person detection and show that their performance degrades rapidly for scenes containing multiple objects of interest such as pictures from urban environment. We extend this set by new cues, which better suits our class-specific task. The cues are designed to be simple and efficient, so that they can be used in the pre-attention phase of a more complex sliding window based person detector.
ER