We propose a dense local region detector to extract features suitable for image matching and object recognition tasks. Whereas traditional local interest operators rely on repeata...
Current zero-knowledge watermark detectors are based on a linear correlation between the asset features and a given secret sequence. This detection function is susceptible of bein...
The basic and widely used edge detection operation in an image usually requires a prior step of setting the edge detector parameters (thresholds, blurring extent etc.). Finding th...
Sensitivity analysis attacks present a serious threat to the security of popular spread spectrum watermarking schemes. Randomization of the detector is thought to increase the imm...
We present an online learning approach for robustly combining unreliable
observations from a pedestrian detector to estimate the rough 3D scene geometry
from video sequences of a...
Michael D. Breitenstein, Eric Sommerlade, Bastian ...