Dynamic attention priors: a new and efficient concept for improving object detection

Recent psychophysical evidence in humans suggests that visual attention is a highly dynamic and predictive process involving precise models of object trajectories. We present a proof-of-concept that such predictive spatial attention can benefit a technical system solving a challenging visual object detection task. To this end, we introduce a Bayes-like integration of the so-called dynamic attention priors (DAPs) and dense detection likelihoods, which get enhanced at predicted object positions obtained by the extrapolation of trajectories. Using annotated video sequences of pedestrians in a parking lot setting, we quantitatively show that DAPs can improve detection performance significantly as compared to a baseline condition relying purely on pattern analysis.