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

Abstract : Recent psychophysical evidence in humans suggests that visual attention is a highly dynamic and predictive process involving precise models of object tra-jectories. 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 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.
Document type :
Journal articles
Complete list of metadatas

Cited literature [43 references]  Display  Hide  Download

Contributor : Alexander Gepperth <>
Submitted on : Friday, December 16, 2016 - 1:12:03 PM
Last modification on : Wednesday, July 3, 2019 - 10:48:05 AM
Long-term archiving on : Tuesday, March 21, 2017 - 9:33:49 AM


Files produced by the author(s)



Alexander Gepperth, Michael Garcia Ortiz, Egor Sattarov, Bernd Heisele. Dynamic attention priors: a new and efficient concept for improving object detection. Neurocomputing, Elsevier, 2016, 197, pp.14 - 28. ⟨10.1016/j.neucom.2016.01.036⟩. ⟨hal-01418128⟩



Record views


Files downloads