Dynamic attention priors: a new and efficient concept for improving object detection
Gepperth, Alexander R. T., Garcia Ortiz, M. 
ORCID: 0000-0003-4729-7457, Sattarov, E. & Heisele, B. (2016).
Dynamic attention priors: a new and efficient concept for improving object detection.
Neurocomputing, 197,
pp. 14-28.
doi: 10.1016/j.neucom.2016.01.036
Abstract
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.
| Publication Type: | Article |
|---|---|
| Additional Information: | Visual attention, Object detection |
| Subjects: | Q Science > QA Mathematics > QA75 Electronic computers. Computer science |
| Departments: | School of Science & Technology > Computer Science |
Available under License Creative Commons Attribution Non-commercial No Derivatives.
Download (3MB) | Preview
Export
Downloads
Downloads per month over past year
Metadata
MetadataActions (login required)
Admin Login