DBF: Dynamic Belief Fusion for Combining Multiple Object Detectors
This work addresses the challenge of improving object detection accuracy for computer vision applications by fusing multiple detector outputs, representing an incremental advance in score-level fusion techniques.
The paper tackles the problem of combining outputs from multiple object detectors by proposing Dynamic Belief Fusion (DBF), which estimates ambiguity in detection scores and fuses probabilities using Dempster's rule, resulting in significantly higher detection accuracy on ARL, PASCAL VOC 07, and 12 datasets compared to baseline fusion methods and individual detectors.
In this paper, we propose a novel and highly practical score-level fusion approach called dynamic belief fusion (DBF) that directly integrates inference scores of individual detections from multiple object detection methods. To effectively integrate the individual outputs of multiple detectors, the level of ambiguity in each detection score is estimated using a confidence model built on a precision-recall relationship of the corresponding detector. For each detector output, DBF then calculates the probabilities of three hypotheses (target, non-target, and intermediate state (target or non-target)) based on the confidence level of the detection score conditioned on the prior confidence model of individual detectors, which is referred to as basic probability assignment. The probability distributions over three hypotheses of all the detectors are optimally fused via the Dempster's combination rule. Experiments on the ARL, PASCAL VOC 07, and 12 datasets show that the detection accuracy of the DBF is significantly higher than any of the baseline fusion approaches as well as individual detectors used for the fusion.