Dynamic Belief Fusion for Object Detection
This work addresses the challenge of improving object detection accuracy by effectively combining outputs from disparate detectors, which is an incremental advancement in fusion methods for computer vision.
The paper tackles the problem of fusing detection scores from multiple object detectors by proposing Dynamic Belief Fusion (DBF), which estimates uncertainty and uses Dempster's combination rule to improve accuracy. Experiments on ARL and PASCAL VOC 07 datasets show that DBF achieves considerably greater detection accuracy than conventional fusion approaches and state-of-the-art individual detectors.
A novel approach for the fusion of detection scores from disparate object detection methods is proposed. In order to effectively integrate the outputs of multiple detectors, the level of ambiguity in each individual detection score (called "uncertainty") is estimated using the precision/recall relationship of the corresponding detector. The proposed fusion method, called Dynamic Belief Fusion (DBF), dynamically assigns basic probabilities to propositions (target, non-target, uncertain) based on confidence levels in the detection results of individual approaches. A joint basic probability assignment, containing information from all detectors, is determined using Dempster's combination rule, and is easily reduced to a single fused detection score. Experiments on ARL and PASCAL VOC 07 datasets demonstrate that the detection accuracy of DBF is considerably greater than conventional fusion approaches as well as state-of-the-art individual detectors.