arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1502.07643cs.CV
收藏

目标检测的动态置信度融合

Dynamic Belief Fusion for Object Detection

Ryan Robinson

摘要:

提出了一种新的融合不同目标检测方法的检测分数的方法。为了有效地整合多个检测器的输出,使用相应检测器的精确度/召回率关系来估计每个单独检测分数中的模糊性水平(称为“不确定性”)。所提出的融合方法,称为动态信念融合(DBF),动态分配基本概率命题(目标,非目标,不确定)的基础上的置信水平,在个别方法的检测结果。一个联合的基本概率分配,包含来自所有检测器的信息,使用Dempster的组合规则确定,并很容易减少到一个单一的融合检测得分。在ARL和PASCAL VOC 07数据集上的实验表明,DBF的检测精度大大高于传统的融合方法以及最先进的单个检测器。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑