基于前景—背景可区分性评价因子的运动目标多源协同检测  

Multi-modal cooperative moving objects detection based on F-BDEF

作　　者：张秀伟[1,2] 张艳宁[1,2] 梁君[1,2] 

机构地区：[1]西北工业大学计算机学院,陕西西安710129 [2]陕西省语音与图像信息处理重点实验室,陕西西安710129

出　　处：《红外与毫米波学报》2015年第5期619-629,共11页Journal of Infrared and Millimeter Waves

基　　金：国家自然科学基金(61303123;U1404607);陕西省自然科学基金(2015JQ6256);中央高校基本科研业务费专项资金(3102015JSJ0008;NPU-FFR-JCT20130109)~~

摘　　要：在多源信息融合中,对不同源信息及处理结果的可信度度量是影响多源信息融合精确性的关键.针对可见光和热红外动目标检测问题,提出了基于F-BDEF的运动目标多源协同检测算法.F-BDEF即前景-背景可区分性评价因子,是一种无基准的运动分割质量评价因子,用来评价不同信息源(可见光/热红外)运动检测结果的好坏.实验表明:与现有融合检测算法比较,该算法具有较高的检测精度,能较好得解决光照突变、阴影、鬼影、低对比度夜晚场景等问题.How to evaluate the reliabilities of different image sensors and their processing results is an important issue in the field of multi-modal fusion. In this paper,w e focus on multi-modal fusion moving objects detection,in w hich visible light and infrared image sensors are adopted. An evaluation factor named F-BDEF（ Foreground-Background Distinguishability Evaluation Factor） w as proposed to evaluate the reliabilities of the detection results of tw o sensors. Then a multimodal fusion moving objects detection based on F-BDEF w as proposed,in w hich F-BDEF w as used to distinguish betw een false positive alarm and false negative alarm,and to choose the accurate detection region from visible light result and infrared result. The experiments show ed that the proposed detection method received more accurate results and could overcome many disturbances,such as sudden change of illumination,shadow,ghost,low-contrast night scene.

关 键 词：运动目标检测 多源 协同 无基准性能评价 

分 类 号：TP751.1[自动化与计算机技术—检测技术与自动化装置]