基于光强—光谱—偏振信息融合的水下目标检测

由于图像建模及参数估计的困难和复杂性，水下目标检测算法的性能受到了严重影响。受水下生物视觉信息处理机制的启发，针对特殊的水下光学环境提出一种新的基于光强—光谱—偏振的仿生信息融合目标检测方法，能够根据所获得的水下光学先验知识进行适应性特征融合。算法摆脱繁琐的图像预处理过程，以较低的运算复杂度为代价实现可靠的目标检测结果。

Light intensity,spectrum and polarization information fusion based underwater object detection

Difficulties and high computational costs in the model establishmen and parameter estimation seriously de-graded the efficiency of the underwater object detection system, making them too cumbersome to the practical work. A noval light intensity, spectrum and polarization feature fusion method was proposed. This method directly introduces the prior underwater knowledge into the system for feature fusion, getting rid of the harassment of the image preprocessing. Experiments prove that this method by comparison can achieve more reliable results at the lower computational cost.