海底主动光学探测影像亮度校正与色彩恢复

Brightness correction and color restoration of seabed image obtained by active optical detection

主动光学成像探测是海底形貌与环境探测的重要方式,广泛应用于大洋勘探、海底探测等领域。然而,由于海水对光的衰减作用,造成光学影像照度不均、颜色失真、对比度低等质量退化问题。本文依据水下主动光学成像探测的特点,提出了一种基于相对辐射校正原理的水下图像增强方法。该方法将增强过程分为亮度补偿和色彩恢复两个阶段。在亮度补偿阶段,依据水下点光源的成像特点和辐射衰减机制,采用相对辐射校正原理对水下图像分通道进行补偿,消除因光源不均、光程不同等因素造成的亮度畸变。在色彩恢复阶段,首先对红通道图像进行自适应补偿和色彩粗平衡,在此基础上进一步利用Retinex模型对图像进行色彩恢复。利用实际的海底勘探图像进行实验验证,结果表明本文方法的增强结果亮度均匀、色彩自然,有效提升了图像质量。相较现有方法,本文方法的结果无论主观感受还是客观评价整体更优。同时,由于本文方法不需要光源、相机等特性参数,仅利用实际观测图像本身进行校正,因而具有更好的适应性。

Active optical imaging detection is an important method for seabed topography and environment detection,which is widely used in ocean exploration.However,due to the attenuation effect of light in seawater,the optical images often suffer uneven illumination,color distortion and low contrast.According to the property of underwater active optical imaging,an underwater image enhancement method based on relative radiometric correction is proposed in this paper.The procedure is divided into brightness compensation and color restoration.In brightness compensation,according to the imaging characteristics and radiation attenuation mechanism of a point light source,the relative radiation correction is used to compensate for the channels of underwater images.This stage eliminates the brightness distortion caused by an uneven light source,varying optical paths and so on.In the color restoration,adaptive compensation and rough color balance are performed first on the red channel.Then,the Retinex model is used to restore colors.The real seabed images are used for experiments.The results show that the enhanced images by the proposed method have uniform brightness and natural look.Compared with the other methods,the results of the proposed method are better overall both subjectively and objectively.At the same time,the method proposed in this paper does not need the properties of light source,camera and others.Only the real detection images themselves are used for correction,and achieve better adaptability.