一种矿井动态图像增强方法

基金项目:

“十二五”国家科技支撑计划资助项目（2013BAK06B01）

国家自然科学基金资助项目（61201326, 61273266, 61375028）

详细信息

A dynamic image enhancement method for mine

1.
School of Resources and Geosciences, China University of Mining and Technology, Xuzhou 221008, China
2.
School of Information and Electrical Engineering, Xuzhou College of Industrial Technology, Xu

摘要: 针对矿井动态监控图像存在“雪花”噪声、图像灰度值较低、细节灰度差别较小等问题，提出一种动态图像增强方法。首先对原始图像进行改进的直方图均匀化处理，然后进行照度估计，对得到的光照度图像进行归一化修正，同时采用非线性动态增益对反射光图像进行修正。采用矿井机车管理系统采集的监控图像对该方法进行验证，结果表明经该方法处理的图像效果较好。
- 矿井监控图像 /
- 矿井机车管理系统 /
- 图像增强 /
- 多尺度Retinex算法
Abstract: Aiming at noise, low image grey and little gray difference of dynamic monitoring image of coal mine, a dynamic image enhancement method was proposed. Original image is processed by an improved histogram equalization method firstly and then dealt with illumination estimatation. The illumination image is normalized, while reflected light image is revised by nonlinear dynamic gain. The experimental results by use of monitoring image from mine locomotive management system show that the method has better image processing effect.
- mine monitoring image /
- mine locomotive management system /
- image enhancement /
- multi-scale Retinex algorithm