关键词: 图像去雾, 视频去雾, 引导滤波, 透射率

Abstract:

Outdoor image often lose visibility and contrast due to the presence of haze. To effectively enhance the degraded haze image, we can get clear image by enhancing haze image's contrast. However, the excessive enhancement of the degraded contrast may truncate pixel values and cause information loss. Therefore, we proposed a fast and optimized dehazing algorithm based on information loss. By minimizing the information loss, the output image not only has high contrast but also has very little information loss. Moreover, we convert RGB color space into YUV color space, and only process the luminance component. This greatly improves the computational speed, thus suitable for processing video sequence. The contrast experimental results show that the proposed algorithm can effectively remove haze and the computing speed is fast, which can fully meet the real-time requirement for the removal of video haze.

Key words: image dehazing, video dehazing, guide filter, transmittance