This paper aims at presenting a new frame work for video frame enhancement. The often faced challenge to preserve naturalness of digital videos arise when they are taken under non uniform illumination either due to poor light environment or due to uneven lighting on the object surface or due to prevalence of fixed noise patterns. The first step recommended in the study is to decompose the frame into reflectance and illumination. We can use Bright Pass Filter (BPF) for this purpose. Next step is to obtain uniform illumination. Towards this we can apply the technique called Adaptive Gamma Correction with Weighted distribution of illumination. After this we can combine reflectance and uniform illumination. For further improvement we suggest DSCE (Dual combination of background Subtraction and Color consistency Enhancement). This considerably reduces fixed pattern noise enhancing the quality of video frames. The naturalness of the frame is measured by lightness-order-error. Naturalness-image–quality-evaluator measures the quality of enhancement. Experimental result of the proposed frame work reveals that besides enhancing details it preserve naturalness and suppress fixed pattern noise for extremely low light video.
Volume 11 | 07-Special Issue
Pages: 1043-1051