A Framework for Robust Online Video Contrast Enhancement Using Modularity Optimization

Abstract

We address the problem of video contrast enhancement. Existing techniques either do not exploit temporal information at all or do not exploit it correctly. This results in inconsistency that causes undesirable flash and flickering artifacts. Our method analyzes video streams and cluster frames that are similar to each other. Our method does not have omniscient information about the entire video sequence. It is an online process with a fixed delay. A sliding window mechanism successfully detects shot boundaries "on-the-fly" in a video. A graph-based technique called "modularity" performs automatic clustering of video frames without a priori information about clusters. For every cluster in the video, we extract key frames belonging to each cluster using eigen analysis and estimate enhancement parameters for only the key frame, then use these parameters to enhance frames belonging to that cluster, thus making our method robust. We evaluate the clustering method on video sequences from the TRECVid 2001 dataset and compare it with existing methods. We show reduction of flash artifacts in enhanced videos. We show statistically significant improvement in perceived video quality and validate that by conducting experiments on human observers. We show application of our clustering process to perform robust video segmentation.

Static video summarization approach using Binary Robust Invariant Scalable Keypoints

“…The clustering algorithms cluster video frames and then select the centroids of each cluster to generate the final summary. The k-means clustering method [28], a graph-based technique called "modularity" [29], Delaunay Triangulation [30], Farthest Point-First (FPF) algorithm [31], and Density-Based Spatial Clustering (DBSCAN) [32] are all used in video summarization.…”

Gaussian mixture model‐based contrast enhancement

“…The main drawback of EM is its complexity and inability of implementation for real time applications [27]. For example, if the application is auto contrast in digital video recorders [28], it is not feasible to apply EM for every single frame. Moreover, EM-based methods are highly dependent on the starting points.…”

A new method of contrast enhancement of musculoskeletal ultrasound imaging based on fuzzy inference technique

“…Because grey level intensities of many important musculoskeletal constituents of each ultrasound image overlap, obtaining a proper value for this threshold. In terms of image contrast enhancement using fuzzy techniques, these techniques inhibit noise and intensify contrast because they optimize parameters of membership functions based on the highest value of fuzzy entropy and modify membership equation based on these parameters [10][11][12]. They have also been performed efficiently on many kinds of images, such as medical x-ray images [10], breast ultrasound images [13], musculoskeletal ultrasound images [14] and satellite images [15].…”