Statistical sequential analysis for real-time video scene change detection on compressed multimedia bitstream

Abstract

Abstract-The increased availability and usage of multimedia information have created a critical need for efficient multimedia processing algorithms. These algorithms must offer capabilities related to browsing, indexing, and retrieval of relevant data. A crucial step in multimedia processing is that of reliable video segmentation into visually coherent video shots through scene change detection. Video segmentation enables subsequent processing operations on video shots, such as video indexing, semantic representation, or tracking of selected video information. Since video sequences generally contain both abrupt and gradual scene changes, video segmentation algorithms must be able to detect a large variety of changes. While existing algorithms perform relatively well for detecting abrupt transitions (video cuts), reliable detection of gradual changes is much more difficult. In this paper, a novel one-pass, real-time approach to video scene change detection based on statistical sequential analysis and operating on compressed multimedia bitstream is proposed. Our approach models video sequences as stochastic processes, with scene changes being reflected by changes in the characteristics (parameters) of the process. Statistical sequential analysis is used to provide an unified framework for the detection of both abrupt and gradual scene changes.

Video scene identification and classification for user-tailored QoE in GEO satellites

“…The problem of video scene detection has also attracted significant attention from the research community for two reasons: (a) it can be used for pure video segmentation [23,24] which has applications in storing, processing or analyzing the semantics of videos, and (b) it can be used in video traffic modeling in order to improve the model's efficiency [25,26]. The interested reader can refer to [27] for a more complete treatment of the scene detection literature.…”

Video Shot Boundary Detection: A Review

“…Features include the following parameters: (I) Luminance and color: The simplest feature which is used to recognize a ROI is its average grayscale luminance. It is capable of illumination changes [19,20], (II) Histogram: Another feature for ROI is grayscale or color histogram [21]. It is easier to calculate and often insensitive to rotational, translational and zooming motion of the camera, (III) Image edges: This feature is based on edge information of a ROI.…”

“…(I) Thresholding: Calculated feature values are compared with a fixed threshold [21,22], (II) Adaptive Thresholding: In this type of thresholding the above mentioned problem is solved by taking threshold value which can vary based on average discontinuity within a temporal domain [19], (III)Probabilistic Detection: Shot changes detection can be done by modeling the pattern of specific types of shot transitions and then changing the shot estimation assuming their specific probability distributions [20,23], (IV) Trained Classifier: This technique formulates the shot change detection as a classification problem, with two classes: "Shot change" and "no shot change" [24].…”

Advances in Video Summarization and Skimming

“…Usually hue saturation value (HSV) is considered as a more robust choice to provide a suitable color space [34][35]. -Histogram of Luminance/color: The grayscale or color histogram is a richer feature to be able to represent a frame, which has the advantages as discriminant and easy to compute [36].…”