Pii: S0031-3203(01)00134-0
نویسندگان
چکیده
E4ective annotation and content-based search for videos in a digital library require a preprocessing step of detecting, locating and classifying scene transitions, i.e., temporal video segmentation. This paper proposes a novel approach— spatial–temporal joint probability image (ST-JPI) analysis for temporal video segmentation. A joint probability image (JPI) is derived from the joint probabilities of intensity values of corresponding points in two images. The ST-JPT, which is a series of JPIs derived from consecutive video frames, presents the evolution of the intensity joint probabilities in a video. The evolution in a ST-JPI during various transitions falls into one of several well-de:ned linear patterns. Based on the patterns in a ST-JPI, our algorithm detects and classi:es video transitions e4ectively. Our study shows that temporal video segmentation based on ST-JPIs is distinguished from previous methods in the following way: (1) It is e4ective and relatively robust not only for video cuts but also for gradual transitions; (2) It classi:es transitions on the basis of prede:ned evolution patterns of ST-JPIs during transitions; (3) It is e>cient, scalable and suitable for real-time video segmentation. Theoretical analysis and experimental results of our method are presented to illustrate its e>cacy and e>ciency. ? 2002 Pattern Recognition Society. Published by Elsevier Science Ltd. All rights reserved.
منابع مشابه
Fast nearest-neighbor search algorithms based on approximation-elimination search
In this paper, we provide an overview of fast nearest-neighbor search algorithms based on an &approximation}elimination' framework under a class of elimination rules, namely, partial distance elimination, hypercube elimination and absolute-error-inequality elimination derived from approximations of Euclidean distance. Previous algorithms based on these elimination rules are reviewed in the cont...
متن کاملFitness functions in editing k-NN reference set by genetic algorithms
-In a previous paper the use of GAs as an editing technique for the k-nearest neighbor (k-NN) classification technique has been suggested. Here we are looking at different fitness functions. An experimental study with the IRIS data set and with a medical data set has been carried out. Best results (smallest subsets with highest test classification accuracy) have been obtained by including in th...
متن کاملAmbiguity reduction in speaker identification by the relaxation labeling process
A nonlinear probabilistic model of the relaxation labeling (RL) process is implemented in the speaker identi"cation task in order to disambiguate the labeling of the speech feature vectors. In this proposed algorithm, the deterministic labeling of the vector quantization (VQ)-based speaker identi"cation is relaxed by means of introducing initial probabilistic weights to the labeling process of ...
متن کاملGaussian mixture parameter estimation with known means and unknown class-dependent variances
متن کامل
Finding approximate palindromes in strings
We introduce a novel de nition of approximate palindromes in strings, and provide an algorithm to nd all maximal approximate palindromes in a string with up to k errors. Our de nition is based on the usual edit operations of approximate pattern matching, and the algorithm we give, for a string of size n on a xed alphabet, runs in O(kn) time. We also discuss two implementationrelated improvement...
متن کامل