Mitsubishi Electric Research Laboratories, Inc.

Mitsubishi Electric Research Labs.

Mitsubishi Denki Kabushiki Kaisha

Ajay Divakaran

Huifang Sun

Kadir A Peker

Regunathan Radhakrishnan

Anthony Vetro

Shih-Fu Chang

Isao Otsuka

Hiroshi Ito

Daniel Nikolaev Nikovski

Kevin William Wilson

Tommy C Poon

Mamoru Kato

Naveen Goela

Feng Niu

Lexing Xie

Peng Xu

Kazuhiko Nakane

Fatih M Porikli

Masaharu Ogawa

Paris Smaragdis

Bangalore S Manjunath

Bhiksha Ramakrishnan

Hae-Kwang Kim

Sun-Yuan Kung

Xinding Sun

Manoranjan D Jesudoss

Vinod Vijayalekshmi Vasudevan

I-Jong Lin

Chul-soo Park

Michael A Casey

Paul DaGraca

Michael Siracusa

Romain Cabasson

Hyundoo Shin

Ganesh Rattinassababady

Koji Miyahara

Ziyou Xiong

A method segments a video. Audio frames of the video are classified with labels. Dominant labels are assigned to successive time intervals of consecutive labels. A semantic description is constructed for sliding time windows of the successive time intervals, in which the sliding time windows overlap in time, and the semantic description for each time window is a transition matrix determined from the dominant labels of the time intervals. A marker is determined from the transition matrices, in which a frequency of occurrence of the marker is between a low frequency threshold and a high frequency threshold. Then, the video is segmented at the locations of the markers.

Method and system for video segmentation

A method and system denoises a mixed signal. A constrained non-negative matrix factorization (NMF) is applied to the mixed signal. The NMF is constrained by a denoising model, in which the denoising model includes training basis matrices of a training acoustic signal and a training noise signal, and statistics of weights of the training basis matrices. The applying produces weight of a basis matrix of the acoustic signal of the mixed signal. A product of the weights of the basis matrix of the acoustic signal and the training basis matrices of the training acoustic signal and the training noise signal is taken to reconstruct the acoustic signal. The mixed signal can be speech and noise.

Denoising acoustic signals using constrained non-negative matrix factorization

A system determines real-time locations of railcars in a railroad environment. Railcars are equipped with at least four RFID tags. A RFID reader at a fixed location at every track branch in the environment reads the RFID tags. Railcar locations are updated for the railcars by determining the branches on which the railcars are located.

System for tracking railcars in a railroad environment

A computer implemented method detects scene boundaries in videos by first extracting feature vectors from videos of different genres. The feature vectors are then classified as scene boundaries using a support vector machine. The support vector machine is trained to be independent of the different genres of the videos.

Method for detecting scene boundaries in genre independent videos

A method classifies segments of a video using an audio signal of the video and a set of classes. Selected classes of the set are combined as a subset of important classes, the subset of important classes being important for a specific highlighting task, the remaining classes of the set are combined as a subset of other classes. The subset of important classes and classes are trained with training audio data to form a task specific classifier. Then, the audio signal can be classified using the task specific classifier as either important or other to identify highlights in the video corresponding to the specific highlighting task. The classified audio signal can be used to segment and summarize the video.

Task specific audio classification for identifying video highlights

A method generates a summary of a video. Faces are detected in a plurality of frames of the video. The frames are classified according to a number of faces detected in each frame and the video is partitioned into segments according to the classifications to produce a summary of the video. For each frame classified as having a single detected face, one or more characteristics of the face is determined. The frames are labeled according to the characteristics to produce labeled clusters and the segments are partitioned into sub-segments according to the labeled clusters.

Method and system for segmenting videos using face detection

A method and system detects and diagnoses faults in heating, ventilating and air conditioning (HVAC) equipment. Internal state variables of the HVAC equipment are measured under external driving conditions. Expected internal state variables are predicted for the HVAC equipment operating under the external driving conditions using a locally weighted regression model. Features are determined of the HVAC based on differences between the measured and predicted state variables. The features are classified to determine a condition of the HVAC equipment.

Detecting and diagnosing faults in HVAC equipment

A method detects events in multimedia. Features are extracted from the multimedia. The features are sampled using a sliding window to obtain samples. A context model is constructed for each sample. An affinity matrix is determined from the models and a commutative distance metric between each pair of context models. A second generation eigenvector is determined for the affinity matrix, and the samples are then clustered into events according to the second generation eigenvector.

Multimedia event detection and summarization

A system and method summarizes multimedia stored in a compressed multimedia file partitioned into a sequence of segments, where the content of the multimedia is, for example, video signals, audio signals, text, and binary data. An associated metadata file includes index information and an importance level for each segment. The importance information is continuous over as closed interval. An importance level threshold is selected in the closed interval, and only segments of the multimedia having a particular importance level greater than the importance level threshold are reproduced. The importance level can also be determined for fixed-length windows of multiple segments, or a sliding window. Furthermore, the importance level can be weighted by a factor, such as the audio volume.

System and method for recording and reproducing multimedia based on an audio signal

A method plays frames of a video adaptively according to a visual complexity of the video. First a spatial frequency of pixel within frames of the video is measured, as well as a temporal velocity of corresponding pixels between frames of the video. The spatial frequency is multiplied by the temporal velocity to obtain a measure of the visual complexity of the frames of the video. The frames of the video are then played at a speed that corresponds to the visual complexity.

Visual complexity measure for playing videos adaptively

A method for generating a representation of multimedia content by first segmenting the multimedia content spatially and temporally to extract objects. Feature extraction is applied to the objects to produce semantic and syntactic attributes, relations, and a containment set of content entities. The content entities are coded to produce directed acyclic graphs of the content entities, where each directed acyclic graph represents a particular interpretation of the multimedia content. Attributes of each content entity are measured and the measured attributes are assigned to each corresponding content entity in the directed acyclic graphs to rank order the multimedia content.

Method for representing and comparing multimedia content according to rank

A method mines unknown content of a video by first selecting one or more low-level features of the video. For each selected feature, or combination of features, time series data is generated. The time series data is then self-correlated to identify similar segments of the video according to the low-level features. The similar segments are grouped into clusters to discover high-level patterns in the unknown content of video.

Video mining using unsupervised clustering of video content

A method segments a compressed video by extracting audio and visual features from the compressed video. The audio features are clustered according to K-means clustering in a set of classes, and the compressed video is then partitioned into first segments according to the set of classes. The visual features are then used to partitioning each first segment into second segments using motion analysis. Summaries of the second segments can be provided to assist in the browsing of the compressed video.

Audio-assisted video segmentation and summarization

A method detects short term, unusual events in a video. First, features are extracted features from the audio and the video portions of the video. Segments of the video are labeled according to the features. A global sliding window is applied to the labeled segments to determine global characteristics over time, while a local sliding window is applied only to the labeled segments of the global sliding window to determine local characteristic over time. The local window is substantially shorter in time than the global window. A distance between the global and local characteristic is measured to determine occurrences of the unusual short time events.

Method for detecting short term unusual events in videos

A method learns a structure of a video, in an unsupervised setting, to detect events in the video consistent with the structure. Sets of features are selected from the video. Based on the selected features, a hierarchical statistical model is updated, and an information gain of the hierarchical statistical model is evaluated. Redundant features are then filtered, and the hierarchical statistical model is updated, based on the filtered features. A Bayesian information criteria is applied to each model and feature set pair, which can then be rank ordered according to the criteria to detect the events in the video.

Growing community of inventors

Denville, NJ, United States of America

Ajay Divakaran