Efficient Video Retrieval Research Articles

Conditional deep clustering based transformed spatio-temporal features and fused distance for efficient video retrieval

Conditional deep clustering based transformed spatio-temporal features and fused distance for efficient video retrieval

Video retrieval framework based on color co-occurrence feature of adaptive low rank extracted keyframes and graph pattern matching

In recent times, exploration of multimedia required ever increasing demand and application for intelligent video retrieval from repositories. This paper presents an efficient video retrieval framework by employing the effective singular value decomposition and computationally low complex ordered dither block truncation coding to extract simple, compact, and well discriminative Color Co-occurrence Feature (CCF). In this context, the occurrence probability of a video frame pixel in the neighborhood is employed to formulate this specific and distinct feature. Moreover, we applied a new adaptive low rank thresholding based on energy concentricity, transposition, and replacement invariance characteristics to formulate a unified fast shot boundary detection approach to solve the protuberant bottleneck problem for real-time cut and gradual transition that eventually contributes for effective keyframes extraction. Therefore, we can assert that the keyframes are distinct and discriminative to represent the whole video content. For effective indexing and retrieval, it is imperative to formulate similarity score evaluator for the encapsulated contextual video information with substantial temporal consistency, least computation, and post-processing. Therefore, we introduced graph-based pattern matching for video retrieval with an aim to sustain temporal consistency, accuracy and time overhead. Experimental results signify that the proposed method on average provides 7.40% and 17.91% better retrieval accuracy and 23.21% and 20.44% faster than the recent state-of-the-art methods for UCF11 and HMDB51 standard video dataset, respectively.

Content-Based Video Retrieval Using Integration of Curvelet Transform and Simple Linear Iterative Clustering

Video is a rich information source containing both audio and visual information along with motion information embedded in it. Applications such as e-learning, live TV, video on demand, traffic monitoring, etc. need an efficient video retrieval strategy. Content-based video retrieval and superpixel segmentation are two diverse application areas of computer vision. In this work, we are presenting an algorithm for content-based video retrieval with help of Integration of Curvelet transform and Simple Linear Iterative Clustering (ICTSLIC) algorithm. Proposed algorithm consists of two steps: off line processing and online processing. In offline processing, keyframes of the database videos are extracted by employing features: Pearson Correlation Coefficient (PCC) and color moments (CM) and on the extracted keyframes superpixel generation algorithm ICTSLIC is applied. The superpixels generated by applying ICTSLIC on keyframes are used to represent database videos. On other side, in online processing, ICTSLIC superpixel segmentation is applied on query frame and the superpixels generated by segmentation are used to represent query frame. Then videos similar to query frame are retrieved through matching done by calculation of Euclidean distance between superpixels of query frame and database keyframes. Results of the proposed method are irrespective of query frame features such as camera motion, object’s pose, orientation and motion due to the incorporation of ICTSLIC superpixels as base feature for matching and retrieval purpose. The proposed method is tested on the dataset comprising of different categories of video clips such as animations, serials, personal interviews, news, movies and songs which is publicly available. For evaluation, the proposed method randomly picks frames from database videos, instead of selecting keyframes as query frames. Experiments were conducted on the developed dataset and the performance is assessed with different parameters Precision, Recall, Jaccard Index, Accuracy and Specificity. The experimental results shown that the proposed method is performing better than the other state-of-art methods.

Learning a Multi-Concept Video Retrieval Model with Multiple Latent Variables

Effective and efficient video retrieval has become a pressing need in the “big video” era. The objective of this work is to provide a principled model for computing the ranking scores of a video in response to one or more concepts, where the concepts could be directly supplied by users or inferred by the system from the user queries. Indeed, how to deal with multi-concept queries has become a central component in modern video retrieval systems that accept text queries. However, it has been long overlooked and simply implemented by weighted averaging of the corresponding concept detectors’ scores. Our approach, which can be considered as a latent ranking SVM, integrates the advantages of various recent works in text and image retrieval, such as choosing ranking over structured prediction, modeling inter-dependencies between querying concepts, and so on. Videos consist of shots, and we use latent variables to account for the mutually complementary cues within and across shots. Concept labels of shots are scarce and noisy. We introduce a simple and effective technique to make our model robust to outliers. Our approach gives superior performance when it is tested on not only the queries seen at training but also novel queries, some of which consist of more concepts than the queries used for training.

Application of Artificial Immune Recognition System for Identification of Advertisement Video Frames using BICC Features

Objectives: In this present study, there are various methods and techniques that are reviewed to dig the hidden information from the video frames to process the live stream Television (TV) videos. Video classification is an emerging trend that is intended to classify the Advertisement (ADD) videos from the television programme. Classification of ADD videos from the general programs provides an efficient approach to manage and utilize the ADD video data. Detection of ADD video plays a major role for advertisement content management, advertisement for targeted customers, querying, retrieving, inserting, and skipping the advertisement to view the desired channels. Detection of advertisement frames creates a unique application in the multimedia systems. Methods/Analysis: The process of feature extraction which enables recognition of ADD videos and Non Advertisement (NADD) videos directly from the TV streams are discussed. The features are extracted using Block Intensity Comparison Code (BICC) technique. BICC technique is applied on various block sizes of a frame and the best performing block size 8×8 has been chosen for the experimental study. Decision tree (J48) algorithm and BICC feature are utilized to find out the promising block size of the frame. The best features are identified and selected by decision tree (J48) algorithm. Artificial Immune Recognition System (AIRS) is applied on these features to classify the ADD class and NADD class. The AIRS classification algorithms are motivated by the biological immune system components that include important and unique abilities. These algorithms recreate the specialities of the immune framework like; discrimination, learning, and the memorizing methodology in place are utilized to classification and pattern recognition. AIRS2 algorithm is parallelism, separating the dataset into number segments and handling them exclusively. Findings: In this study, three versions of AIRS algorithms, namely, AIRS1, AIRS2 and AIRS2 parallel are used for classification with BICC feature. AIRS2 parallel classifier performed better compared with AIRS1 and AIRS2. The present study proved the biological immune recognition based AIRS algorithm out performs than various classifiers in terms of reliability and classification accuracy. The classification capability and the efficiency of AIRS2 parallel algorithm with BICC feature has been compared among various classifiers and reported. Application/Improvements: This study is very much helpful and essential for television viewers and the busy current generation to skip the nuisance of advertisements to enjoy watching their favourable shows of various television channels. The proposed work is useful for demands on video and video content management systems. This work can also be extended with novel feature set to improve the classifiers performance for efficient video classification and retrieval systems.

State of the Art: A Summary of Semantic Image and Video Retrieval Techniques

Our paper comprises of almost maximum used state of the art techniques in video retrieval as a brief summary. As there is developments in all fields, media becomes more popular and so people begun to search videos to know the world happenings visually. This paper gives a review of existed combinational methods, algorithms and techniques. The image retrieval was obtained from multiple lower ranking methods. The survey of many methods leads to an introduction of combination of a best method. The main focus of this survey is focused on video retrieval techniques to identify the underlying factors that affect the performance of the combinational method and to judge the effectiveness to provide efficient semantic video retrieval. Finally we descript a broad discussion about the advantages and drawbacks that have been in state of the art. Due to these reasons semantic video retrieval became a challenging issue in various industries.

Video Data Model and Retrieval Service Framework Using Geographic Information

AbstractAlong with a rapid growth in the volume of user‐generated video clips, efficient video retrieval methods have become one of the most critical challenges in multimedia management. In this article, we propose a service framework using geographic information for retrieval of the videos on the web. The main idea is to describe and query videos by video‐related geographic data such as video location, field of view and trajectory. Based on the point, line and polygon description for videos, we define the commonly used video retrieval methods. A video retrieval service framework and the service interfaces are designed based on the REST architecture. A prototype system is also implemented to test the services. The experiment shows that the proposed video description, retrieval methods and web services are feasible and useful. We believe that the integration of geographical video retrieval methods into existing methods will promote the geo‐tagged video sharing, discovery and consumption in various web applications.

Low-complexity range tree for video synopsis system

This work proposes an efficient video retrieval technique for video synopsis. In a video system, the Region of Interest (ROI) should be extracted in a long video effectively such that users can browse it quickly and easily. Focusing on the characteristics of objects in the foreground of real-world video sequences, this work employs the Gaussian Mixture Model (GMM) and color-histograms for object detection. In order to reduce the search time, a new video synopsis search approach, a low-complexity range tree algorithm, is proposed to improve the effectiveness of searches for objects of interest matching pre-set conditions. With the time and space redundancy-reducing techniques of video synopsis, the objects of interest can be displayed within a short time. Objects and events can be found and displayed quickly without allocating time to watching non-ROIs. For the test video sequences, the results show an accuracy rate of 97 % and a processing speed of 32 FPS (frames per second) in the online phase, and the time complexity of object searching is reduced from O(N) to O(logD-1N).

Rank-mediated collaborative tagging recommendation service using video-tag relationship prediction

A great many tags and videos are shared and created by a mass of distributors on Web 2.0 video sharing sites. This increasing user-generated content can further benefit service innovation of collaborative tagging. In order to enhance efficient video retrieval and online video marketing (OVM) application, this research proposes a rank-mediated collaborative tagging recommendation service that allows the distributors predicting the ranks of video retrieval from the shared video archive using vote-promotion algorithm (VPA). The system experiments evaluate the number of tags and videos between simple text retrieval and VPA. The user surveys verify the relevance, helpfulness, and satisfaction of the recommended tags. From the perspectives of service innovation, this research is to develop a systematic and quantified a video-tag relationship prediction and recommendation self-service that can provide an intelligent collaborative tagging service on video sharing sites.

A spatio-temporal pyramid matching for video retrieval

An efficient video retrieval system is essential to search relevant video contents from a large set of video clips, which typically contain several heterogeneous video clips to match with. In this paper, we introduce a content-based video matching system that finds the most relevant video segments from video database for a given query video clip. Finding relevant video clips is not a trivial task, because objects in a video clip can constantly move over time. To perform this task efficiently, we propose a novel video matching called Spatio-Temporal Pyramid Matching (STPM). Considering features of objects in 2D space and time, STPM recursively divides a video clip into a 3D spatio-temporal pyramidal space and compares the features in different resolutions. In order to improve the retrieval performance, we consider both static and dynamic features of objects. We also provide a sufficient condition in which the matching can get the additional benefit from temporal information. The experimental results show that our STPM performs better than the other video matching methods.

Fast and Accurate Video Retrieval of a DVR Special-Purpose File System

Based on the characteristics of video storage, this paper analyzes the shortages of existing file system in video application. Then a DVR (Digital Video Recorder) special-purpose file system is proposed. In this special file system efficient video storage and retrieval can be achieved. Video pictures of specified time can be positioned quickly and accurately.

A smart atlas for endomicroscopy using automated video retrieval

To support the challenging task of early epithelial cancer diagnosis from in vivo endomicroscopy, we propose a content-based video retrieval method that uses an expert-annotated database. Motivated by the recent successes of non-medical content-based image retrieval, we first adjust the standard Bag-of-Visual-Words method to handle single endomicroscopic images. A local dense multi-scale description is proposed to keep the proper level of invariance, in our case to translations, in-plane rotations and affine transformations of the intensities. Since single images may have an insufficient field-of-view to make a robust diagnosis, we introduce a video-mosaicing technique that provides large field-of-view mosaic images. To remove outliers, retrieval is followed by a geometrical approach that captures a statistical description of the spatial relationships between the local features. Building on image retrieval, we then focus on efficient video retrieval. Our approach avoids the time-consuming parts of the video-mosaicing by relying on coarse registration results only to account for spatial overlap between images taken at different times. To evaluate the retrieval, we perform a simple nearest neighbors classification with leave-one-patient-out cross-validation. From the results of binary and multi-class classification, we show that our approach outperforms, with statistical significance, several state-of-the art methods. We obtain a binary classification accuracy of 94.2%, which is quite close to clinical expectations.

Special issue on dynamic textures in video

Two-dimensional textures in images have been extensively studied in the past. On the other hand, there is comparatively limited research on three-dimensional dynamic textures that exhibit certain time-varying properties in video. In many scenes there are regions having significant structural similarity and exhibit high temporal correlations between image frames forming the video [1]. A tree swaying in the wind or a wave lapping on a beach is not just a collection of randomly shuffled appearances, but a physical system that has characteristic responses associated with its dynamics. Examples of such dynamic phenomena include flames, smoke, sea, waves, clouds, fog, crowds in public places and sports events, some human movements, and even shadows [1–9]. It is known that dynamic textures, especially for outdoor scenes, cause major problems in motion detection and analysis tasks. Besides, they drastically decrease the coding efficiency of video encoders although they do not contain any useful and discriminative information. They complicate motion-based object recognition methods. By segmenting and excluding dynamic textures, the robustness of the moving object detection and action identification can be improved. Other practical applications include detection of certain types of dynamic textures such as fire and smoke, realistic rendering and compact visualization of dynamic textures, and efficient retrieval of video in multimedia databases. The

장면전환검출을 이용한 교양비디오 개요 검색 시스템

본 논문에서는 교양 비디오 데이터베이스 시스템을 구축하기 위한 비디오 모델을 제안한다. 먼저, 교양 비디오의 효율적인 색인화와 검색을 위하여 교양 비디오를 의미 있는 단위로 분할하는 효율적인 장면 전환 검출 기법을 사용하였다 비디오가 대용량이며 장시간의 재생이 필요하다는 특징 때문에 전체 비디오를 시청해야하는 문제점이 있다. 이 문제점을 해결하기 위해 교양 비디오의 개요를 추출하여 시청자들에게 시간을 절약할 수 있고, 비디오 선택의 폭을 넓히도록 하였다. 비디오 개요는 개요 생성 규칙을 설정하여 중요 이벤트가 발생한 장면들을 요약한 형태이다. This paper proposes a video model for the implementation of the cultural video database system. We have utilized an efficient scene change detection method that segments cultural video into semantic units for efficient indexing and retrieval of video. Since video has a large volume and needs to be played for a longer time, it implies difficulty of viewing the entire video. To solve this Problem. the cultural video abstraction was made to save the time and widen the choices of video the video abstract is the summarization of scenes, which includes important events produced by setting up the abstraction rule.

A hard disk drive embedded digital satellite receiver with scene change detector for video indexing

We present a hard disk drive embedded digital satellite receiver with a scene change detector for video indexing. We implement a scene change detection algorithm in the compressed domain for low computing power systems. This receiver can store, retrieve and manage the broadcast data by implementing an interface between the conventional digital satellite receiver and digital storage media. In addition, this receiver gives users an ability to search the scene change position by implementing a scene change detection algorithm. The detected temporal video segments are stored in the HDD and retrieved when users want them. The user can obtain more information for efficient video retrieval, using this proposed system.

Indexing and retrieval of the MPEG compressed video

To keep pace with the increased popularity of digital video as an archival medium, the development of techniques for fast and efficient analysis of video streams is essential. In particular, solutions to the problems of storing, indexing, browsing, and retrieving video data from large multimedia databases are necessary to allow access to these collections. Given that video is often stored efficiently in a compressed format, the costly overhead of decompression can be reduced by analyzing the compressed representation directly. In earlier work, we presented compressed domain parsing techniques which identified shots, subshots, and scenes. In this article, we present efficient key frame selection, feature extraction, indexing, and retrieval techniques that are directly applicable to MPEG compressed video. We develop a frame type independent representation which normalizes spatial and temporal features including frame type, frame size, macroblock encoding, and motion compensation vectors. Features for indexing are derived directly from this representation and mapped to a low-dimensional space where they can be accessed using standard database techniques. Spatial information is used as primary index into the database and temporal information is used to rank retrieved clips and enhance the robustness of the system. The techniques presented enable efficient indexing, querying, and retrieval of compressed video as demonstrated by our system which typically takes a fraction of a second to retrieve similar video scenes from a database, with over 95% recall.