Search

The amount of audio visual content kept in networked repositories has increased dramatically in recent years. Many video hosting websites exist, such as YouTube, Metacafe, and Google Video. Currently, indexing and categorising these videos is a time-consuming task. The system either asks the user to provide tags for the videos they submit, or manual labelling is used. The aim of this research is to develop a classifier that can accurately identify videos. Every video has content that is either visual, audio, or text. Researchers categorised the videos based on any of these three variables. With the Pattern Change with Size Invariance (PCSI) algorithm, this study provides a hybrid model that takes into account all three components of the video: audio, visual, and textual content. This study tries to classify videos into broad categories such as education, sports, movies, and amateur videos. Key feature extraction and pattern matching would be used to accomplish this. A fuzzy logic and ranking system would be used to assign the tag to the video. The proposed system is tested only on a virtual device in addition a legitimate distributed cluster for the aim of reviewing real-time performance, especially once the amount and duration of films are considerable. The efficiency of video retrieval is measured with metrics like accuracy, precision, and recall is over 99% success. [ABSTRACT FROM AUTHOR]

Within the exponential growth in raw data production, attributed in no small part to social media - Facebook, Youtube, and others. Video is proving to be the most important data type thanks to the substantial amount of raw data it contains, requiring an efficient way to be understood, organized, structured, and stored for ease of retrieval. Hence, an efficient video indexing architecture is thus crucial for video datasets. This paper proposes an efficient Multi-Object Semantic Video Detection (MOSD) that leverages the deep learning power to achieve effective indexing on the semantic concept level. MOSD is multi-detection network of video semantics in multiple frames. MOSD exploits a 3D convolution operation to do multiple detections among multiple frames with higher performance. The detected semantics then structured and used for indexing the video segments. MOSD has been trained and evaluated on ImageNet VID dataset and has been compared to peers. MOSD showed efficiency in exploiting the temporal context of a video to do simultaneous detections of consecutive frames which speeds up the detection of semantic objects. MOSD also showed performance efficiency in terms of mAP which is 85.2%. [ABSTRACT FROM AUTHOR]

Numerous researches on content-based video indexing and retrieval besides video search engines are tied to a large-scaled video dataset. Unfortunately, reduction in open-sourced datasets resulted in complications for novel approaches exploration. Although, video datasets that index video files located on public video streaming services have other purposes, such as annotation, learning, classification, and other computer vision areas, with little interest in indexing public video links for purpose of searching and retrieval. This paper introduces a novel large-scaled dataset based on YouTube video links to evaluate the proposed content-based video search engine, gathered 1088 videos, that represent more than 65 hours of video, 11,000 video shots, and 66,000 unmarked and marked keyframes, 80 different object names used for marking. Moreover, a state-of-the-art features vector, and combinational-based matching, beneficial to the accuracy, speed, and precision of the video retrieval process. Any video record in the dataset is represented by three features: temporal combination vector, object combination vector with shot annotations, and 6 keyframes, sideways with other metadata. Video classification for the dataset was also imposed to expand the efficiency of retrieval of video-based queries. A two-phased approach has been used based on object and event classification, storing video records in aggregations related to feature vectors extracted. While object aggregation stores video records with the maximal occurrence of extracted object/concept from all shots, event aggregation classify based on groups according to the number of shots per video. This study indexed 58 out of 80 different object/concept categories, each has 9 shot number groups. [ABSTRACT FROM AUTHOR]

Videos are used often for communicating ideas, concepts, experience, and situations, because of the significant advances made in video communication technology. The social media platforms enhanced the video usage expeditiously. At, present, recognition of a video is done, using the metadata like video title, video descriptions, and video thumbnails. There are situations like video searcher requires only a video clip on a specific topic from a long video. This paper proposes a novel methodology for the analysis of video content and using video storytelling and indexing techniques for the retrieval of the intended video clip from a long duration video. Video storytelling technique is used for video content analysis and to produce a description of the video. The video description thus created is used for preparation of an index using wormhole algorithm, guarantying the search of a keyword of definite length L, within the minimum worst-case time. This video index can be used by video searching algorithm to retrieve the relevant part of the video by virtue of the frequency of the word in the keyword search of the video index. Instead of downloading and transferring a whole video, the user can download or transfer the specifically necessary video clip. The network constraints associated with the transfer of videos are considerably addressed. [ABSTRACT FROM AUTHOR]

Multi-view hashing can well support large-scale near-duplicate video retrieval, due to its desirable advantages of mutual reinforcement of multiple features, low storage cost, and fast retrieval speed. However, there are still two limitations that impede its performance. First, existing methods only consider local structures in multiple features. They ignore the global structure that is important for near-duplicate video retrieval, and cannot fully exploit the dependence and complementarity of multiple features. Second, existing works always learn hashing functions bit by bit, which unfortunately increases the time complexity of hash function learning. In this paper, we propose a supervised hashing scheme, termed as joint multi-view hashing (JMVH), to address the aforementioned problems. It jointly preserves the global and local structures of multiple features while learning hashing functions efficiently. Specially, JMVH considers features of video as items, based on which an underlying Hamming space is learned by simultaneously preserving their local and global structures. In addition, a simple but efficient multi-bit hash function learning based on generalized eigenvalue decomposition is devised to learn multiple hash functions within a single step. It can significantly reduce the time complexity of conventional hash function learning processes that sequentially learn multiple hash functions bit by bit. The proposed JMVH is evaluated on two public databases: CC_WEB_VIDEO and UQ_VIDEO. Experimental results demonstrate that the proposed JMVH achieves more than a 5 percent improvement compared to several state-of-the-art methods which indicates the superior performance of JMVH. [ABSTRACT FROM AUTHOR]

Rapid growth in storage technology and data acquisition has significantly increased the volume of multimedia data online. A challenging problem is to analyze that multimedia data which are in massive quantity. In recent years, indexing of video files based on contents has gained increased popularity in research community. There are also attempts at identifying if a video clip is containing a specific genre of video, e.g., an sports video, movie, drama, animation or talk show. These proposed techniques, however, use a long list of audio visual features in achieving this classification task, which obviously decreases processing efficiency. Based on certain patterns in audio visual features and basic grammar of talk show, this research differentiates multimedia contents of talk shows from rest of the video genres. Our multimodal rule-based classification approach exploits shots and scenes in a video as classification features. The contents from popular multimedia databases like DailyMotion, YouTube and movies from Hollywood and Bollywood are used as dataset to test overall system of genre identification. The system achieves precision and recall of 98% and 100%, respectively, on 600 selected videos of more than 600 h of duration to classify multimedia content as either 'TalkShow' or 'OtherVideo' category. [ABSTRACT FROM AUTHOR]

In this paper, we propose a new approach to monitor a solar plant in real-time using an embedded vision system, comprised mainly of raspberry Pi3 card, GPS and thermometer sensors, and an HD camera module. This approach consists on using image processing techniques on solar energy fields. It is implemented on two steps, the first apply the digital watermarking technique based on discrete cosine transform (DCT) to indexing a captured video. We start by capturing all information from the solar plant (GPS coordinates, temperature, date, and time), then we embed on each video frame their related data. This method depends on transforming the video frames from the spatial to the frequency domain using DCT and embedding data in 8 × 8 block coefficients. The second step consists on applying a mosaicing techniques based on the scale invariant features transform (SIFT), in order to generate a panoramic image of the solar plant from video frames. Remotely, the supervisor can visualize the image of the whole, part, or panel of the solar plant, and exploits the embedded data to ensure an efficient real-time monitoring. The proposed method allows a high efficiency in terms of accuracy, data security, and retrieving data quickly, also it offers a high capacity, less imperceptibility and good robustness. [ABSTRACT FROM AUTHOR]

In the field of shot boundary detection the fundamental step is video content analysis towards video indexing, summarization and retrieval as to be carried out for video cloud based applications. However, there are several beneficial in the previous work; reliable detection of video shot is still a challenging issue. In this paper the focus is carried out on the problem of gradual transition detection from video. The proposed approach is fuzzy-rule based system with gradual identification and a set of fuzzy rules are evaluated with dissolve and wipes (fad-in and fad-out) during gradual transition. First, extracting the features from the video frames then applying the fuzzy rules in to the frames for identifying the gradual transitions. The main advantage of the proposed method is its level of accuracy in the gradual detection getting increased. Also, the existing gradual detection algorithms are mainly based on the threshold component, but the proposed method is rule based. The proposed method is evaluated on variety of video sequences from different genres and compared with existing techniques from the literature. Experimental results proved for its effectiveness on calculating performance in terms of the precision and recall rates. [ABSTRACT FROM AUTHOR]

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. [ABSTRACT FROM AUTHOR]

Motion vectors (MVs) are the most common temporal descriptors in video analysis, indexing and retrieval applications. However, video indexing and analysis based on MVs do not perform well for videos at different dimension ratios (DRs) or even various resolutions. As a result, video indexing and analysis which are based on identifying similar video face with many difficulties at different DRs or resolutions by MVs. In this study, a two‐stage algorithm is introduced to make MV descriptors robust against variations first in DR and then at resolution. In the experiments performed on motion vector histograms, the proposed method improves the performance on identifying similar videos at various spatial specifications by up to 73%. Moreover, in the video retrieval experiments, the proposed modified MV outperforms original MV feature vector. This is an indication of improvement in differentiation of similar and dissimilar videos by the proposed temporal feature vector. [ABSTRACT FROM AUTHOR]

This is the era of video surveillance, not just security. The arrival of inexpensive surveillance cameras and increasing demands of security has caused an explosive growth of surveillance videos, which are used by government or other organizations for prevention or investigation of crime. As browsing such lengthy videos is very time consuming, most of the videos are never watched and analyzed. The video synopsis is a technique to represent such lengthy videos in a condensed way by showing multiple activities simultaneously. The purpose of this paper is to explore development stages, various algorithms of it, framework and tools used to implement them, challenges and limitations of existing video synopsis techniques and its application in the field of surveillance video analysis. [ABSTRACT FROM AUTHOR]

Knowledge extraction is one of the fastest growing fields today. Proper extraction of the needed information presents a challenging job for many researchers. This becomes even more complicated in the case of multimedia content. Clustering is a useful technique for finding useful patterns from the given data set. Video clustering is done on video files for video data mining. Existing clustering techniques works well for only a few particular types of inputs. It has been experimentally verified that the proposed clustering technique offers the best clustering solution for a majority of input files. [ABSTRACT FROM AUTHOR]

Detecting and locating a desired information in hefty amount of video data through manual procedure is very cumbersome. This necessitates segregation of large video into shots and finding the boundary between the shots. But shot boundary detection problem is unable to achieve satisfactory performance for video sequences consisting of flash light and complex object/camera motion. The proposed method is intended for recognising abrupt boundary between shots in the presence of motion and illumination change in an automatic way. Typically any scene change detection algorithm assimilates time separation in a shot resemblance metric. In this communication, absolute sum gradient orientation feature difference is matched to automatically generated threshold for sensing a cut. Experimental study on TRECVid 2001 data set and other publicly available data set certifies the potentiality of the proposed scheme that identifies scene boundaries efficiently, in a complex environment while preserving a good trade-off between recall and precision measure. [ABSTRACT FROM AUTHOR]

Event discovery aims to discover a temporal segment of interest, such as human behavior, actions or activities. Most approaches to event discovery within or between time series use supervised learning. This becomes problematic when relevant event labels are unknown, are difficult to detect, or not all possible combinations of events have been anticipated. To overcome these problems, this paper explores Common Event Discovery (CED), a new problem that aims to discover common events of variable-length segments in an unsupervised manner. A potential solution to CED is searching over all possible pairs of segments, which would incur a prohibitive quartic cost. In this paper, we propose an efficient branch-and-bound (B&B) framework that avoids exhaustive search while guaranteeing a globally optimal solution. To this end, we derive novel bounding functions for various commonality measures and provide extensions to multiple commonality discovery and accelerated search. The B&B framework takes as input any multidimensional signal that can be quantified into histograms. A generalization of the framework can be readily applied to discover events at the same or different times (synchrony and event commonality, respectively). We consider extensions to video search and supervised event detection. The effectiveness of the B&B framework is evaluated in motion capture of deliberate behavior and in video of spontaneous facial behavior in diverse interpersonal contexts: interviews, small groups of young adults, and parent-infant face-to-face interaction. [ABSTRACT FROM AUTHOR]

Videos of classroom lectures have proven to be a popular and versatile learning resource. A key shortcoming of the lecture video format is accessing the content of interest hidden in a video. This work meets this challenge with an advanced video framework featuring topical indexing, search, and captioning (ICS videos). Standard optical character recognition (OCR) technology was enhanced with image transformations for extraction of text from video frames to support indexing and search. The images and text on video frames is analyzed to divide lecture videos into topical segments. The ICS video player integrates indexing, search, and captioning in video playback providing instant access to the content of interest. This video framework has been used by more than 70 courses in a variety of STEM disciplines and assessed by more than 4000 students. Results presented from the surveys demonstrate the value of the videos as a learning resource and the role played by videos in a students learning process. Survey results also establish the value of indexing and search features in a video platform for education. This paper reports on the development and evaluation of ICS videos framework and over 5 years of usage experience in several STEM courses. [ABSTRACT FROM AUTHOR]

Various content-based methods (e.g., audio-visual feature recognition and dialogs analysis) have been proposed for analyzing, indexing and understanding movies. Our previous approach introduced a method for character indexing based on manual annotation. However, this method has shown several unsatisfactoriness on performing of indexing. For addressing this issue, in this work, we take into account using image processing techniques for semi-automatically character-based indexing. Besides, a movie ontological model is created for connecting character appearances and character's roles in the movie. Moreover, we propose a system for assist user indexing manually. On the other hand, a searching and browsing tool is also introduced. Using this tool, user can query character-based semantic indexing. Experimental results are shown that our proposed method is able to assist user in consuming index time and providing a method for automatic indexing, searching and browsing based on semantic queries. [ABSTRACT FROM AUTHOR]

Video containment queries find the videos that have similar sequence of frames to query video clips. Applying sequence matching to all possible subsequences for video containment queries is computationally expensive for large volumes of video data. In this paper, we propose an efficient candidate segment selection scheme, which selects only a small set of subsequences to be matched to the query sequence, by using a cluster of similar frames, called a frame cluster. We also propose a new type of the ordinal feature, called a composite ordinal feature that allows multiple ranks to certain cells. In experiments with large scale video data sets, we show our method improves the query response time by efficiently selecting a set of subsequences for sequence matching. [ABSTRACT FROM AUTHOR]

A video retrieval system user hopes to find relevant information when the proposed queries are ambiguous. The retrieval process based on detecting concepts remains ineffective in such a situation. Potential relationships between concepts have been shown as a valuable knowledge resource that can enhance the retrieval effectiveness, even for ambiguous queries. Recent researches in multimedia retrieval have focused on ontology modeling as a common framework to manage knowledge. Handling these ontologies has to cope with issues related to generic knowledge management and processing scalability. Considering these issues, we suggest a context-based fuzzy ontology framework for video content analysis and indexing. In this paper, we focused on the way in which we modeled our fuzzy ontology: First, we populate automatically the generated ontology by gathering various available video annotation datasets. Then, the ontology content was used to infer enhanced video semantic interpretation. Finally, considering user feedback, the content of the ontology was improved. Experimental results showed that our approach achieves the goal of scalability while at the same time allowing better video content semantic interpretation. [ABSTRACT FROM AUTHOR]

To manipulate large video contents, effective video indexing and retrieval are required. A large number of video indexing and retrieval algorithms have been presented for frame-wise user query or video content query whereas a relatively few video sequence matching algorithms have been proposed for video sequence query. In this paper, we propose an efficient algorithm that extracts key frames using color histograms and matches the video sequences using edge features. To effectively match video sequences with a low computational load, we make use of the key frames extracted by the cumulative measure and the distance between key frames, and compare two sets of key frames using the modified Hausdorff distance. Experimental results with real sequence show that the proposed video sequence matching algorithm using edge features yields the higher accuracy and performance than conventional methods such as histogram difference, Euclidean metric, Battachaya distance, and directed divergence methods. [ABSTRACT FROM AUTHOR]

This paper presents a novel multimedia information system, called SAPTE, for supporting the discourse analysis and information retrieval of television programs from their corresponding video recordings. Unlike most common systems, SAPTE uses both content independent and dependent metadata, which are determined by the application of discourse analysis techniques as well as image and audio analysis methods. The proposed system was developed in partnership with the free-to-air Brazilian TV channel Rede Minas in an attempt to provide TV researchers with computational tools to assist their studies about this media universe. The system is based on the Matterhorn framework for managing video libraries, combining: (1) discourse analysis techniques for describing and indexing the videos, by considering aspects, such as, definitions of the subject of analysis, the nature of the speaker and the corpus of data resulting from the discourse; (2) a state of the art decoder software for large vocabulary continuous speech recognition, called Julius; (3) image and frequency domain techniques to compute visual signatures for the video recordings, containing color, shape and texture information; and (4) hashing and k-d tree methods for data indexing. The capabilities of SAPTE were successfully validated, as demonstrated by our experimental results, indicating that SAPTE is a promising computational tool for TV researchers. [ABSTRACT FROM AUTHOR]

This paper presents a method to automatically detect slide changes in lecture videos. For accurate detection, the regions capturing slide images are first identified from video frames. Then, SIFT features are extracted from the regions, which are invariant to image scaling and rotation. These features are used to compare similarity between frames. If the similarity is smaller than a threshold, slide transition is detected. The threshold is estimated based on the mean and standard deviation of sample frames' similarities. Using this method, high detection accuracy can be obtained without any supplementary slide images. The proposed method also supports detection of backward slide transitions that occur when a speaker returns to a previous slide to emphasize its contents. In experiments conducted on our test collection, the proposed method showed 87 % accuracy in forward transition detection and 86 % accuracy in backward transition detection. [ABSTRACT FROM AUTHOR]

The research context of this article is the recognition and description of dynamic textures. In image processing, the wavelet transform has been successfully used for characterizing static textures. To our best knowledge, only two works are using spatio-temporal multiscale decomposition based on the tensor product for dynamic texture recognition. One contribution of this article is to analyze and compare the ability of the 2D+T curvelet transform, a geometric multiscale decomposition, for characterizing dynamic textures in image sequences. Two approaches using the 2D+T curvelet transform are presented and compared using three new large databases. A second contribution is the construction of these three publicly available benchmarks of increasing complexity. Existing benchmarks are either too small not available or not always constructed using a reference database. Feature vectors used for recognition are described as well as their relevance, and performances of the different methods are discussed. Finally, future prospects are exposed. [ABSTRACT FROM AUTHOR]

Video indexing is employed to represent the features of video sequences. Motion vectors derived from compressed video are preferred for video indexing because they can be accessed by partial decoding; thus, they are used extensively in various video analysis and indexing applications. In this study, we introduce an efficient compressed domain video indexing method and implement it on the H.264/AVC coded videos. The video retrieval experimental evaluations indicate that the video retrieval based on the proposed indexing method outperforms motion vector based video retrieval in 74 % of queries with little increase in computation time. Furthermore, we compared our method with a pixel level video indexing method which employs both temporal and spatial features. Experimental evaluation results indicate that our method outperforms the pixel level method both in performance and speed. Hence considering the speed and precision characteristics of indexing methods, the proposed method is an efficient indexing method which can be used in various video indexing and retrieval applications. [ABSTRACT FROM AUTHOR]

This paper presents a method for indexing activities of daily living in videos acquired from wearable cameras. It addresses the problematic of analyzing the complex multimedia data acquired from wearable devices, which has been recently a growing concern due to the increasing amount of this kind of multimedia data. In the context of dementia diagnosis by doctors, patient activities are recorded in the environment of their home using a lightweight wearable device, to be later visualized by the medical practitioners. The recording mode poses great challenges since the video data consists in a single sequence shot where strong motion and sharp lighting changes often appear. Because of the length of the recordings, tools for an efficient navigation in terms of activities of interest are crucial. Our work introduces a video structuring approach that combines automatic motion based segmentation of the video and activity recognition by a hierarchical two-level Hidden Markov Model. We define a multi-modal description space over visual and audio features, including mid-level features such as motion, location, speech and noise detections. We show their complementarities globally as well as for specific activities. Experiments on real data obtained from the recording of several patients at home show the difficulty of the task and the promising results of the proposed approach. [ABSTRACT FROM AUTHOR]

Music and songs are integral parts of Bollywood movies. Every movie of two to three hours, contains three to ten songs, each song is 3-10 min long. Music lovers like to listen music and songs of a movie, however it is time consuming and error prone to search manually all the songs in a movie. Moreover, the task becomes much harder when songs are to be extracted from a huge archived movies' database containing hundreds of movies. This paper presents an approach to automatically extract music and songs from archived musical movies. We used song grammar to construct Markov Chain Model that differentiates song scenes from dialogue and action scenes in a movie. We tested our system on Bollywood, Hollywood, Pakistani, Bengali, and Tamil movies. A total of 20 movies from different industries were selected for the experiments. On Bollywood movies, we achieved 97.22% recall in song extraction, whereas the recall on Hollywood musical movies is 80%. The test result on Pakistani, Tamil and Bengali movies is 87.09%. [ABSTRACT FROM AUTHOR]

Text displayed in a video is an essential part for the high-level semantic information of the video content. Therefore, video text can be used as a valuable source for automated video indexing in digital video libraries. In this paper, we propose a workflow for video text detection and recognition. In the text detection stage, we have developed a fast localization-verification scheme, in which an edge-based multi-scale text detector first identifies potential text candidates with high recall rate. Then, detected candidate text lines are refined by using an image entropy-based filter. Finally, Stroke Width Transform (SWT)- and Support Vector Machine (SVM)-based verification procedures are applied to eliminate the false alarms. For text recognition, we have developed a novel skeleton-based binarization method in order to separate text from complex backgrounds to make it processible for standard OCR ( Optical Character Recognition) software. Operability and accuracy of proposed text detection and binarization methods have been evaluated by using publicly available test data sets. [ABSTRACT FROM AUTHOR]

Audio-Visual People Diarization (AVPD) is an original framework that simultaneously improves audio, video, and audiovisual diarization results. Following a literature review of people diarization for both audio and video content and their limitations, which includes our own contributions, we describe a proposed method for associating both audio and video information by using co-occurrence matrices and present experiments which were conducted on a corpus containing TV news, TV debates, and movies. Results show the effectiveness of the overall diarization system and confirm the gains audio information can bring to video indexing and vice versa. [ABSTRACT FROM AUTHOR]

Near-duplicate video retrieval (NDVR) has recently attracted much research attention due to the exponential growth of online videos. It has many applications, such as copyright protection, automatic video tagging and online video monitoring. Many existing approaches use only a single feature to represent a video for NDVR. However, a single feature is often insufficient to characterize the video content. Moreover, while the accuracy is the main concern in previous literatures, the scalability of NDVR algorithms for large scale video datasets has been rarely addressed. In this paper, we present a novel approach—Multiple Feature Hashing (MFH) to tackle both the accuracy and the scalability issues of NDVR. MFH preserves the local structural information of each individual feature and also globally considers the local structures for all the features to learn a group of hash functions to map the video keyframes into the Hamming space and generate a series of binary codes to represent the video dataset. We evaluate our approach on a public video dataset and a large scale video dataset consisting of 132,647 videos collected from YouTube by ourselves. This dataset has been released (http://itee.uq.edu.au/shenht/UQ_VIDEO/). The experimental results show that the proposed method outperforms the state-of-the-art techniques in both accuracy and efficiency. [ABSTRACT FROM PUBLISHER]

We propose an efficient real-time automatic license plate recognition (ALPR) framework, particularly designed to work on CCTV video footage obtained from cameras that are not dedicated to the use in ALPR. At present, in license plate detection, tracking and recognition are reasonably well-tackled problems with many successful commercial solutions being available. However, the existing ALPR algorithms are based on the assumption that the input video will be obtained via a dedicated, high-resolution, high-speed camera and is/or supported by a controlled capture environment, with appropriate camera height, focus, exposure/shutter speed and lighting settings. However, typical video forensic applications may require searching for a vehicle having a particular number plate on noisy CCTV video footage obtained via non-dedicated, medium-to-low resolution cameras, working under poor illumination conditions. ALPR in such video content faces severe challenges in license plate localization, tracking and recognition stages. This paper proposes a novel approach for efficient localization of license plates in video sequence and the use of a revised version of an existing technique for tracking and recognition. A special feature of the proposed approach is that it is intelligent enough to automatically adjust for varying camera distances and diverse lighting conditions, a requirement for a video forensic tool that may operate on videos obtained by a diverse set of unspecified, distributed CCTV cameras. [ABSTRACT FROM AUTHOR]

Video indexing, also called video concept detection, has attracted increasing attentions from both academia and industry. To reduce human labeling cost, active learning has been introduced to video indexing recently. In this paper, we propose a novel active learning approach based on the optimum experimental design criteria in statistics. Different from existing optimum experimental design, our approach simultaneously exploits sample's local structure, and sample relevance, density, and diversity information, as well as makes use of labeled and unlabeled data. Specifically, we develop a local learning model to exploit the local structure of each sample. Our assumption is that for each sample, its label can be well estimated based on its neighbors. By globally aligning the local models from all the samples, we obtain a local learning regularizer, based on which a local learning regularized least square model is proposed. Finally, a unified sample selection approach is developed for interactive video indexing, which takes into account the sample relevance, density and diversity information, and sample efficacy in minimizing the parameter variance of the proposed local learning regularized least square model. We compare the performance between our approach and the state-of-the-art approaches on the TREC video retrieval evaluation (TRECVID) benchmark. We report superior performance from the proposed approach. [ABSTRACT FROM PUBLISHER]

Copyright of Journal of Decision Systems is the property of Taylor & Francis Ltd and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

As the quantity of publicly available multimedia material becomes larger and larger, automatic indexing becomes increasingly important in accessing multimedia databases. In this paper, a novel set of low-level descriptors is presented for the aim of content-based video classification. Concerning temporal features, we use a modified PMES descriptor for the spatial distribution of local motion and a Dominant Direction Histogram we have developed to represent the temporal distribution of camera motion. Concerning color, we present the Weighted Color Histogram we have designed in order to model color distribution. The histogram models the H parameter of the HSV color space, and we combine it with weighted means for the S and V parameters. For the selection of key-frames from which to extract the spatial descriptors we use a modified version of a simple efficient method. We then proceed to evaluate our descriptor set on a database of video shots resulting from the temporal segmentation of the archive of a real-world TV station. Results demonstrate that our approach can achieve high success rates on a wide range of semantic classes. [ABSTRACT FROM AUTHOR]

This paper presents a new learning algorithm for audiovisual fusion and demonstrates its application to video classification for film database. The proposed system utilized perceptual features for content characterization of movie clips. These features are extracted from different modalities and fused through a machine learning process. More specifically, in order to capture the spatio-temporal information, an adaptive video indexing is adopted to extract visual feature, and the statistical model based on Laplacian mixture are utilized to extract audio feature. These features are fused at the late fusion stage and input to a support vector machine (SVM) to learn semantic concepts from a given video database. Based on our experimental results, the proposed system implementing the SVM-based fusion technique achieves high classification accuracy when applied to a large volume database containing Hollywood movies. [ABSTRACT FROM AUTHOR]

With the phenomenal growth of the online and personal video repositories, an efficient and robust example-based video search solution is required to support applications like query by clip, query by capture, and repeated clip detection. In this letter, video sequences are represented as temporal trajectories via scaling and lower dimensional representation of the video frame luminance field, and a video trajectory indexing and matching scheme is developed to support video clip search. Simulation results demonstrate that the proposed approach achieves excellent performance in both response speed and precision-recall accuracy. [ABSTRACT FROM AUTHOR]

The design and implementation of a client-centered multimedia content adaptation system suitable for a mobile environment comprising of resource-constrained handheld devices or clients is described. The primary contributions of this work are: (1) the overall architecture of the client-centered content adaptation system, (2) a data-driven multi-level Hidden Markov model (HMM)-based approach to perform both video segmentation and video indexing in a single pass, and (3) the formulation and implementation of a Multiple-choice Multidimensional Knapsack Problem (MMKP)-based video personalization strategy. In order to segment and index video data, a video stream is modeled at both the semantic unit level and video program level. These models are learned entirely from training data and no domain-dependent knowledge about the structure of video programs is used. This makes the system capable of handling various kinds of videos without having to manually redefine the program model. The proposed MMKP-based personalization strategy is shown to include more relevant video content in response to the client's request than the existing 0/1 knapsack problem and fractional knapsack problem-based strategies, and is capable of satisfying multiple client-side constraints simultaneously. Experimental results on CNN news videos and Major League Soccer (MLS) videos are presented and analyzed. [ABSTRACT FROM AUTHOR]