85 research outputs found
Predicting Sensitive Relationships from Email Corpus
No full textIn this paper, we focus on the problem of predicting sensitive relationships from Email corpus. We refer to the problem of predicting sensitive relationships from a social network as link re-identification. We propose a predicting sensitive relationships method which has two steps. First step is counting mutual privacy communication. Second step is evaluation cluster factor. Experimental results on Enron email corpus are presented to support our analysis.</p
Crowd Scene Analysis in Video Surveillance
Get PDFThere is an increasing interest in crowd scene analysis in video surveillance due to the ubiquitously deployed video surveillance systems in public places with high density of objects amid the increasing concern on public security and safety. A comprehensive crowd scene analysis approach is required to not only be able to recognize crowd events and detect abnormal events, but also update the innate learning model in an online, real-time fashion. To this end, a set of approaches for Crowd Event Recognition (CER) and Abnormal Event Detection (AED) are developed in this thesis.
To address the problem of curse of dimensionality, we propose a video manifold learning method for crowd event analysis. A novel feature descriptor is proposed to encode regional optical flow features of video frames, where adaptive quantization and binarization of the feature code are employed to improve the discriminant ability of crowd motion patterns. Using the feature code as input, a linear dimensionality reduction algorithm that preserves both the intrinsic spatial and temporal properties is proposed, where the generated low-dimensional video manifolds are conducted for CER and AED.
Moreover, we introduce a framework for AED by integrating a novel incremental and decremental One-Class Support Vector Machine (OCSVM) with a sliding buffer. It not only updates the model in an online fashion with low computational cost, but also adapts to concept drift by discarding obsolete patterns. Furthermore, the framework has been improved by introducing Multiple Incremental and Decremental Learning (MIDL), kernel fusion, and multiple target tracking, which leads to more accurate and faster AED.
In addition, we develop a framework for another video content analysis task, i.e., shot boundary detection. Specifically, instead of directly assessing the pairwise difference between consecutive frames over time, we propose to evaluate a divergence measure between two OCSVM classifiers trained on two successive frame sets, which is more robust to noise and gradual transitions such as fade-in and fade-out. To speed up the processing procedure, the two OCSVM classifiers are updated online by the MIDL proposed for AED.
Extensive experiments on five benchmark datasets validate the effectiveness and efficiency of our approaches in comparison with the state of the art
Crowd Scene Analysis in Video Surveillance
No full textThere is an increasing interest in crowd scene analysis in video surveillance due to the ubiquitously deployed video surveillance systems in public places with high density of objects amid the increasing concern on public security and safety. A comprehensive crowd scene analysis approach is required to not only be able to recognize crowd events and detect abnormal events, but also update the innate learning model in an online, real-time fashion. To this end, a set of approaches for Crowd Event Recognition (CER) and Abnormal Event Detection (AED) are developed in this thesis.
To address the problem of curse of dimensionality, we propose a video manifold learning method for crowd event analysis. A novel feature descriptor is proposed to encode regional optical flow features of video frames, where adaptive quantization and binarization of the feature code are employed to improve the discriminant ability of crowd motion patterns. Using the feature code as input, a linear dimensionality reduction algorithm that preserves both the intrinsic spatial and temporal properties is proposed, where the generated low-dimensional video manifolds are conducted for CER and AED.
Moreover, we introduce a framework for AED by integrating a novel incremental and decremental One-Class Support Vector Machine (OCSVM) with a sliding buffer. It not only updates the model in an online fashion with low computational cost, but also adapts to concept drift by discarding obsolete patterns. Furthermore, the framework has been improved by introducing Multiple Incremental and Decremental Learning (MIDL), kernel fusion, and multiple target tracking, which leads to more accurate and faster AED.
In addition, we develop a framework for another video content analysis task, i.e., shot boundary detection. Specifically, instead of directly assessing the pairwise difference between consecutive frames over time, we propose to evaluate a divergence measure between two OCSVM classifiers trained on two successive frame sets, which is more robust to noise and gradual transitions such as fade-in and fade-out. To speed up the processing procedure, the two OCSVM classifiers are updated online by the MIDL proposed for AED.
Extensive experiments on five benchmark datasets validate the effectiveness and efficiency of our approaches in comparison with the state of the art
4D.002 Using computer vision for assessing law-adherence of motorcyclists
No full textBackground The motorcycle is the main form of transport for many road users in the world, especially in low- and middle-income countries (LMIC). and since motorcycle riders are critically vulnerable in case of a crash, there should be strong enforcement of road safety related rules, such as helmet use. However, insufficient resources in LMIC hinder a comprehensive and continuous enforcement, subsequently leading to risky rider behavior. Computer vision can be used as a resource-efficient method to detect safety-critical behavior of motorcyclists and facilitate targeted enforcement on a country wide level.Methods Using video data from Myanmar, a computer vision algorithm was trained to detect helmet use of motorcycle riders. The algorithm was trained on 91,000 frames of thevideo dataset, containing 10,006 individual annotated motorcycles. It was then tested on diverse data that was not part of the training dataset, and compared to helmet use rates registered by human observers.Results The computer vision based approach can detect motorcycle helmet use with a precision of -4.4% to +2.1% compared to human observation, independent of traffic flows and road type. Detection accuracy deteriorated only whenvideo data was unclear, e.g. due to adverse weather conditions.Conclusion Computer vision can facilitate an economic datacollection of crucial road safety related rider behaviors. It canbe applied to collect continuous data and create an evidencebase for police enforcement that targets specific patterns oftraffic law violations.Learning Outcomes Attendants will learn how computer visioncan be levied to improve road safety globall
Empirical evaluation of no-reference VQA methods on a natural video quality database
No full textNo-Reference (NR) Video Quality Assessment (VQA) is a challenging task since it predicts the visual quality of a video sequence without comparison to some original reference video. Several NR-VQA methods have been proposed. However, all of them were designed and tested on databases with artificially distorted videos. Therefore, it remained an open question how well these NR-VQA methods perform for natural videos. We evaluated two popular VQA methods on our newly built natural VQA database KoNViD-1k. In addition, we found that merely combining five simple VQA-related features, i.e., contrast, colorfulness, blurriness, spatial information, and temporal information, already gave a performance about as well as those of the established NR-VQA methods. However, for all methods we found that they are unsatisfying when assessing natural videos (correlation coefficients below 0.6). These findings show that NR-VQA is not yet matured and in need of further substantial improvement.publishe
Detecting motorcycle helmet use with deep learning
Get PDFThe continuous motorization of traffic has led to a sustained increase in the global number of road related fatalities and injuries. To counter this, governments are focusing on enforcing safe and law-abiding behavior in traffic. However, especially in developing countries where the motorcycle is the main form of transportation, there is a lack of comprehensive data on the safety-critical behavioral metric of motorcycle helmet use. This lack of data prohibits targeted enforcement and education campaigns which are crucial for injury prevention. Hence, we have developed an algorithm for the automated registration of motorcycle helmet usage from video data, using a deep learning approach. Based on 91,000 annotated frames of video data, collected at multiple observation sites in 7 cities across the country of Myanmar, we trained our algorithm to detect active motorcycles, the number and position of riders on the motorcycle, as well as their helmet use. An analysis of the algorithm's accuracy on an annotated test data set, and a comparison to available human-registered helmet use data reveals a high accuracy of our approach. Our algorithm registers motorcycle helmet use rates with an accuracy of −4.4% and +2.1% in comparison to a human observer, with minimal training for individual observation sites. Without observation site specific training, the accuracy of helmet use detection decreases slightly, depending on a number of factors. Our approach can be implemented in existing roadside traffic surveillance infrastructure and can facilitate targeted data-driven injury prevention campaigns with real-time speed. Implications of the proposed method, as well as measures that can further improve detection accuracy are discussed
- …
