Search

Spectrum sensing is essential for the success of the cognitive radio networks. In traditional spectrum sensing schemes, secondary users (SUs) are responsible for the spectrum sensing which could be very time and resource consuming. It leads to a great deal of inefficiency in spectrum usage and introduces many practical challenges. To tackle these challenges and leverage the spectrum opportunity more efficiently, we propose a new system that provides a spectrum sensing service for SUs using dedicated wireless spectrum sensor networks (WSSNs). In this paper we focus on the sensing channel assignment problem in WSSNs and formulate the problem as a sensing effectiveness maximization problem (SEMP). We prove that SEMP is NP-complete under the ideal case, and show that more challenges arise in real environments. To address the issue, we systematically study the design tradeoff and critical factors when maximizing the sensing effectiveness. Based on these study results we propose a sensing channel assignment algorithm (SCAS). We conduct test-bed empirical investigations as well as comprehensive simulations. Performance evaluation results show that for both the scenarios of given deployments and manual deployments, SCAS is able to sense more channels to improve the sensing effectiveness. The improvement is up to 300 % and the average improvement is 150 % compared with other simple alternatives. [ABSTRACT FROM AUTHOR]

Recently, the video data has very huge volume, taking one city for example, thousands of cameras are built of which each collects high-definition video over 24-48 GB every day with the rapidly growth; secondly, data collected includes variety of formats involving multimedia, images and other unstructured data; furthermore the valuable information contains in only a few frames called key frames of massive video data; and the last problem caused is how to improve the processing velocity of a large amount of original video with computers, so as to enhance the crime prediction and detection effectiveness of police and users. In this paper, we conclude a novel architecture for next generation public security system, and the 'front + back' pattern is adopted to address the problems brought by the redundant construction of current public security information systems which realizes the resource consolidation of multiple IT resources, and provides unified computing and storage environment for more complex data analysis and applications such as data mining and semantic reasoning. Under the architecture, we introduce cloud computing technologies such as distributed storage and computing, data retrieval of huge and heterogeneous data, provide multiple optimized strategies to enhance the utilization of resources and efficiency of tasks. This paper also presents a novel strategy to generate a super-resolution image via multi-stage dictionaries which are trained by a cascade training process. Extensive experiments on image super-resolution validate that the proposed solution can get much better results than some state-of-the-arts ones. [ABSTRACT FROM AUTHOR]

Given a language query, temporal grounding task is to localize temporal boundaries of the described event in an untrimmed video. There is a long-standing challenge that multiple moments may be associated with one same video-query pair, termed label uncertainty. However, existing methods struggle to localize diverse moments due to the lack of multi-label annotations. In this paper, we propose a novel Diverse Temporal Grounding framework (DTG) to achieve diverse moment localization with only single-label annotations. By delving into the label uncertainty, we find the diverse moments retrieved tend to involve similar actions/objects, driving us to perceive these interest moments. Specifically, we construct soft multi-label through semantic similarity of multiple video-query pairs. These soft labels reveal whether multiple moments in the intra-videos contain similar verbs/nouns, thereby guiding interest moment generation. Meanwhile, we put forward a diverse moment regression network (DMRNet) to achieve multiple predictions in a single pass, where plausible moments are dynamically picked out from the interest moments for joint optimization. Moreover, we introduce new metrics that better reveal multi-output performance. Extensive experiments conducted on Charades-STA and ActivityNet Captions show that our method achieves state-of-the-art performance in terms of both standard and new metrics. [ABSTRACT FROM AUTHOR]

Visual relationship detection, as a challenging task used to find and distinguish interactions between object-pairs in one image, has received much attention recently. In this work, we devise a unified visual relationship detection framework with two types of correlation exploitation to address the combination explosion problem in the object-pairs proposing stage and the non-exclusive label problem in the predicate recognition stage. In the object-pairs proposing stage, with the exploitation of relative location correlation between two objects in one pair, one location-embedded rating module (LRM) is developed to effectively select plausible proposals. In the predicate recognition stage, one label-correlation graph module (LGM) is introduced to measure the implicit semantic correlation among predicates; and then assign discrete distributed labels to predicates to improve the precision of top-n recall. Experiments on the two widely used VRD and VG datasets show that our proposed method outperforms current state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Recently, with the fast proliferation of smart phones, mobile phone has the powerful ability of not only communication but also computation. Human beings are not only data consumers, but data producer with their objective or subjective sensing needs. Mobile crowd sensing is an emerging computing paradigm that tasks everyday mobile devices to form participatory sensor networks. It allows the increasing number of mobile phone users to share local knowledge acquired by their sensor-enhanced devices. Social sensors, social sensor receiver platform, and mobile crowd sensing paradigm compose a process by which physical sensors present in mobile devices such as GPS are used to infer social relationships and human activities. In this survey, we review the mobile crowd sensing applications on social sensors based on social sensor receiver platform (e.g., Weibo and Twitter) from three categories: public security, smart city, and location based services. Most applications adopted in current works fit in one of these categories. Existing works on applications of mobile crowd sensing on social sensors are collected and studied. Some possible future directions of potential new application category are proposed and analyzed. [ABSTRACT FROM AUTHOR]

With the development of Web 2.0, ubiquitous computing, and corresponding technologies, social media has the ability to provide the concepts of information contribution, diffusion, and exchange. Different from the permitting the general public to issue the user-generated information, social media has enabled them to avoid the need to use centralized, authoritative agencies. One of the important functions of Weibo is to monitor real time urban emergency events, such as fire, explosion, traffic jam, etc. Weibo user can be seen as social sensors and Weibo can be seen as the sensor platform. In this paper, the proposed method focuses on the step for storytelling of urban emergency events: given the Weibo posts related to a detected urban emergency event, the proposed method targets at mining the multi-modal information (e.g., images, videos, and texts), as well as storytelling the event precisely and concisely. To sum up, we propose a novel urban emergency event storytelling method to generate multi-modal summary from Weibo. Specifically, the proposed method consists of three stages: irrelevant Weibo post filtering, mining multi-modal information and storytelling generation. We conduct extensive case studies on real-world microblog datasets to demonstrate the superiority of the proposed framework. [ABSTRACT FROM AUTHOR]

Recently, the number of surveillance video data has grown enormously since the popularity of the smart cities, which brings the difficulties to users for searching and analyzing the content of the videos. These video data are not limited to data anymore, which provide the effective information for criminal investigation systems, intrusion detection system, and many others. However, as the number of available cloud services increases, the problem of data discovery and selection arises. The semantic technology is an effective choice for enhancing the accurate of the data searching and analyzing process. In this paper, a semantic based cloud environment is proposed to facilitate the analyzing and searching process of surveillance video data. An architecture integrating ontology building, semantic annotation, and semantic search is proposed to leverage the semantic description of the video data to find them from concept-based level. A semantic intermediate layer which organizes the video data based on their semantic relations is given. Moreover, the proposed method is used in the intelligent transportation field, which shows the bright prospect of the proposed method in real applications. [ABSTRACT FROM AUTHOR]

Today, video surveillance technology is playing a more and more important role in traffic detection. Vehicle’s static properties are crucial information in examining criminal and traffic violations. With the development of video surveillance technology, it has been wildly used in the traffic monitoring. Image and video resources play an important role in traffic events analysis. With the rapid growth of the video surveillance devices, a large number of image and video resources are increasingly being created. It is crucial to explore, share, reuse, and link these multimedia resources for better organizing traffic events. Most of the video resources are currently annotated in an isolated way, which means that they lack semantic connections. Thus, providing the facilities for annotating these video resources is highly demanded. These facilities create the semantic connections among video resources and allow their metadata to be understood globally. Adopting semantic technologies, this paper introduces a video annotation platform. The platform enables user to semantically annotate video resources using vocabularies defined by traffic events ontologies. Moreover, the platform provides the search interface of annotated video resources. The result of initial development demonstrates the benefits of applying semantic technologies in the aspects of reusability, scalability, and extensibility. [ABSTRACT FROM AUTHOR]

With the popularity of web, the internet is becoming a major information provider and poster of an event due to its real-time, open, and dynamic features. In this paper, crowd sensing based burst computation algorithm of a web event is developed in order to let the people know a web event clearly and help the social group or government process the events effectively. Different temporal features of web events are developed to provide the basics for the proposed computation algorithm. The burst power is presented to integrate the above temporal features of an event. Empirical experiments on real datasets including Google Zeitgeist and Google Trends show that the number of web pages and the average clustering coefficient can be used to detect events. The evaluations on real dataset show that the proposed function integrating the number of web pages and the average clustering coefficient can be used for event detection efficiently and correctly. [ABSTRACT FROM AUTHOR]

The prevalence of intelligent video systems such as urban video surveillance or Google Glass, is gradually changing our daily life. This type of systems applies online analysis on video streams for the extraction of object information, which will be utilized to provide abundant content-based services. However, the system also brings challenges to the system resource utilization, while providing convenience to users. The online video analysis requires continuous and immediate processing of video streams, which always causes massive investment on the processing hardware and intolerable power consumption. In this paper, we propose to utilize the power of cloud to improve the energy efficiency of intelligent video systems, through video stream consolidation based on the fluctuation characteristic of analysis workloads. Our trace-driven study proves that the pressure on the power consumption can be significantly alleviated, while ensuring the processing ability in practical scenes. [ABSTRACT FROM AUTHOR]