14 October 2019 in IEEE Transactions on Geoscience and Remote Sensing
Infrared small target detection technology is one of the key technologies in the field of computer vision. In recent years, several methods have been proposed for detecting small infrared targets. However, the existing methods are highly sensitive to challenging heterogeneous backgrounds, which are mainly due to: 1) infrared images containing mostly heavy clouds and chaotic sea backgrounds and 2) the inefficiency of utilizing the structural prior knowledge of the target. In this article, we propose a novel approach for infrared small target detection in order to take both the structural prior knowledge of the target and the self-correlation of the background into account. First, we construct a tensor model for the high-dimensional structural characteristics of multiframe infrared images. Second, inspired by the low-rank background and morphological operator, a novel method based on low-rank tensor completion with top-hat regularization is proposed, which integrates low-rank tensor completion and a ring top-hat regularization into our model. Third, a closed solution to the optimization algorithm is given to solve the proposed tensor model. Furthermore, the experimental results from seven real infrared sequences demonstrate the superiority of the proposed small target detection method. Compared with traditional baseline methods, the proposed method can not only achieve an improvement in the signal-to-clutter ratio gain and background suppression factor but also provide a more robust detection model in situations with low false-positive rates.
8 March 2017 in IEEE Journal on Selected Areas in Communications
Due to rapid developments of smart devices and mobile applications, there is an urgent need for a new human-in-the-loop architecture with better system efficiency and user experience. Compared with conventional device-based human-computer interactive (HCI) methods, device-free technology with WiFi provides a new HCI method and is promising for providing better user-perceived quality-of-experience. Being essential for device-free applications, device-free human detection has gained increasing interest, of which through-the-wall (TTW) human detection is of great challenge. Existing TTW detection systems either rely on massive deployment of transceivers or require specialized WiFi monitors, making them inapplicable for real-world applications. Recently, more and more researchers have tapped into the physical layer for more robust and reliable human detection, ever since channel state information (CSI) can be exported with commodity devices. Despite great progress achieved, there have been few works studying TTW detection. In this paper, we propose a novel scheme for robust device-free TTW detection (R-TTWD) of a moving human with commodity devices. Different from the time dimension-based features exploited in the previous works, R-TTWD takes advantage of the correlated changes over different subcarriers and extracts the first-order difference of eigenvector of CSI across different subcarriers for TTW human detection. Instead of direct feature extraction, we first perform a PCA-based filtering on the preprocessed data, since a simple low-pass filtering is insufficient for noise removal. Furthermore, the detection results across different transmit-receive antenna pairs are fused with a majority-vote-based scheme for more robust and accurate detection. We prototype R-TTWD on commodity WiFi devices and evaluate its performance both in different environments and over long test period, validating the robustness of R-TTWD with both detection rates for moving human and human absence over 99% regardless of different wall materials, dynamic moving speeds, and so on.
3 December 2019 in IEEE Internet of Things Journal
As the infrastructure of intelligent transportation system, vehicular ad hoc networks (VANETs) have greatly improved traffic efficiency. However, due to the openness characteristics of VANETs, trust and privacy are still two challenging issues in building a more secure network environment: it is difficult to protect the privacy of vehicles and meanwhile to determine whether the message sent by the vehicle is credible. In this paper, a blockchain-based trust management model, combined with conditional privacy-preserving announcement scheme (BTCPS), is proposed for VANETs. Firstly, an anonymous aggregate vehicular announcement protocol is designed to allow vehicles to send messages anonymously in the non-fully trusted environment to guarantee the privacy of the vehicle. Secondly, a blockchain-based trust management model is present to realize the message synchronization and credibility. Roadside Units (RSUs) are able to calculate message reliability based on vehicles’ reputation values which are safely stored in the blockchain. In addition, BTCPS also achieves conditional privacy since Trusted Authority can trace malicious vehicles’ identities in anonymous announcements with the related public addresses. Finally, a mixed consensus algorithm based on Proof-of-work and Practical Byzantine Fault Tolerates algorithm is suggested for better efficiency. Security analysis and performance evaluation demonstrate that the proposed scheme is secure and effective in VANETs.
6 March 2018 in IEEE Transactions on Industrial Informatics
In this paper, a distributed filtering scheme is presented to deal with the soft fault detection problem of nonlinear stochastic systems with wireless sensor networks (WSNs). The nonlinear stochastic systems, which are of discrete-time form, are represented by interval type-2 (IT2) Takagi--Sugeno (T--S) fuzzy models. Randomly occurred packet losses are considered between the WSN and the filter unit. A novel type of IT2 T--S fuzzy distributed fault detection filter is proposed corresponding to each sensor node. Meanwhile, a fault reference model is adopted for improving the performance of the fault detection system. Then a new distributed fault detection system is formulated in a type-2 fuzzy model framework. New techniques are utilized to analyse and synthesize of the overall fault detection system with a disturbance attenuation performance. Finally, a truck-trailer system with a four-node WSN is established to validate the effectiveness and applicability of the presented distributed fault detection scheme.
17 September 2018 in IEEE Transactions on Mobile Computing
Understanding and predicting cellular traffic at large-scale and fine-granularity is beneficial and valuable to mobile users, wireless carriers and city authorities. Predicting cellular traffic in modern metropolis is particularly challenging because of the tremendous temporal and spatial dynamics introduced by diverse user Internet behaviours and frequent user mobility citywide. In this paper, we characterize and investigate the root causes of such dynamics in cellular traffic through a big cellular usage dataset covering 1.5 million users and 5,929 cell towers in a major city of China. We reveal intensive spatiotemporal dependency even among distant cell towers, which is largely overlooked in previous works. To explicitly characterize and effectively model the spatio-temporal dependency of urban cellular traffic, we propose a novel decomposition of in-cell and inter-cell data traffic, and apply a graph-based deep learning approach to accurate cellular traffic prediction. Experimental results demonstrate that our method consistently outperforms the state-of-the-art time-series based approaches and we also show through an example study how the decomposition of cellular traffic can be used for event inference.
13 November 2017 in IEEE/ACM Transactions on Networking
Exploiting radio frequency signals is promising for locating and tracking objects. Prior works focus on per-tag localization, in which each object is attached with one tag. In this paper, we propose a comprehensive localization and tracking scheme by attaching two RFID tags to one object. Instead of using per-tag localization pattern, adding one-more RFID tag to the object exhibits several benefits: 1) providing rich freedom in RFID reader's antenna spacing and placement; 2) supporting accurate calibration of the reader's antenna location and spacing, and 3) enabling fine-grained calculation on the orientation of the tags. All of these advantages ultimately improve the localization/tracking accuracy. Our extensive experimental results demonstrate that the average errors of localization and orientation of target tags are 6.415 cm and 1.330°, respectively. Our results also verify that the reader's antenna geometry does have impact on tag positioning performance.