Entity

Time filter

Source Type


Chen L.,Sichuan University | Pang L.,Sichuan University | Zhou B.,Sichuan University | Zhang J.,Sichuan University | And 3 more authors.
Electronics Letters | Year: 2015

Node localisation for wireless sensor networks (WSNs) is applied in various fields, and is an indispensable core to promote the development of WSNs. Since the previous localisation algorithms did not fully utilise the anisotropy of nodes, according to the actual radiation model of the node's communication, a novel range-free localisation algorithm called range-free localisation based on the anisotropy of nodes (RLAN) is proposed. RLAN not only uses the information of multi-hop neighbours, but also considers fully the anisotropy of nodes in real networks, which influences the hop relationship and average hop distance, so as to improve the accuracy of node localisation. The simulation results demonstrate that RLAN has better localisation accuracy than other range-free node localisation algorithms. When the nodes are relatively uniformly deployed in the localisation area, the normalised localisation average error using RLAN can be <17%. © 2015 The Institution of Engineering and Technology. Source


Ge S.,Chinese Academy of Sciences | Ge S.,Beijing Key Laboratory of IOT Information Security Technology | Yang R.,Chinese Academy of Sciences | Yang R.,Beijing Key Laboratory of IOT Information Security Technology | And 9 more authors.
Neurocomputing | Year: 2016

Accurate eye localization plays a key role in many face analysis related applications. In this paper, we propose a novel statistic-based eye localization framework with a group of trained filter arrays called multi-channel correlation filter bank (MCCFB). Each filter array in the bank suits to a different face condition, thus combining these filter arrays can locate eyes more precisely in the conditions of variable poses, appearances and illuminations when comparing to single filter based or filter array based methods. To demonstrate the performance of our framework, we compare MCCFB with other statistic-based eye localization methods, experimental results show superiority of our method in detection ratio, localization accuracy and robustness. © 2015. Source

Discover hidden collaborations