共被期刊论文引用了2次
您的检索式：您选中1篇文献正在查看引证文献汇总
|
|
|
题名
|
作者
|
年代
|
出处
|
被引量
|
| 1 | CNN Feature Boosted SeqSLAM for Real-Time Loop Closure Detection显示文摘This paper proposes an efficient and robust Loop closure detection(LCD) method based on Convolutional neural network(CNN) feature. The primary method is called SeqCNNSLAM, in which both the outputs of the intermediate layer of a pre-trained CNN and the outputs of traditional sequence-based matching procedure are incorporated, making it possible to handle the viewpoint and condition variance properly. An acceleration algorithm for SeqCNNSLAM is developed to reduce the search range for the current image, resulting in a new LCD method called A-SeqCNNSLAM. To improve the applicability of A-SeqCNNSLAM to new environments, O-SeqCNNSLAM is proposed for online parameters adjustment in A-SeqCNNSLAM. In addition to the above work, we further put forward a promising idea to enhance Seq SLAM by integrating the both CNN features and VLAD's advantages called patch based Seq CNNSLAM(P-SeqCNNSLAM), and provide some preliminary experimental results to reveal its performance. | BAI Dongdong WANG Chaoqun ZHANG Bo YI Xiaodong YANG Xuejun | 2018 | Chinese Journal of Electronics2018，27，3： | 11 |
| 2 | A Formation Reconfiguration Algorithm for Multi-UAVs Based on Distributed Cooperative Coevolutionary with an Adaptive Grouping Strategy显示文摘The Formation reconfiguration problem plays a crucial role in the implementation of complex t asks for multiple unmanned aerial vehicles,which attracted increasing attention in the past decade.Taking into consideration the control parame ters and time discretization of the multi-UAVs in the 3 Dimensional(3-D)space,the formation reconfiguration problem can be formulated as a large-scale combinatorial optimization problem with complex constraints and tight couplings between variables.The problem results in the reduction in efficiency and effectiveness using classic bio-inspired algorithms.In this paper,a formation reconfiguration method based on cooperative coevolutionary algorithm is proposed along with a new decomposition strategy to improve the optimization capability and prevent premature convergence.In the proposed approach,variables of multi-UAV are divided into several sub-groups based on an adaptive grouping strategy.The proposed strategy groups the variables in order to better deal with the tight coupling among them,taking into account the variables'variance and multi-UAVs characteristics of the formation reconfiguration problem.Therefore,each sub・group can adopt the Self-adaptive differential evolution strategy with neighborhood search(SaNSDE)with the aim to optimize the UAV's control inputs using multithreaded programming.SaNSDE contributes to calculating the results in a fully distributed and paralleled manner.Optimal solution is then obtained through cooperation and coordina tion with all subcomponents.Simulation results based on extreme scenarios adopted by previous researches demonstrate that the proposed algorithm out performed the existing approaches including Par ti cle swarm optimization(PSO),Differential evolution(DE),and the cooperative coevolution algorithms with different well-known grouping strategies. | LIU Huaxian LIU Feng ZHANG Xuejun GUAN Xiangmin CHEN Jun | 2020 | Chinese Journal of Electronics2020，29，5： | 5 |
您所在的机构暂未开通此部分的功能，请联系管理员