基于边缘云计算的分布式行人重识别方法

Distributed Pedestrian Re-identification Method Based on Edge Cloud Computing

为了降低计算密集型行人重识别任务的延迟,利用前沿的边缘云计算技术,设计了一种新颖分布式行人重识别(ECCreID)框架的模型。首先,通过结合属性识别和行人重识别来提出一种分布式模块分配方法。然后,考虑边缘云计算网络的动态性,设计一种基于在线学习的算法。最后,通过使用真实数据集进行的仿真,来评估所提出算法的性能。评估结果表明,所提出的框架具有较好的性能。

In order to reduce the delay of computing-intensive pedestrian re-identification tasks,this paper uses cutting-edge edge cloud computing technology to design a novel distributed pedestrian re-identification(ECCreID)framework model.First,a distributed module allocation method is proposed by combining attribute recognition and pedestrian re-identification.Then,considering the dynamics of the edge cloud computing network,we design an algorithm based on online learning.Finally,the performance of the proposed algorithm is evaluated by simulation using real data sets.The evaluation results show that the proposed framework has good performance.