School of Computer Science, Anhui University, Hefei 230601, China.
Institute of Computing Technology, Chinese Academy of Sciences, Beijing 100190, China.
Sensors (Basel). 2020 Dec 3;20(23):6902. doi: 10.3390/s20236902.
With the advent of the Internet of Everything, more and more devices are connected to the Internet every year. In major cities, in order to maintain normal social order, the demand for deployed cameras is also increasing. In terms of public safety, person Re-Identification (ReID) can play a big role. However, the current methods of ReID are to transfer the collected pedestrian images to the cloud for processing, which will bring huge communication costs. In order to solve this problem, we combine the recently emerging edge computing and use the edge to combine the end devices and the cloud to implement our proposed binarized segmented ResNet. Our method is mainly to divide a complete ResNet into three parts, corresponding to the end devices, the edge, and the cloud. After joint training, the corresponding segmented sub-network is deployed to the corresponding side, and inference is performed to realize ReID. In our experiments, we compared some traditional ReID methods in terms of accuracy and communication overhead. It can be found that our method can greatly reduce the communication cost on the basis of basically not reducing the recognition accuracy of ReID. In general, the communication cost can be reduced by four to eight times.
随着万物互联时代的到来，每年都有越来越多的设备连接到互联网上。在大城市中，为了维持正常的社会秩序，对部署的摄像机的需求也在增加。在公共安全方面，行人重识别（ReID）可以发挥重要作用。然而，当前的 ReID 方法是将采集到的行人图像传输到云端进行处理，这将带来巨大的通信成本。为了解决这个问题，我们结合了新兴的边缘计算，并利用边缘将终端设备和云结合起来，实现我们提出的二值化分割 ResNet。我们的方法主要是将一个完整的 ResNet 分为三部分，分别对应终端设备、边缘和云。联合训练后，将相应的分段子网络部署到相应的一端，并进行推理，以实现 ReID。在我们的实验中，我们根据准确性和通信开销比较了一些传统的 ReID 方法。可以发现，在基本不降低 ReID 识别精度的基础上，我们的方法可以大大降低通信成本。一般来说，通信成本可以降低四到八倍。
