Distributed Search Architecture for Object Tracking in the Internet of Things

Internet of Things (IoT) is rapidly expanding, which will enable many devices to be installed in various environments. However, current IoT services cannot maximally utilize devices because of their silo model. To solve this problem, we aim to realize Open IoT, in which services share devices. In this paper, we propose an architecture for an object tracking service, one of the main services of Open IoT. The architecture uses video data from shared devices, such as surveillance cameras or pedestrians' smartphones. An important research task is to discover the most appropriate devices for a service out of a huge number of devices connected to the Internet. We named real-time data generated by devices “live data”and are trying to use these data to discover appropriate devices. However, it is difficult to collect and handle all live data in the cloud because of the network band limit. Therefore, we propose a distributed search architecture. Generally, distributed architecture uses network and computing resources less efficiently than cloud architecture. Our proposed architecture overcomes this by deploying a search function dynamically and copes with arbitrary searches. We developed a system that embodies our proposed architecture and evaluated its feasibility. An experiment simulating a moving object tracking service with network cameras is shown that the architecture reduces the communication bandwidth of the core network to 1000th or less of that when cloud computing is used. In addition, another experiment is shown that the architecture search speed is sufficient for a walking-person tracking service.