A low-cost indoor IoT object localization method based on monocular cameras at the edge device

Abstract

With the rapid development of Internet of Things (IoT) and edge computing, a lot of edge devices are connected into the network, including the cameras that are used and applied in many scenarios, for example, the indoor environment. Now, in order to solve the problem of fast location of object indoors with low cost, the monocular vision based object location method is proposed in this paper. First of all, the pixel coordinates of the objects are obtained by target matching, and then the area of the object on the captured image is calculated for rough matching. Finally, the precise coordinates of the objects to be located are obtained through their center values and recognized by the fine matching. Experimental results indicate that the proposed method has better performance.