A pargmatic Implementation of Outdoor Localization Scheme for Real Time IoT Applications

object detection and identify their localization is one of the computer vision problems. So, in recent years, many localization algorithms for indoor and outdoor Wireless Sensor Networks (WSNs) have been developed to achieve higher localization accuracy. This paper introduces a localization algorithm that measuring the distance between reference node known as anchor nodes and mobile node based on artificial intelligent system. The system employs on the shelf Wi-Fi access points as three anchor nodes and use one target (mobile) node to measure the Received Signal Strength Indicator (RSSI) from these anchor nodes. Real test scenario is implemented in a 20m outdoor corridor, where 250 samples are collected to train the proposed Artificial Neural Network (ANN) in order to optimize the estimated distance. The structure of ANN was implemented using Field Programmable Gate Arrays (FPGA) to solve the limitations of electronics hardware including the speed of response through building each stage of ANN using Matlab 2012a system generator. The results that are obtained verify an accurate distance estimation, where the mean absolute distance error is less than 0.26 m.