This paper considers the problem of decentralized localization in wireless sensor networks. The problem is set by combining both radio-fingerprints and accelerometer information. It is then resolved in a decentralized manner where the surveillance area is divided into several zones, equipped with calculators. The proposed algorithm consists of computing first estimates using RSSI-fingerprints, then correcting them using accelerometer information leading to more accurate estimates. Computations are performed using the interval analysis and the Kalman filter in a simulated environment.