One of the main aspects affecting the life of people living in urban and suburban areas is their continued exposure to high road traffic noise (RTN) levels, traditionally measured by specialists working on the field. Nowadays, the deployment of Wireless Acoustic Sensor Networks (WASN) has allowed automatic noise mapping in Smart Cities. In order to obtain a reliable picture of the RTN levels affecting citizens, those anomalous noise events (ANE) unrelated to road traffic should be removed from the noise map computation. For this purpose, this paper introduces an Anomalous Noise Event Detector (ANED) designed to differentiate in real-time between RTN and ANE at every 1 second, using an algorithm running at a low-capacity $\mu$controller-based acoustic sensor developed within the DYNAMAP project. The low-cap ANED follows a binary audio event detection approach to discriminate between ANE and RTN. It is based on the computing of spectral differences of the input acoustic data in order to fit the computational capacity of the considered low-cap sensors. The experiments considering real-life acoustic data show the feasibility of the proposal as a means to complement the results obtained by the ANED developed for the high-cap acoustic sensors of the WASN.