Newly emerged dynamic vision sensors (DVS) offer a great potential over traditional sensors (e.g. CMOS) since they have a high temporal resolution in the order of μs, ultra-low power consumption and high dynamic range up to 140 dB compared to 60 dB in frame cameras. Unlike traditional cameras, the output of DVS cameras is a stream of events that encodes the location of the pixel, time, and polarity of the brightness change. An event is triggered when the change of brightness, i.e. log intensity, of a pixel exceeds a certain threshold. The output of event cameras often contains a significant amount of noise (outlier events) alongside the signal (inlier events). The main cause of that is transistor switch leakage and noise. This paper presents a dynamic background activity filtering, called DBA-filter, for event cameras based on an adaptation of the K-nearest neighbor (KNN) algorithm and the optical flow. Results show that the proposed algorithm is able to achieve a high signal to noise ratio up to 13.64 dB.