In this paper, an online differential compression algorithm with reset columns integrated along with a digital pixel sensor (DPS) array is proposed. The proposed architecture of the sensor array reduces by more than half the silicon area of the DPS by sampling and storing the differential values between the pixel and its prediction, featuring compressed dynamic range and hence requiring limited precision (typically 2-3 bits as compared to 8-bit full precision). Column based reset technique is proposed to overcome the error accumulation problem inherent in predictive coding. While the concept of predictive coding was extensively introduced in previous literature, this is the first time this concept is used to reduce the storage requirement at the pixel level and hence drastically improving both the pixel size and the fill-factor - a key problem in DPS implementation. System level simulation results show the importance of the proposed reset scheme while VLSI implementation results illustrate a pixel level implementation of the whole predictive coding scheme featuring a pixel size reduction of more than 40% with a fill-factor of more than 15%.