Fast CU-splitting decisions based on data mining

The HEVC(H.265) has brought in significant improvements in terms of coding efficiency. However, the reduction in bitrates comes along with an increment in computational complexity. This paper presents a data mining approach to reduce the complexity of inter partition modes in HEVC. Determining the CU-splitting in inter partition modes requires substantial resources, so the goal of the work is to terminate the inter partition mode through CU-splitting decision in advance for reducing encoding complexity. We use a method that employs a set of decision trees based on data mining to achieve the goal instead of searching for the best match mode in all modes. Experiments show that the fast algorithm based on decision trees can efficiently enhance the encoding speed 32.6% at a negligible cost of 0.3% increase in terms of BD-rate.