Compressed domain visual information retrieval based on I-frames in HEVC

Compressed domain retrieval is important in the retrieval of HEVC coded videos, because full decompression of HEVC coded videos is very time consuming. In this paper, a texture based retrieval method is proposed for either video retrieval of HEVC coded videos or image retrieval of coded images as HEVC I-frames. The various prediction unit sizes and high number of prediction modes which are employed in I-frame coding of HEVC, provides higher information about the texture of the coded picture compared to the I-frame coding in H.264/AVC. The proposed texture based image retrieval method for HEVC coded visual information is based on histograms of prediction modes and prediction unit sizes. This method achieves 0.34 ANMRR in the image retrieval experiments and 0.33 ANMRR in the conducting video retrieval experiments, which are better compared to the other compressed domain retrieval methods based on H.264/AVC. On the other hand, the experimental evaluations indicate good robustness of the proposed method against variations in quantization parameter and image intensity. Moreover, the timing analysis indicates that feature extraction time by the proposed method is about 35 % of the decoding time of a coded video.