International Journal of Science and Research (IJSR)

International Journal of Science and Research (IJSR)
Call for Papers | Fully Refereed | Open Access | Double Blind Peer Reviewed

ISSN: 2319-7064




Downloads: 93 | Views: 175

M.Tech / M.E / PhD Thesis | Engineering Science | India | Volume 3 Issue 6, June 2014 | Rating: 7 / 10


Design and Implementation of Saliency Detection Model in H.264 Standard

Sheeba Shabnam | H.N. Latha


Abstract: Saliency detection is defined as a region of interest which is focused beyond the background. Nowadays saliency detection is widely used in different fields and have many scopes in image and video processing applications. Existing saliency detection techniques are implemented in uncompressed domain. In this paper we proposed an algorithm for visual saliency detec-tion model for videos by using H.264 standard. Since H.264 is in compressed domain; the storage space is reduced and processing speed is high to deliver data to the end users. Therefore H.264 bit streams is required in various internet based multimedia applica-tions. First the features of H.264 bit streams are extracted then saliency computation is done by calculating its static & motion saliency map. Before extracting the features macro blocks are generated and the frames of input video bit stream are coded in each macro block and it splits into unpredicted DCT coefficients and predicted motion vectors. The DCT coefficients are used to extract the features of luminance; color & texture of the unpre-dicted/current video frame to obtain the static saliency map whe-reas the motion saliency map of predicted frame is computed by motion features. Combining these features of static & motion saliency map; the final saliency map is extracted which focusing only on the particular region of interest which we want in the scene by drawing a rectangle on that region of interest (ROI) along with the irrelevant background but the ROI part is fo-cused beyond the background. Thus the proposed model for videos can predict the salient part accurately and efficiently in compressed domain while separating it with unfocused region. The experimental result indicates that our proposed model outperforms from the other existing saliency detection models.


Keywords: Saliency detection, H264, Visual attention, Static Saliency map, Motion Saliency map


Edition: Volume 3 Issue 6, June 2014,


Pages: 2014 - 2020



How to Download this Article?

Type Your Valid Email Address below to Receive the Article PDF Link


Verification Code will appear in 2 Seconds ... Wait

Top