Perceptual synoptic view of pixel, object and semantic based attributes of video

• The need for various object and semantics level attributes is described in detail.
• Attention model based on object and semantics level attributes is proposed.
• Key frames are selected based on the proposed model.
• Key frames are fused to give perceptual synopsis.

For a scene, what are the object and semantic based attributes, other than the pixel based attributes, and how do they affect our attentional selection are some of the questions we need to address. We studied the effects of various attributes on our attentional perspective. We described a new saliency prediction model that accounts for different pixel-level attributes as color, contrast and intensity; object level attributes such as size, shape of objects and semantic level attributes as motion and speed of objects. We quantified these attributes based on motion contrast, motion energy and motion chromism. With this in view, we examined the problem of information prioritizing and filtering with emphasis on directing this exercise using object and semantic based attributes of the human attention model. We have evaluated proposed approach on different types of videos for their quantitative and qualitative comparison. The promising results create a gateway for synopsis view.

Figure optionsDownload high-quality image (216 K)Download as PowerPoint slide