Unlock instant, AI-driven research and patent intelligence for your innovation.

Device and method for generating a saliency map of a picture

A picture, remarkable technology, applied in image analysis, image data processing, character and pattern recognition, etc., can solve problems such as difficulty in accurately estimating motion area, inaccurate total value, etc.

Inactive Publication Date: 2009-12-09
THOMSON LICENSING SA
View PDF0 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

First, we know that estimating motion regions accurately is a difficult task
Second, even with precise motion regions, the relationship between these motion regions and temporal salience values ​​is not straightforward
State-of-the-art methods often weight temporal and spatial saliency in arbitrary ways to obtain an overall value of spatiotemporal saliency, which is often imprecise

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Device and method for generating a saliency map of a picture
  • Device and method for generating a saliency map of a picture
  • Device and method for generating a saliency map of a picture

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0031] The method according to the invention consists of Figure 4 The screen shown is generated as Figure 5 The spatiotemporal saliency map shown. A saliency map is defined as a two-dimensional topographical representation of salient features. To achieve this goal, the present invention includes computing spatiotemporal saliency values ​​for each pixel block in the frame.

[0032] refer to figure 1 , the frame F(t) of the sequence is divided into multiple pixel blocks, and t is a time parameter. Each block B(x, y, t) of n by m pixels is called a spatio-temporal event. Event B(x, y, t) is thus a block of pixels located at spatial coordinates (x, y) in frame F(t). N co-located blocks from frames F(t), F(t-1), ..., F(t-N+1) (i.e., located at the same spatial position as B(x, y, t) ( A plurality of blocks of x, y)) form a spatio-temporal volume denoted V(x, y, t), where N is a predetermined positive integer. For N, the value of 2 frames is a good compromise between the ac...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention relates to a method for generating a saliency map for a picture of a sequence of pictures, the picture being divided in blocks of pixels. The method comprises a step for computing a saliency value for each block of the picture. According to the invention, the saliency value equals the self information of the block, the self information depending on the spatial and temporal contexts of the block.

Description

technical field [0001] The invention relates to a method and a device for generating a saliency map for a picture in a sequence of pictures. Background technique [0002] Salient visual features that attract attention can be important and powerful cues for video analysis and processing including content-based encoding, compression, transmission / rate control, indexing, browsing, display, and rendering. State-of-the-art methods for detecting and extracting visually salient features mainly deal with still pictures. The few methods that deal with picture sequences first compute spatial and temporal saliency values ​​independently and then combine them in some rather arbitrary way in order to generate spatiotemporal saliency values. Spatial saliency values ​​are generally based on calculations (in some heuristic fashion) of the contrast of various visual features (density, color, texture, etc.). These methods generally assume that temporal saliency values ​​are related to motio...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06T7/00G06V10/50
CPCG06K9/4642G06T7/0097G06T7/174G06V10/50G06V20/40
Inventor 顾晓东邱国平陈志波陈衢清王传铭
Owner THOMSON LICENSING SA