Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

H.264 compression domain real time video object division method based on motion feature

A motion feature and object segmentation technology, applied in digital video signal modification, television, image analysis, etc., can solve problems that cannot be solved well, achieve good segmentation effect, strong practicability, and improve accuracy

Inactive Publication Date: 2008-08-06
SHANGHAI UNIV
View PDF0 Cites 17 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, in this method, there are two problems that have not been well resolved
One is that the effective filtering method cannot be used to filter out the singular motion vectors while retaining the main details of the motion vector field; the other is that the characteristics of the motion vector field cannot be fully utilized to segment video moving objects

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
  • H.264 compression domain real time video object division method based on motion feature
  • H.264 compression domain real time video object division method based on motion feature
  • H.264 compression domain real time video object division method based on motion feature

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0033] An implementation example of the present invention is described in detail as follows in conjunction with accompanying drawing:

[0034] The H.264 compressed domain real-time video object segmentation method based on the motion feature of the present invention is according to the program block diagram shown in Figure 1, and the CPU is a dual-core 2.0GHz, internal memory 900M PC test platform programming implementation, Figure 4 and Figure 5 provide Simulation test results.

[0035] Referring to Fig. 1, the H.264 compressed domain real-time video object segmentation method based on the motion feature of the present invention first carries out spatial normalization to the motion vector field, then carries out weighted median filtering to the normalized motion vector field, and then based on motion The magnitude, divergence and curl of the three motion features of the vector field are divided into multiple objects according to the similarity of the motion features by using ...

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 an H.264 compressed domain realtime video object segmentation method based on motion feature. The method comprises the following steps: after spatial domain normalization of a motion vector field is completed, weighting median filtering of the normalized motion vector field is carried out; then, based on the three motion features of the motion vector field including amplitude, divergence and circuitation, the motion vector field is divided into a plurality of objects according to motion feature similarity through adopting an improved statistical region growing method. The experimental result of an MPEG-4 testing sequence shows that: when a CIF format video sequence is processed in a computer with a 2.0GHz dual-core CPU and 900M memory, the average processing time of each frame is 15 ms which meets the requirements of most real-time application at 30fps; moreover, excellent segmentation quality is obtained. Because the method only makes use of motion vector field information, the method can also be used in the motion object segmentation of an optic flow field.

Description

technical field [0001] The invention relates to a real-time video object segmentation method based on the H.264 compressed domain. Compressed domain segmentation can avoid complete decoding of compressed video, and only motion vectors extracted through entropy decoding are used as motion features required for segmentation. In addition, quite different from the existing methods, this method uses three motion features based on the motion vector field's magnitude, divergence and curl, combined with the improved statistical region growing method to segment different objects in the video sequence, comparable to The calculation amount of the existing video object segmentation method based on the H.264 compressed domain is further reduced. Since this method only uses motion vector field information, it is also applicable to moving object segmentation based on optical flow field. Background technique [0002] Previous studies on video object segmentation mostly focus on the pixel d...

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
IPC IPC(8): H04N7/26G06T7/20H04N19/117H04N19/126H04N19/139H04N19/157H04N19/176
Inventor 张兆杨陆宇刘志
Owner SHANGHAI UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products