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

A method of time-lapse processing video images

A video image, time-lapse technology, applied in image communication, color TV components, TV system components and other directions, can solve the problem of not being able to output time-lapse video in time, very high hardware equipment requirements, and large 3D modeling calculations. and other problems, to achieve the effect of being conducive to computer implementation, avoiding repeated calculations, and low jitter

Inactive Publication Date: 2019-02-05
成都鹰眼视觉科技有限公司
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, due to the huge amount of calculations for 3D modeling and the high requirements for hardware devices, it is difficult to implement it in mobile devices, and it cannot output time-lapse videos in time. It lacks universal applicability, and there are also problems of poor robustness.

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
  • A method of time-lapse processing video images
  • A method of time-lapse processing video images
  • A method of time-lapse processing video images

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0039] figure 1 The flow chart of the method for time-lapse processing video images provided by the present invention is shown. The method for time-lapse processing video images includes the following steps.

[0040] S101. Input a video to be processed.

[0041] S102. Obtain the sharpness value, distortion value, and matching degree value of each frame in the video to be processed, and then calculate a frame extraction reference value corresponding to each frame according to the sharpness value, distortion value, and matching degree value.

[0042] S103. Set a sliding window with a window size of N, and then gradually select M consecutive frames in the video to be processed by moving the sliding window, and remove the frame with the smallest frame reference value among the selected consecutive frames in each step, the M The value is equal to the N value.

[0043] S104. If the total number of remaining frames of the video to be processed is greater than the target value, the...

Embodiment 2

[0047] figure 2 Shows the flow chart of obtaining the sharpness value of the video frame provided by the present invention, image 3 Shows the flow chart of obtaining the distortion value of the video frame provided by the present invention, Figure 4 Shows the flow chart of obtaining the matching degree value of the video frame provided by the present invention, Figure 5 A schematic diagram showing the positional relationship between the current frame and the corresponding adjacent frame provided by the present invention, Image 6 A schematic diagram of frame extraction processing by moving a sliding window provided by the present invention is shown. Embodiment 2 As a refinement scheme of Embodiment 1, each step in Embodiment 1 is described in detail below.

[0048] S101. Input a video to be processed.

[0049] S102. Obtain the sharpness value, distortion value, and matching degree value of each frame in the video to be processed, and then calculate a frame extraction r...

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 the technical field of time-lapse / time-lapse photography, and discloses a method for time-lapse processing video images. The method for time-lapse processing of video images evaluates and scores the image quality of video frames from three angles of clarity, distortion and matching degree, and then performs selective iterative frame extraction processing, which not only avoids three-dimensional Modeling, which greatly reduces the amount of calculation and the configuration requirements of hardware devices, enables timely output of time-lapse video on low-configuration mobile devices, thereby improving the universality and robustness of time-lapse video, and fast output The time-lapse video also makes the final time-lapse video have the advantages of high definition and low jitter.

Description

technical field [0001] The present invention relates to the technical field of time-lapse / time-lapse photography, in particular to a method for time-lapse processing of video images. Background technique [0002] Time-lapse / time-lapse photography technology is a shooting technology that compresses time, that is, through photo concatenation or video frame extraction, a group of photos or videos that are captured and recorded for hours or days are compressed into A photo gallery or video that can be played over a short period of time, showing phenomena that would normally go unnoticed. Usually time-lapse / time-lapse photography technology needs to use special equipment and equipment to complete, such as using a tripod to fix the shooting equipment, so as to obtain highly stable photos or videos. However, for videos taken by mobile devices (such as mobile phone cameras, DV cameras, tablet cameras, wearable device cameras, and airborne / vehicle cameras, etc.), due to the poor sta...

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 Patents(China)
IPC IPC(8): H04N5/915H04N5/21
Inventor 陶科锐郝鸣明
Owner 成都鹰眼视觉科技有限公司
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