Method and device for processing video images based on neural network algorithm
A neural network algorithm, video image technology, applied in the direction of processor architecture/configuration, architecture with multiple processing units, electrical digital data processing, etc. , the effect of efficient output
Active Publication Date: 2019-03-05
HUAWEI TECH CO LTD
View PDF3 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0005] In view of this, the embodiments of the present invention provide a method and device for processing video images based on neural network algorithms to solve the problem of low processing efficiency of neural networks in the process of video image processing
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0054] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative work shall fall within the protection scope of the present invention.
[0055] figure 1 It is a schematic diagram of the forward calculation process of the neural network algorithm. Such as figure 1 As shown, the entire calculation process is divided into k levels, the second level is calculated based on the input of the first level, the third level is calculated based on the second level, and so on, and the kth level is finally calculated And use the final result as output. Among them, the first layer is called...
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
Login to View More Abstract
The invention provides a method for processing video images based on a neural network algorithm. The method includes the steps of determining the original image data of the current frame in video images and the image data of the previous frame, conducting differential operation on the original image data of the current frame and the image data of the previous frame to obtain the differential data which indicate the changing degree of the image of the current frame relative to that of the previous frame, determining first image data with less data bulk than that of the original image data of the current frame according to the differential data, and conducting linear processing and non-linear processing on the first image data according to the neural network algorithm. According to method for processing video images, differential operation on data of each two adjacent frames is conducted during a video image processing process through the neural network algorithm, so that the data bulk of the image processed is reduced, and the video image output is efficiently completed.
Description
Technical field [0001] The present invention relates to the field of communications, and in particular to a method and device for processing video images based on neural network algorithms in the field of communications. Background technique [0002] At present, neural networks and deep learning algorithms have been successfully applied and are in the process of rapid development. The industry generally expects that new calculation methods will help realize more common and complex intelligent applications. In particular, Convolutional Neural Network ("CNN") has made outstanding achievements in image recognition applications in recent years. Therefore, the industry has begun to pay attention to the optimization and high-efficiency implementation of CNN algorithms, such as Facebook, Companies such as Qualcomm, Baidu, and Google have all invested in research on CNN optimization algorithms. [0003] Qualcomm has released a plan to integrate neural network processing modules in next-ge...
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
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06T1/40
CPCG06T1/20
Inventor 费旭东
Owner HUAWEI TECH CO LTD