Long-Focus Camera Rotational Blur Removal Using Neural Networks
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
High zoom ratio cameras are prone to image blurring due to shake during photographing, especially in long-focus and long-distance photography applications.
Innovation Solution
A photographing method and apparatus that utilize a long-focus camera with a neural network model for rotational image deblurring, and optionally a second neural network model for translational image deblurring, to improve image quality.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If a higher zoom ratio is used to achieve long-focus photographing, then the ability to capture distant subjects is improved, but image quality degrades due to increased sensitivity to shake
Solution Approach 1:
The system performs preliminary actions by capturing multiple first images before final image processing. These preliminary captures are then processed through neural network models to remove blur, effectively preparing the images in advance to compensate for shake effects that occur during high-zoom photographing.
Solution Approach 2:
The patent replaces traditional mechanical image stabilization mechanisms with a neural network-based computational approach. Instead of relying solely on physical stabilization, the system uses deep learning models to analyze and correct blur in captured images, substituting mechanical prevention with intelligent post-processing.
2Manufacturing precision
If multiple images are captured and processed through neural network models to reduce blur, then image quality is improved, but processing time and computational complexity increase
Solution Approach 1:
The processing system is segmented into specialized neural network models with distinct functions: a first neural network model for rotational blur removal and a second neural network model for translational blur removal. This segmentation allows each model to focus on specific types of shake, improving processing efficiency while maintaining image quality.
Solution Approach 2:
The system applies partial action by selectively processing images based on detected blur characteristics. Rather than applying all processing steps to every image, the system determines the appropriate neural network model based on the type of shake detected, reducing unnecessary computational overhead while still achieving effective blur removal.
Data Source
AI summary
This application discloses a photographing method and apparatus, to overcome blurring that occurs during photographing. When a zoom ratio is greater than a first zoom ratio threshold, a long-focus camera is started to capture an image. A zoom ratio of the long-focus camera is greater than or equal to the first zoom ratio threshold. Because a high zoom ratio causes large shake, a rotational blur occurs in the image. According to the photographing method disclosed in this application, a first neural network model for rotational image deblurring is used to implement rotational image deblurring processing. In this way, high imaging quality of an image, a video, or a preview image is presented to a user to some extent, and the imaging effect may not be inferior to the effect of photographing with a tripod.