Image Generation Method for Subject Detection Accuracy
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing image generation methods face challenges in enhancing detection accuracy, particularly in monochrome modes where color information is lacking, leading to decreased detection precision.
Innovation Solution
An image generation method that involves acquiring an imaging signal, generating a first color image through initial processing, detecting subjects using a trained machine learning model, and creating a second image with different processing, which can be monochrome or sepia, to improve detection accuracy by utilizing color information even in monochrome modes.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If color image processing is performed to maintain detection accuracy, then detection precision is improved, but processing time and computational load increase
Solution Approach 1:
The patent segments the image processing workflow into distinct stages: a fast first image processing pipeline that generates low-resolution images for quick display, and a second image processing pipeline that generates high-resolution images for recording. Subject detection is performed on the faster first processed images, allowing detection to occur without waiting for complete high-resolution processing, thus reducing overall processing time while maintaining detection accuracy.
Solution Approach 2:
The system performs subject detection on the first processed images before the second (high-resolution) images are fully generated. This preliminary detection action allows the system to identify subjects early in the processing pipeline, enabling subsequent operations like autofocus or image capture to be triggered without waiting for complete high-resolution processing, thereby reducing processing time while preserving detection accuracy.
2Manufacturing precision
If high-resolution image processing is performed for all images, then image quality is improved, but processing complexity and time increase
Solution Approach 1:
The patent divides image processing into two separate pipelines: first image processing that generates lower-resolution images for live view display and subject detection, and second image processing that generates high-resolution images for recording. This segmentation allows the system to apply different processing complexities appropriately - simpler processing where high quality is not critical and more complex processing only where needed, reducing overall processing complexity while maintaining image quality for recorded outputs.
Solution Approach 2:
The system applies different processing qualities to different outputs: the first processed images provide sufficient quality for real-time display and detection purposes, while the second processed images provide high quality for recording. This local quality approach ensures that computational resources are not wasted applying high-resolution processing to images that will only be used for display, thereby reducing processing complexity while maintaining image quality where it matters most.
Data Source
AI summary
An image generation method includes: an imaging step of acquiring an imaging signal output from an imaging element; a first generation step of using the imaging signal to generate a first image through first image processing; a detection step of detecting a subject within the first image by using the first image via a trained model trained through machine learning; and a second generation step of using the imaging signal to generate a second image through second image processing different from the first image processing.