Multi-Lens Camera Control for Neural Screen Type Identification and Filtering
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing electronic apparatuses struggle to accurately determine the type of screen in an image due to limited angle of view and difficulty in identifying multiple objects, often providing inappropriate filters or failing to provide any filters, leading to misrecognition.
Innovation Solution
The apparatus employs multiple lenses with different angles of view, using neural network models to analyze depth maps, saliency, and object relationships to accurately identify the screen type and apply corresponding filters.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If a single lens with limited angle of view is used for image capture, then the device complexity is reduced, but the screen type identification accuracy deteriorates due to insufficient field of view
Solution Approach 1:
The camera system is segmented into multiple lenses with different fields of view (wide-angle lens and telephoto lens). Each lens captures images of different areas, allowing the system to analyze both the overall screen configuration and specific details for accurate screen type identification.
Solution Approach 2:
The system transitions from a single viewpoint to multiple viewpoints by using lenses with different focal lengths and fields of view. This dimensional change in observation perspective enables comprehensive analysis of the screen layout and object relationships for accurate classification.
2Device complexity
If screen type is determined based on a single object, then the device complexity is reduced, but the identification accuracy deteriorates when multiple objects are present
Solution Approach 1:
The system merges information from multiple detected objects and their spatial relationships to determine screen type. Instead of relying on a single object, it combines data from all detected objects within the captured area, analyzing their configurations and relationships for accurate screen type classification.
Solution Approach 2:
The object detection system is designed to handle both single-object and multi-object scenarios universally. It can detect various types of objects (people, furniture, devices) and automatically adapt its analysis method based on the number and arrangement of detected objects, providing accurate screen type determination in diverse situations.
3Device complexity
If the captured area is narrow, then the device complexity is reduced, but the screen type determination becomes difficult due to limited field of view
Solution Approach 1:
The system dynamically switches between wide-angle and telephoto lenses based on the shooting scenario and detected objects. When the screen area is narrow or objects are far away, it automatically transitions to the wide-angle lens to capture a broader view, enabling comprehensive screen type detection without requiring manual intervention.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
An electronic apparatus and a controlling method are provided. The electronic apparatus includes a camera including a first lens and a second lens capable of obtaining an image having an angle of view different from the first lens, a display, a memory, and a processor configured to provide a first image obtained using the first lens to the display as a live view, obtain a second image using the second lens while providing the first image as a live view, obtain information regarding the second image and information regarding at least one object included in the second image using at least one neural network model, identify a screen type of the second image based on the information regarding the second image and the information regarding at least one object included in the second image, identify a set of filters corresponding to the screen type of the second image, and correct the first image provided as the live view based on the identified set of filters.