Display Content Start Detection for Adaptive Viewing Control
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing display devices struggle to obtain attribute information about content executed on external devices, leading to inefficient control of content execution environments, especially when connected via wire, resulting in reduced accuracy and resource waste during analysis.
Innovation Solution
The display device employs neural network models to analyze image screens from external devices, identifying content execution starts and extracting attribute information, such as metadata, to control settings like image quality, sound, and viewing age restrictions based on the content's characteristics.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If the display device analyzes image screens from external devices to obtain content attribute information, then the accuracy of content execution environment control is improved, but the consumption of computational resources and time increases
Solution Approach 1:
The system performs preliminary actions by detecting content execution start points before full analysis begins. The first neural network model identifies when content actually starts executing, allowing the second neural network model to begin attribute information extraction at the precise moment needed, rather than continuously analyzing all frames from the beginning.
Solution Approach 2:
The system employs periodic action by continuously monitoring image screens at regular intervals to detect content execution start points. The first neural network model periodically analyzes frames to identify transitions from idle states to content execution states, enabling timely activation of the more resource-intensive second model only when necessary.
2Reliability
If the display device uses neural network models to analyze image screens, then the ability to identify content execution start points is improved, but the device complexity increases
Solution Approach 1:
The system segments the content execution detection process into two distinct functional components: a first neural network model dedicated to detecting execution start points, and a second neural network model dedicated to extracting attribute information. This segmentation allows each model to be optimized for its specific task and enables independent management of computational resources.
Solution Approach 2:
The first neural network model acts as an intermediary between the image screen input and the second neural network model. It processes raw image frames to identify content execution start points, then triggers the second model only when relevant events occur, serving as a gatekeeper that reduces unnecessary processing by the more complex second model.
3Reliability
If the display device continuously analyzes all image screens, then no content execution start points are missed, but the time required for analysis increases
Solution Approach 1:
The system performs preliminary detection using the first neural network model to identify content execution start points before initiating full attribute analysis. This preliminary action ensures that the more time-consuming second neural network model is activated only when and where content actually begins executing, rather than continuously analyzing all frames.
Solution Approach 2:
The system implements periodic sampling and detection using the first neural network model to monitor image screens at intervals. This periodic detection maintains reliability by continuously checking for content execution start points while reducing overall processing time compared to continuous full analysis, as the second model is triggered only periodically when needed.
Data Source
AI summary
According to various embodiments, a display device and an operation method thereof are disclosed. The disclosed display device includes: a display, an input/output interface comprising circuitry, a communication interface comprising communication circuitry, a memory in which one or more instructions are stored, and at least one processor, comprising processing circuitry, individually and/or collectively, configured to execute the one or more instructions stored in the memory to cause the display device to: display an image screen received from an electronic device connected to the display device, determine whether execution of content starts by analyzing the displayed image screen using a first neural network model, call a second neural network model based on determining that the execution of the content starts, obtain attribute information of the content by analyzing the image screen of the content using the second neural network model, and control an execution environment of the content based on the obtained attribute information.