Machine Learning Model for Augmented Reality Image Processing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing augmented reality (AR) application programs lack intelligent data analysis, object identification, and anomaly detection, and are limited by high hardware costs for computation-intensive data processing, unable to dynamically augment content based on user input or intentions.
Innovation Solution
A method using a machine learning model to acquire and process images from AR scenes, determining target objects, augmenting information, and displaying enhanced images, which reduces hardware resource usage and improves user experience.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If computation-intensive data processing is performed to achieve intelligent data analysis, object identification, and anomaly detection in AR applications, then the intelligence and functionality of the AR system is improved, but the hardware costs and resource requirements increase significantly
Solution Approach 1:
The patent introduces a pre-trained machine learning model as an intermediary component that performs complex data processing tasks. This model acts as a mediator between the AR application and the underlying computational infrastructure, enabling intelligent analysis without requiring the end-device to have high computational power. The model is trained offline on powerful hardware and then deployed to run on devices with limited resources.
Solution Approach 2:
The machine learning model is pre-trained in advance on large datasets using high-performance computing resources. This preliminary training action transfers the computational burden to the training phase rather than the runtime phase. Once trained, the model can perform inference with minimal computational resources, thus resolving the contradiction between achieving intelligent analysis and reducing hardware costs.
2Productivity
If traditional image processing methods are used in AR applications, then the system is simpler to implement, but the processing speed and efficiency are insufficient for real-time augmentation
Solution Approach 1:
The patent replaces traditional mechanical image processing methods with a machine learning-based approach. Instead of using conventional algorithms that manually process image data, the system employs a trained neural network model that automatically learns and applies processing patterns. This substitution enables faster processing speeds while maintaining manageable system complexity through the use of standardized model deployment frameworks.
3Manufacturing precision
If high-quality image augmentation is achieved through comprehensive data processing, then the user experience is improved, but the hardware resource consumption increases
Solution Approach 1:
The machine learning model performs computationally intensive training operations in advance, before deployment to the AR device. This preliminary action transfers the energy-consuming processing to the model creation phase, allowing the deployed model to deliver high-quality image augmentation with minimal runtime resource consumption. The model encapsulates learned patterns that can be applied efficiently during actual AR operations.
Data Source
AI summary
Embodiments of the present disclosure relate to a method, an electronic device, and a computer program product for processing an image. The method includes acquiring an image about an augmented reality scene. The method further includes determining a target image part corresponding to a target object from the image. The method further includes using a machine learning model to augment information about the target object in the target image part to obtain an augmented target image part. The method further includes displaying the augmented target image part. Through the method, augmentation of an augmented reality image may be quickly achieved, the image quality is improved, the use of hardware resources is reduced, and user experience is improved.