18494604. INFORMATION PROCESSING METHOD AND APPARATUS simplified abstract (Huawei Technologies Co., Ltd.)
Contents
INFORMATION PROCESSING METHOD AND APPARATUS
Organization Name
Inventor(s)
INFORMATION PROCESSING METHOD AND APPARATUS - A simplified explanation of the abstract
This abstract first appeared for US patent application 18494604 titled 'INFORMATION PROCESSING METHOD AND APPARATUS
Simplified Explanation
The patent application discloses a method for visual cognition processing using machine learning models in a computer system like a vehicle or handheld terminal.
- Obtaining an image
- Inputting the image into a feature extraction model
- Obtaining a first feature map from the feature extraction model
- Inputting the first feature map into a first semantic recognition model
- Obtaining first target semantic information from the first semantic recognition model
Potential applications of this technology:
- Autonomous vehicles
- Surveillance systems
- Augmented reality devices
Problems solved by this technology:
- Enhancing visual cognition process
- Improving accuracy of visual tasks
- Optimizing visual cognition process
Benefits of this technology:
- Increased accuracy in visual recognition
- Enhanced performance in visual tasks
- Improved efficiency in processing visual information
Original Abstract Submitted
This application discloses an information processing method, and the method may be applied to a computer like a vehicle or a handheld terminal. The vehicle is, for example, an intelligent vehicle or an intelligent connected vehicle. The method is used to implement a visual cognition process. The method includes: obtaining an image; inputting the image into a feature extraction model; obtaining, from the feature extraction model, a first feature map; inputting the first feature map into a first semantic recognition model; and obtaining, from the first semantic recognition model, first target semantic information. The visual cognition process is split and implemented by using two machine learning models, to facilitate optimization of the visual cognition process, improve accuracy of visual cognition, and further improve accuracy of a visual task.
