18221417. COMPUTER-READABLE RECORDING MEDIUM STORING MACHINE LEARNING PROGRAM, MACHINE LEARNING METHOD, AND INFORMATION PROCESSING DEVICE simplified abstract (Fujitsu Limited)
Contents
- 1 COMPUTER-READABLE RECORDING MEDIUM STORING MACHINE LEARNING PROGRAM, MACHINE LEARNING METHOD, AND INFORMATION PROCESSING DEVICE
- 1.1 Organization Name
- 1.2 Inventor(s)
- 1.3 COMPUTER-READABLE RECORDING MEDIUM STORING MACHINE LEARNING PROGRAM, MACHINE LEARNING METHOD, AND INFORMATION PROCESSING DEVICE - A simplified explanation of the abstract
- 1.4 Simplified Explanation
- 1.5 Potential Applications
- 1.6 Problems Solved
- 1.7 Benefits
- 1.8 Potential Commercial Applications
- 1.9 Possible Prior Art
- 1.10 Unanswered Questions
- 1.11 Original Abstract Submitted
COMPUTER-READABLE RECORDING MEDIUM STORING MACHINE LEARNING PROGRAM, MACHINE LEARNING METHOD, AND INFORMATION PROCESSING DEVICE
Organization Name
Inventor(s)
Suguru Yasutomi of Kawasaki (JP)
Masayuki Hiromoto of Kawasaki (JP)
COMPUTER-READABLE RECORDING MEDIUM STORING MACHINE LEARNING PROGRAM, MACHINE LEARNING METHOD, AND INFORMATION PROCESSING DEVICE - A simplified explanation of the abstract
This abstract first appeared for US patent application 18221417 titled 'COMPUTER-READABLE RECORDING MEDIUM STORING MACHINE LEARNING PROGRAM, MACHINE LEARNING METHOD, AND INFORMATION PROCESSING DEVICE
Simplified Explanation
The patent application describes a machine learning program stored on a computer-readable medium that processes moving image data using a trained model to detect and determine the identity of objects in different frames.
- Input moving image data with first and second frame images to a trained machine learning model.
- Detect first and second objects in the frames based on the model's inference result.
- Determine the identity between the detected objects.
- Input data from the identified objects to an encoder for further processing.
Potential Applications
This technology could be applied in video surveillance systems for object tracking and identification, autonomous vehicles for detecting and recognizing objects in real-time, and video editing software for automated object manipulation.
Problems Solved
This technology solves the problem of efficiently detecting and tracking objects across different frames of a video, enabling automated analysis and processing of visual data.
Benefits
The benefits of this technology include improved accuracy and speed in object detection and tracking, enhanced automation of video analysis tasks, and increased efficiency in processing moving image data.
Potential Commercial Applications
The technology could be commercialized in industries such as security and surveillance, automotive technology, and video editing software development, offering solutions for object recognition and tracking in various applications.
Possible Prior Art
One possible prior art for this technology could be existing machine learning algorithms used for object detection and tracking in videos, such as those employed in surveillance systems and autonomous vehicles.
Unanswered Questions
How does the technology handle occlusions or partial visibility of objects in the frames?
The patent application does not specify how the technology addresses situations where objects are partially obscured or hidden in the frames.
What is the computational overhead of training the machine learning model and processing the moving image data?
The patent application does not provide information on the computational resources required for training the model and executing the object detection and identification process.
Original Abstract Submitted
A non-transitory computer-readable recording medium storing a machine learning program for causing a computer to execute a process, the process includes inputting moving image data that includes at least a first frame image and a second frame image to a first machine learning model trained by using training data, and training an encoder by detecting a first object and a second object from the first frame image and the second frame image, respectively, based on an inference result by the first machine learning model, determining identity between the first object and the second object that have been detected, and inputting, to the encoder, first data in a first image area that includes the first object and second data in a second image area that includes the second object, the first object and the second object having been determined to have the identity.