17953883. METHOD FOR PROVIDING VIDEO AND ELECTRONIC DEVICE SUPPORTING THE SAME simplified abstract (Samsung Electronics Co., Ltd.)
METHOD FOR PROVIDING VIDEO AND ELECTRONIC DEVICE SUPPORTING THE SAME
Organization Name
Inventor(s)
METHOD FOR PROVIDING VIDEO AND ELECTRONIC DEVICE SUPPORTING THE SAME - A simplified explanation of the abstract
This abstract first appeared for US patent application 17953883 titled 'METHOD FOR PROVIDING VIDEO AND ELECTRONIC DEVICE SUPPORTING THE SAME
Simplified Explanation
The abstract describes an electronic device that can analyze videos to obtain information about objects in the video and their positions. It uses image and audio data to extract visual and audio features of the objects. This information is then combined to determine the position of the objects in the video. The device also stores the position information and corresponding audio parts in its memory.
- The electronic device can analyze videos to extract information about objects and their positions.
- It uses image data to obtain information about objects in the video.
- It extracts visual features of the objects based on the image and object information.
- The device also analyzes the audio in the video by obtaining a spectrogram.
- It extracts audio features of the objects from the spectrogram.
- The visual and audio features are combined to determine the position of the objects in the video.
- The device also identifies the audio part corresponding to the objects based on the combined features.
- The position information and corresponding audio parts are stored in the device's memory.
Potential Applications
- Video surveillance systems: The technology can be used to automatically detect and track objects in surveillance videos, providing valuable information for security purposes.
- Augmented reality: By analyzing videos in real-time, the device can identify and track objects in the user's environment, enhancing the augmented reality experience.
- Content creation: The technology can assist in automatically tagging and organizing videos, making it easier to search and edit specific objects or scenes.
Problems Solved
- Object identification and tracking: The technology solves the problem of automatically identifying and tracking objects in videos, which can be time-consuming and challenging for humans.
- Audio-visual synchronization: By combining visual and audio features, the device can accurately synchronize audio parts with specific objects in the video, improving the overall viewing experience.
Benefits
- Efficiency: The device automates the process of object identification and tracking, saving time and effort compared to manual analysis.
- Accuracy: By combining visual and audio features, the technology provides more accurate object positioning and audio synchronization.
- Enhanced user experience: The technology can improve the user experience in various applications, such as video surveillance and augmented reality, by providing real-time object information and audio synchronization.
Original Abstract Submitted
An electronic device is provided. The electronic device includes a memory, and at least one processor electrically connected to the memory, wherein the at least one processor is configured to obtain a video including an image and an audio, obtain information on at least one object included in the image from the image, obtain a visual feature of the at least one object, based on the image and the information on the at least one object, obtain a spectrogram of the audio, obtain an audio feature of the at least one object from the spectrogram of the audio, combine the visual feature and the audio feature, obtain, based on the combined visual feature and audio feature, information on a position of the at least one object the information indicating the position of the at least one object in the image, obtain an audio part corresponding to the at least one object in the audio, based on the combined visual feature and audio feature, and store, in the memory, the information on the position of the at least one object and the audio part corresponding to the at least one object.
