Video object detecting apparatus, video object deforming apparatus, and methods thereof
AssigneeSamsung Electronics Co., Ltd.
InventorsByung In YOO, Chang Kyu Choi, Jae Joon Han
Life of this patent
Estimating the term…
Abstract
A video object detecting apparatus enables a user to not only simply watch the video but also to explore a video using a motion and a posture of the user. In addition, the user may manipulate the video using body motion instead of general input units such as a mouse and a touch system. Also, a video object deforming apparatus enables the user to recognize a difference in motions between an interactive video and the user, and provides the user with a video reflecting the difference.
Claims17
A video object detecting apparatus comprising:
- a processor comprising:
- an object retrieval unit to retrieve a sensing object from a sensing image related to a user, and also retrieve a video object from an interactive video;
- a calculation unit to calculate similarity between the sensing object and the video object;
- and
- a frame extraction unit to extract a frame having the highest similarity from the interactive video.
A video object detecting apparatus comprising:
- a processor comprising:
- an object retrieval unit to retrieve a video object input by a user from an interactive video;
- a tracking unit to track a position of a control point for controlling the video object;
- a calculation unit to calculate a difference of positions between a moment of the video object and the control point, based on an identification of the video object and the position of the control point;
- and
- a frame extraction unit to extract a frame having the lowest similarity from the interactive video.
A video object deforming apparatus comprising:
- a processor comprising:
- an object retrieval unit to retrieve a sensing object from a sensing image related to a user, and also retrieve a video object from an interactive video;
- a calculation unit to calculate a difference between an object shape related to the sensing object and a depth image related to the video object;
- and
- a generation unit to generate a difference map based on the calculated difference.
A video object detecting method comprising:
- retrieving a sensing object from a sensing image related to a user and also retrieving a video object from an interactive video;
- calculating, by a processor, similarity between the sensing object and the video object;
- and
- extracting a frame having the lowest similarity from the interactive video.
A video object detecting method comprising:
- retrieving a video object input by a user from an interactive video;
- tracking a position of a control point for controlling the video object;
- calculating, by a processor, a difference of positions between a moment of the video object and the control point, based on an identification of the video object and the position of the control point;
- and
- extracting a frame having the lowest similarity from the interactive video.
A video object deforming method comprising:
- retrieving a sensing object from a sensing image related to a user and also retrieving a video object from an interactive video;
- calculating, by a processor, a difference between an object shape related to the sensing object and a depth image related to the video object;
- and
- generating a difference map based on the calculated difference.
A system for utilizing an interactive video comprising:
- a video object detecting apparatus comprising:
- an object retrieval unit to retrieve a sensing object from a sensing image related to a user, and also retrieve a video object from an interactive video,
- a calculation unit to calculate similarity between the sensing object and the video object, and
- a frame extraction unit to extract a frame having the highest similarity from the interactive video;
- and
- a video object deforming apparatus comprising:
- an object retrieval unit to retrieve a sensing object from a sensing image related to a user, and also retrieve a video object from an interactive video,
- a calculation unit to calculate a difference between an object shape related to the sensing object and a depth image related to the video object, and
- a generation unit to generate a difference map based on the calculated difference.
Dependencies are inferred from the claim text.