Video processing and playing method and video processing apparatus thereof

• US 9,805,766 B1
• Filed: 07/19/2016
• Issued: 10/31/2017
• Est. Priority Date: 07/19/2016
• Status: Active Grant

• Current Assignee: Compal Electronics Incorporated
• Original Assignee: Compal Electronics Incorporated
• Inventors: Peng, Sheng-Hua
• Primary Examiner(s): Chowdhury, Nigar
• Application Number:
  US15/213,412
• Time in Patent Office: 469 Days
• Field of Search: 386223-228, 386248
• CPC Class Codes: G06F 18/22 Matching criteria, e.g. proximity measures
• CPC Class Codes: G06V 10/75 Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
• CPC Class Codes: G06V 20/46 Extracting features or characteristics from the video content, e.g. video fingerprints, representative shots or key frames
• CPC Class Codes: G06V 40/161 Detection; Localisation; Normalisation
• CPC Class Codes: G06V 40/168 Feature extraction; Face representation
• CPC Class Codes: G06V 40/174 Facial expression recognition
• CPC Class Codes: G06V 40/20 Movements or behaviour, e.g. gesture recognition recognition of facial expressions G06V40/16
• CPC Class Codes: G11B 27/102 Programmed access in sequence to addressed parts of tracks of operating record carriers access by moving the head G11B3/08, G11B5/54, G11B7/085, G11B21/022; by moving the record carrier G11B15/005, G11B17/005, by driving of both record carrier and head G11B15/1816
• CPC Class Codes: G11B 27/28 by using information signals recorded by the same method as the main recording G11B27/22 takes precedence

Abstract

A video processing and playing method adapted to a video processing apparatus is provided. The method includes the following steps. A digital video is received and the digital video is decoded to obtain a plurality of video frames. The video frames are analyzed to detect a human feature of the digital video. A recognition result of the detected human feature is determined by comparing the detected human feature with a plurality of sample features. The recognition result of the detected human feature is associated with a timestamp according to a time point of detecting the human feature. A first video segment of the digital video played according to the timestamp when receiving a user command selecting the recognition result.

Claims

1. A video processing and playing method, adapted to a video processing apparatus, comprising:

receiving a digital video and decoding the digital video to obtain a plurality of video frames;

analyzing the video frames of the digital video by detecting a human feature in the video frames of the digital video;

determining a recognition result of the detected human feature by comparing the detected human feature with a plurality of sample features;

associating the recognition result of the detected human feature with a timestamp according to a time point of detecting the human feature;

segmenting the digital video according to the recognition result of the digital video and the timestamp to obtain a plurality of video segments comprising a first video segment; and

playing the first video segment of the digital video according to the timestamp when receiving a user command selecting the recognition result.

2. The video playing method according to claim 1, wherein the human feature comprises a human face, and the step of analyzing the video frames to detect the human feature of the digital video comprises:

identifying the human face in one of the video frames by performing a facial detection on the video frames.

3. The video playing method according to claim 2, wherein the step of determining the recognition result of the detected human feature by comparing the detected human feature with the sample features comprises:

determining a person by performing a facial reorganization through comparing the human face with a plurality of face templates of the sample features.

4. The video playing method according to claim 2, wherein the human feature further comprises a face expression, and the step of analyzing the video frames to detect the human feature of the digital video further comprises:

recognizing the face expression in the one of the video frames by analyzing the human face.

5. The video playing method according to claim 4, wherein the step of determining the recognition result of the detected human feature by comparing the detected human feature with the sample features comprises:

determining a human emotion by comparing the face expression with a plurality of expression templates of the sample features.

6. The video playing method according to claim 2, wherein the human feature further comprises a body posture, and the step of analyzing the video frames to detect the human feature of the digital video further comprises:

identifying a human body base on the human face and recognizing the body posture by analyzing the human body in one of the video frames.

7. The video playing method according to claim 6, wherein the step of determining the recognition result of the detected human feature by comparing the detected human feature with the sample features comprises:

determining a human action by comparing the body posture with a plurality of posture templates of the sample features.

8. The video playing method according to claim 1, further comprises:

receiving a plurality of sample images;

generating the sample features based on the sample images; and

establishing a template database comprising the sample features.

9. The video playing method according to claim 1, wherein the step of playing the first video segment of the digital video according to the timestamp when receiving the user command selecting the recognition result comprises:

displaying a plurality of candidates associated with the recognition result on a screen; and

successively playing the first video segment and a second video segment among the video segments according to the timestamp when receiving the user command selecting one of the candidates, wherein the recognition result corresponding to the one of the candidates is shown in the first video segment and the second video segment.

18. The video processing apparatus according to claim 1, wherein the processor is configured to display a plurality of candidates associated with the recognition result on the screen, and successively play the first video segment and a second video segment among the video segments according to the timestamp when receiving the user command selecting one of the candidates, wherein the recognition result corresponding to the one of the candidates is shown in the first video segment and the second video segment.

10. A video processing apparatus, comprising:

a memory, storing a plurality of instructions; and

a processor, coupled to the memory and configured for executing the instructions to;

receive a digital video and decoding the digital video to obtain a plurality of video frames;

analyze the video frames of the digital video by detecting a human feature in the video frames of the digital video;

determine a recognition result of the detected human feature by comparing the detected human feature with a plurality of sample features;

associate the recognition result of the detected human feature with a timestamp according to a time point of detecting the human feature;

segment the digital video according to the recognition result of the digital video and the timestamp to obtain a plurality of video segments comprising a first video segment; and

play the first video segment of the digital video according to the timestamp when receiving a user command selecting the recognition result.

11. The video processing apparatus according to claim 10, wherein the human feature comprises a human face, and the processor is configured to identify the human face in one of the video frames by performing a facial detection on the video frames.

12. The video processing apparatus according to claim 11, wherein the processor is configured to determine a person by performing a facial reorganization through comparing the human face with a plurality of face templates of the sample features.

13. The video processing apparatus according to claim 11, wherein the human feature further comprises a face expression, and the processor is configured to recognize the face expression in the one of the video frames by analyzing the human face.

14. The video processing apparatus according to claim 13, wherein the processor is configured to determine a human emotion by comparing the face expression with a plurality of expression templates of the sample features.

15. The video processing apparatus according to claim 11, wherein the human feature further comprises a body posture, and the processor is configured to identify a human body base on the human face and recognize the body posture by analyzing the human body in one of the video frames.

16. The video processing apparatus according to claim 15, wherein the processor is configured to determine a human action by comparing the body posture with a plurality of posture templates of the sample features.

17. The video processing apparatus according to claim 10, wherein the processor is configured to receive a plurality of sample images, generate the sample features based on the sample images, and establish a template database comprising the sample features.