IP Library Granted Patent US 10,356,487
Granted Patent B2
US 10,356,487 · App. 15/115,584 · Granted Jul 16, 2019

Video advertisement filtering method, apparatus and device

Inventor: Zefa Xiong (Beijing, CN)
Assignee: BAIDU ONLINE NETWORK TECHNOLOGY (BEIJING) CO., LTD
H04N21/812H04N21/23424H04N21/454H04N21/8456
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 10,356,487
App. No.
15/115,584
Granted
Jul 16, 2019
Kind
B2
Abstract

Disclosed in embodiments of the present invention are a video advertisement filtering method, apparatus and device. The video advertisement filtering method includes: recognizing a time count number in a time count area of an advertisement frame in a video; determining a time difference between advertisement broadcast end time and present time based on the recognized time count number; and advancing playing time of the video to the advertisement broadcast end time based on the time difference. The video advertisement filtering method, apparatus and device that are provided in the embodiments of the present invention can filter an inserted video advertisement from a video program.

Claims (36)

1. A method for filtering a video advertisement, comprising:

determining, by using a video frame recognition algorithm, whether a presently displayed frame in a video comprising a time count area displayed along with the frame, and affirming the presently displayed frame in the video being an advertisement frame in response to the presently displayed frame in the video comprising the time count area displayed along with the frame;

identifying a time count number in the time count area displayed along with the presently displayed advertisement frame in the video;

determining a time difference between an advertisement broadcast end time and a present time based on the identified time count number; and

automatically advancing playing time of the video to the advertisement broadcast end time based on the time difference.

2. The method of claim 1 , wherein determining the time difference between the advertisement broadcast end time and the present time based on the identified time count number comprises:

using the identified time count number in the time count area at the present time as the time difference between the advertisement broadcast end time and the present time.

3. The method of claim 1 , wherein determining the time difference between the advertisement broadcast end time and the present time based on the identified time count number comprises:

determining whether the time count number is a countdown number based on values of the time count numbers at the present time and a reference time in the time count area and an order of the present time and the reference time; and

using the time count number at the present time as the time difference between the advertisement broadcast end time and the present time where the time count number is a countdown number.

4. The method of claim 1 , wherein identifying the time count number in the time count area displayed along with the presently displayed advertisement frame in the video comprises:

identifying the time count number in the time count area displayed along with the presently displayed advertisement frame in the video by using a text recognition algorithm.

5. A video advertisement filtering device comprising at least one processor, a memory, and at least one computer program, the at least one computer program being stored in the memory and configured to be executed by the at least one processor, wherein the computer program comprises instructions for causing the at least one processor to perform:

determining, by using a video frame recognition algorithm, whether a presently displayed frame in a video comprising a time count area displayed along with the frame, and affirming the presently displayed frame in the video being an advertisement frame in response to the frame in the video comprising the time count area displayed along with the frame;

identifying a time count number in the time count area displayed along with the presently displayed advertisement frame in the video;

determining a time difference between an advertisement broadcast end time and a present time based on the identified time count number; and

automatically advancing playing time of the video to the advertisement broadcast end time based on the time difference.

6. The device of claim 5 , wherein determining the time difference between the advertisement broadcast end time and the present time based on the identified time count number comprises:

using the identified time count number in the time count area at the present time as the time difference between the advertisement broadcast end time and the present time.

7. The device of claim 5 , wherein determining the time difference between the advertisement broadcast end time and the present time based on the identified time count number comprises:

determining whether the time count number is a countdown number based on values of the time count numbers at the present time and a reference time in the time count area and an order of the present time and the reference time; and

using the time count number at the present time as the time difference between the advertisement broadcast end time and the present time where the time count number is a countdown number.

8. The device of claim 5 , wherein identifying the time count number in the time count area displayed along with the presently displayed advertisement frame in the video comprises:

identifying the time count number in the time count area displayed along with the currently displayed advertisement frame in the video by using a text recognition algorithm.

9. A non-transitory computer storage medium storing computer program comprising instructions, which, when executed by one or more computers, cause the one or more computers to perform:

determining, by using a video frame recognition algorithm, whether a presently displayed frame in a video comprising a time count area displayed along with the frame, and affirming the presently displayed frame in the video being an advertisement frame in response to the presently displayed frame in the video comprising the time count area displayed along with the frame;

identifying a time count number in the time count area displayed along with the presently displayed advertisement frame in the video;

determining a time difference between an advertisement broadcast end time and a present time based on the identified time count number; and

automatically advancing playing time of the video to the advertisement broadcast end time based on the time difference.

10. The non-transitory computer storage medium of claim 9 , wherein determining the time difference between the advertisement broadcast end time and the present time based on the identified time count number comprises:

using the identified time count number in the time count area at the present time as the time difference between the advertisement broadcast end time and the present time.

11. The non-transitory computer storage medium of claim 9 , wherein determining the time difference between the advertisement broadcast end time and the present time based on the identified time count number comprises:

determining whether the time count number is a countdown number based on values of the time count numbers at the present time and a reference time in the time count area and an order of the present time and the reference time; and

using the time count number at the present time as the time difference between the advertisement broadcast end time and the present time where the time count number is a countdown number.

12. The non-transitory computer storage medium of claim 9 , wherein identifying the time count number in the time count area displayed along with the presently displayed advertisement frame in the video comprises:

identifying the time count number in the time count area displayed along with the presently displayed advertisement frame in the video by using a text recognition algorithm.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Nov 30, 2016
From: XIONG, ZEFA
To: BAIDU ONLINE NETWORK TECHNOLOGY (BEIJING) CO., LTD.
Reel/Frame 040471/0955 →
Priority Claims (1)
CN 2014 1 0455677 · Sep 9, 2014 · national
Continuity (1)
Related Publication 20180176658A1 · Jun 21, 2018
Cited By (1)
US 12,477,191