In-Frame Ad Surface Detection for Automated Video Placement
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current systems for inserting advertisements in video frames are inefficient and time-consuming, as they require manual marking of hundreds of thousands of frames, which is prohibitive due to the large number of frames in a typical media asset.
Innovation Solution
A media guidance application dynamically identifies suitable surfaces in a video frame, such as oceans or skies, by analyzing color and shape patterns, and inserts advertisements on these surfaces without interfering with the content.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of manufacture
If manual marking of frames is used to identify advertisement spaces, then advertisement placement can be achieved, but the time and effort required becomes prohibitive due to the large number of frames
Solution Approach 1:
The patent replaces the manual mechanical process of marking frames with an automated computer vision system that uses image processing algorithms to detect surfaces and identify advertisement spaces automatically, eliminating the need for manual frame-by-frame marking
Solution Approach 2:
The system enables the video content itself to identify suitable advertisement spaces through automated surface detection and analysis, allowing the content to 'mark' its own suitable areas without external manual intervention
2Productivity
If advertisements are inserted between program segments, then advertisement opportunities arise, but viewers can change channels or leave the room to avoid viewing
Solution Approach 1:
The patent transitions advertisement placement from the temporal dimension (between segments) to the spatial dimension (within frames on surfaces), allowing advertisements to be embedded in the visual content itself rather than inserted as separate temporal elements
Solution Approach 2:
The system identifies specific local regions within frames (surfaces) that are suitable for advertisement placement, making advertisements contextually appropriate to the local scene rather than universally inserted at segment boundaries
Data Source
AI summary
Systems and methods are described to detect a location to place an advertisement in a media asset, the method comprising, identifying a plurality of points in a video frame of a media asset, detecting a color associated with each point of the plurality of points, calculating a change in color between each point of the plurality of points, comparing the change in color between each point of the plurality of points with a threshold, identifying, based on the comparing, an area within the frame that constitutes a surface; and selecting an advertisement to be placed on the surface.


