Landscape Video Cropping with Object Tracking for Portrait Output
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Users face challenges in converting landscape videos to portrait videos efficiently, as existing editing programs lack effective options and manual conversion is time-consuming, often resulting in the exclusion of desired video portions.
Innovation Solution
A system and method for automatically generating portrait videos from landscape videos by tracking objects within the landscape videos using a cropping window that moves based on object movement, with user interface support for conversion and video effects application.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If manual conversion of landscape video to portrait video is performed, then user control over video content is maintained, but time consumption increases and editing efficiency decreases
Solution Approach 1:
The system automatically performs the video conversion process without requiring manual user intervention. The processing system autonomously identifies objects in the landscape video, determines appropriate cropping regions, and generates the portrait video through automated cropping and aspect ratio adjustment, eliminating the need for users to manually edit each frame.
Solution Approach 2:
The manual mechanical process of frame-by-frame editing is replaced with an automated computational system that uses object detection algorithms, cropping window management, and digital signal processing to achieve the same transformation, significantly reducing time requirements.
2Productivity
If automated cropping is applied to convert landscape video to portrait video, then conversion speed increases, but video content may be excluded or distorted
Solution Approach 1:
The system continuously monitors the cropping window position and size during the conversion process, adjusting these parameters based on detected object locations and movements. This feedback mechanism ensures that the cropping window maintains proper framing of the subject while adapting to changes in the video content, preventing exclusion or distortion of important elements.
Solution Approach 2:
The cropping window parameters (position, size, aspect ratio) are dynamically adjusted during video processing rather than using fixed predetermined values. The system adapts the cropping region in real-time based on object detection results, allowing the automated process to maintain content accuracy despite variations in the original video composition.
3Ease of operation
If existing editing programs are used for video conversion, then user control over editing options is maintained, but the amount of time available for editing is insufficient
Solution Approach 1:
The system performs all necessary cropping decisions and video transformation actions automatically in advance, before the user would traditionally need to manually intervene. By pre-determining the optimal cropping regions and executing the conversion process automatically, the system eliminates the time-consuming manual editing phase while preserving user control through automated decision-making.
Data Source
AI summary
Example systems, computer readable medium and methods for automatically generating portrait videos from landscape videos include receiving a landscaped video, identifying one or more objects to track, and tracking the one or more objects by moving a cropping window. A user interface is presented that provides options for a user to automatically convert a landscape video into a portrait video. The options include selecting one or more objects in the landscape video to track and tracking based on a flight plan used to capture the video. The automatic tracking uses a hierarchy of a person for tracking where a face is used if the person is close, an upper body is used if the person is farther away, and a whole body is used if the person is even farther away. A hierarchy of a person includes indications of which parts of the hierarchy to exclude first.