Automated Storyline Definition via Path Probability Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for defining storylines in immersive multimedia content, such as 360° videos, are manual and time-consuming, often failing to align with viewer preferences, as they rely on the subjective decisions of creators rather than actual viewer behavior.
Innovation Solution
A method that automates the definition of storylines based on path probabilities by analyzing viewer behavior across frames, identifying viewed regions, determining transition probabilities, and clustering regions to create a storyline that reflects viewer habits, with constraints to optimize the narrative flow.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual methods are used to define storylines in immersive multimedia content, then the storyline can be created with creator's subjective decisions, but the process is time-consuming and may not align with actual viewer preferences
Solution Approach 1:
The system collects actual viewer behavior data (gaze tracking, head movements, interaction patterns) and uses this feedback to automatically define storylines. This closes the loop between creator intent and viewer preference, allowing storylines to be dynamically adjusted based on real viewer responses rather than relying solely on creator subjective decisions
Solution Approach 2:
The system enables automated storyline generation by having viewers themselves define the storyline through their natural viewing behavior. The aggregation of individual viewer paths and preferences automatically creates a collective storyline representation, eliminating the need for manual creator intervention in the storyline definition process
2Adaptability or versatility
If the field of view in 360° video is expanded to provide immersive content, then viewer engagement is enhanced, but it becomes difficult for viewers to decide where to focus and maintain consistent attention on important aspects
Solution Approach 1:
The system performs preliminary analysis of viewer behavior data before playback to pre-identify important regions and objects in the 360° video. During playback, this pre-computed information is used to automatically guide viewers to significant areas without requiring them to manually search through the entire field of view, thus maintaining both immersive coverage and focused attention
3Productivity
If automated storyline definition based on path probabilities is implemented, then storyline creation efficiency is increased and viewer behavior representation is improved, but the system complexity increases
Solution Approach 1:
The system introduces probability calculations and path aggregation algorithms as intermediary processing layers between raw viewer behavior data and the final storyline definition. These intermediaries transform complex, unstructured viewer paths into structured probability distributions, which then guide automated storyline generation without requiring direct complex processing of individual viewer behaviors
Data Source
Figure 1
Figure 2
Figure 3
AI summary
A method, apparatus and computer-readable storage medium are provided to define a storyline based on path probabilities for a plurality of paths through the frames of a video. Relative to a method and for a plurality of frames of a video, regions of a first frame and regions of a second, subsequent frame that have been viewed are identified. For each of at least one first-frame region of one or more regions of the first frame, the method determines a transition probability of transitioning from a respective first-frame region of the first frame to each of at least one second-frame region of a plurality of regions of the second frame. Based on the transition probabilities, the method determines a path probability for each of at least one of a plurality of paths through the frames of the video. The method additionally defines a storyline based on the path probabilities.