Crowdsourced Video Data Collection via Interactive User Inputs
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing technologies are labor-intensive and time-consuming for manually collecting data like player positions and strategies during sporting events, often resulting in inaccurate or delayed data delivery.
Innovation Solution
A crowdsourcing system that utilizes large-scale interactive user input from viewers, converting two-dimensional video data into three-dimensional player positions through user input analysis, with rewards for accurate and timely submissions presented as an interactive game.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual input by professional operators is used to collect event data, then data accuracy is improved, but labor intensity and time consumption increase
Solution Approach 1:
The patent segments the data collection task by dividing the field of view into multiple zones and assigning different users to capture data from different zones. This allows parallel data collection from multiple areas simultaneously, improving overall productivity while maintaining accuracy through specialized focus in each zone
Solution Approach 2:
The patent merges inputs from multiple users into a unified event data record. By combining data from multiple users who are each capturing specific zones or aspects, the system achieves both high accuracy (through multiple observations) and high productivity (through parallel collection)
2Productivity
If automatic data collection systems are used, then productivity is improved, but measurement precision deteriorates
Solution Approach 1:
The patent introduces an intermediary processing layer that receives data from multiple users and automatically merges it into unified event records. This intermediary system enables automatic high-speed data collection while maintaining accuracy through the aggregation of multiple human observations, bridging the gap between automatic speed and manual precision
3Productivity
If more users are involved in data collection, then productivity is improved, but data processing complexity increases
Solution Approach 1:
The patent implements a self-service system where users automatically register their observations and the system automatically merges these inputs into event data. The multi-user input merging operates autonomously without requiring complex coordination or manual intervention, allowing the system to scale to many users while keeping operational complexity manageable
Data Source
AI summary
A method including receiving a broadcast of an event comprising a plurality of frames; receiving, from a plurality of users, a corresponding plurality of inputs, each of the inputs relating to a characteristic of an object depicted in one of the frames of the broadcast; and analyzing the plurality of inputs to determine a best guess of the characteristic of the object in the frame.