Video Processing Event Recognition Through Category Learning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing behavior recognition systems in surveillance cameras rely on machine learning and prior learning, lacking operator intervention for discriminator learning, which hinders accuracy improvement during actual operation.
Innovation Solution
A video processing apparatus and system that includes a video analyzer, display controller, and learning data accumulator, allowing operators to set category information through a category setting screen, and accumulate this data for learning processing to enhance analytical accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Extent of automation
If machine learning is used for behavior recognition without operator intervention, then the system can operate autonomously, but the analytical accuracy cannot be improved during actual operation
Solution Approach 1:
The system implements feedback by displaying detected events to operators who provide correction information. This feedback loop allows the learning data accumulator to store corrected category information, which then feeds back into the video analyzer to improve its recognition accuracy over time while maintaining autonomous operation.
Solution Approach 2:
The system enables self-service learning where operators can correct category assignments without manual system reconfiguration. The learning data accumulator automatically processes operator corrections and updates the video analyzer's discrimination learning, allowing the system to improve itself through operator feedback rather than requiring complete system redesign.
2Measurement precision
If operator intervention is required for discriminator learning, then analytical accuracy can be improved, but the operation complexity increases
Solution Approach 1:
The learning data accumulator acts as an intermediary between operators and the video analyzer. Operators interact with a simplified interface to correct category information, and the accumulator automatically translates these corrections into learning data that updates the video analyzer, reducing the complexity of direct operator-system interaction while maintaining accuracy improvement.
Solution Approach 2:
The system creates a simplified copy of the learning process interface for operators. Instead of requiring operators to directly configure complex discrimination parameters, they interact with a user-friendly category setting screen that copies the essential learning function while abstracting away the complexity of the underlying machine learning algorithms.
Data Source
AI summary
A video processing apparatus includes a video analyzer that analyzes video data captured by a surveillance camera, detects an event belonging to a specific category, and outputs a detection result, a display controller that displays, together with a video of the video data, a category setting screen for setting a category of an event included in the video, and a learning data accumulator that accumulates, as learning data together with the video data, category information set in accordance with an operation by an operator to the category setting screen. The video analyzer performs learning processing by using the learning data accumulated in the learning data accumulator.