Event Identification in Motion Video Using Segmented Camera Processing

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Surveillance and monitoring systems require significant processing power to detect and recognize events, mainly due to the large amount of spatial and temporal image data needed, which is resource-intensive and inefficient.

Innovation Solution

A two-step event detection process using camera processing data instead of pixel data, involving a temporary identification process for initial training and a long-term identification process, where camera processing data is used to reduce processing power requirements and improve detection quality, especially suited for cameras with limited computing resources.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If pixel data from captured image frames is used for event identification, then measurement precision is improved, but use of energy increases and productivity decreases

Engineering Contradiction:

Improveevent detection accuracyVSAvoidprocessing power

Core Design Contradiction:

Measurement precisionVSUse of energy by moving object

Solution Approach 1:

The patent divides the event detection process into two distinct phases: a temporary identification phase using full pixel data for training, and a long-term identification phase using condensed camera processing data for actual event detection. This segmentation allows the system to achieve high accuracy during training while consuming minimal processing power during operation.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The system performs preliminary training during a temporary identification phase where pixel data is used to train the event identifying operation. This preliminary action prepares the system in advance, so that during long-term operation, only condensed camera processing data needs to be processed, significantly reducing ongoing computational requirements.

Inventive Principle:

Principle #10Preliminary action

2Measurement precision

If pixel data from captured image frames is used for event identification, then measurement precision is improved, but productivity decreases

Engineering Contradiction:

Improveevent detection accuracyVSAvoidprocessing efficiency

Core Design Contradiction:

Measurement precisionVSProductivity

Solution Approach 1:

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

Inventive Principle:

Principle #10Preliminary action

3Use of energy by moving object

If camera processing data is used for event identification, then use of energy is decreased, but measurement precision worsens without training

Engineering Contradiction:

Improveprocessing powerVSAvoidevent detection accuracy

Core Design Contradiction:

Use of energy by moving objectVSMeasurement precision

Solution Approach 1:

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system uses feedback from the temporary identification process to adjust weights in the event identifying operation. This feedback mechanism ensures that the condensed camera processing data becomes progressively more accurate at detecting events, resolving the initial precision deficit while maintaining low processing power consumption.

Inventive Principle:

Principle #23Feedback

4Measurement precision

If a temporary identification process with pixel data is implemented, then measurement precision is improved for training, but device complexity increases

Engineering Contradiction:

Improvetraining accuracyVSAvoidsystem structure

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

Inventive Principle:

Principle #1Segmentation

Data Source

PatentUS10824872B2Method for identifying events in a motion video

Publication Date: 2020.11.03 AXIS

AI summary

A method for identifying events in a scene captured by a motion video camera comprises two identification processes, a temporary identification process and a long-term identification process. The temporary process includes: analyzing pixel data from captured image frames and identifying events; registering camera processing data relating to each image frame subjected to the identification of events; and adjusting weights belonging to an event identifying operation, wherein the weights are adjusted for achieving high correlation between the result from the event identifying operation and the result from the identification based on analysis of pixels from captured image frames of the captured scene. The long-term identification process includes: identifying events in the captured scene by inputting registered camera processing data to the event identifying operation. The temporary identification process is then executed during a predetermined time period and the long-term identification process is executed after the predetermined initial time has expired.