Video Stream Event Detection with Adaptive Visual Indicators

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing monitoring camera systems require significant human resources and attention to detect important details in multiple video streams, leading to operator fatigue and inefficiency, especially when faced with high levels of movement or distractions.

Innovation Solution

A computer-implemented method for displaying a video stream with added visual indicators that highlight new events, filtered based on criteria such as the absence of prior events in the area, distance from other events, level of motion, object class, and operator attention, to conserve resources and enhance operator detection capabilities.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If visual indicators are added to all movement in the video stream, then operator detection capability is improved, but encoding, transmission, and storage resources are consumed and operator fatigue increases

Engineering Contradiction:
Improvedetection capabilityVSAvoidprocessing and storage resources
Core Design Contradiction:
Measurement precisionVSLoss of energy

Solution Approach 1:

The system changes parameters by filtering events based on multiple criteria including motion magnitude thresholds, event type classification, and spatial-temporal patterns. Only events meeting specific parameter thresholds are highlighted, transforming the approach from highlighting all movement to highlighting only significant movement patterns.

Inventive Principle:
Principle #35Parameter changes

Solution Approach 2:

Different regions of the video stream receive different treatment based on local characteristics. Areas with significant events receive visual indicators while areas with normal activity remain unmarked. The system adapts the highlighting behavior locally based on event significance rather than applying uniform highlighting across the entire scene.

Inventive Principle:
Principle #3Local quality

2Measurement precision

If visual indicators are added to all movement in the video stream, then operator detection capability is improved, but operator fatigue increases due to constant indicators

Engineering Contradiction:
Improvedetection capabilityVSAvoidoperator fatigue
Core Design Contradiction:
Measurement precisionVSEase of operation

Solution Approach 1:

The system dynamically adjusts the number and density of visual indicators based on event significance parameters. By filtering out low-significance events and only highlighting parameters that meet threshold criteria, the system maintains detection capability while reducing the overall quantity of indicators presented to the operator.

Inventive Principle:
Principle #35Parameter changes

Solution Approach 2:

Instead of highlighting all movement (excessive action), the system applies partial highlighting only to movement that meets significance thresholds. This selective approach provides enough information for detection while avoiding the overload that causes fatigue.

Inventive Principle:
Principle #16Partial or excessive action

3Area of stationary object

If multiple video streams are monitored to cover larger areas, then monitoring coverage is improved, but human resources and attention requirements increase

Engineering Contradiction:
Improvemonitoring coverageVSAvoidhuman resources
Core Design Contradiction:
Area of stationary objectVSQuantity of substance

Solution Approach 1:

The system introduces an automated event detection and filtering intermediary between multiple video streams and the operator. This intermediary processes events from multiple streams, applies filtering criteria, and presents only significant events to the operator, reducing the need for human resources to manually monitor all streams.

Inventive Principle:
Principle #24Intermediary (Mediator)

Solution Approach 2:

The monitoring system performs self-service by automatically detecting, filtering, and prioritizing events across multiple video streams without requiring proportional increases in human resources. The automated event processing capability allows the system to handle expanded coverage independently.

Inventive Principle:
Principle #25Self-service

Data Source

PatentEP3979633B1Displaying a video stream
Publication Date: 2025.02.19 AXIS
  • EP3979633B1 patent drawingFigure 1
  • EP3979633B1 patent drawingFigure 2a~2b
  • EP3979633B1 patent drawingFigure 2c~2d

AI summary

There is provided a computer implemented method for displaying a video stream of a scene (100) captured by a video capture device on a display of a client device. The method comprising: detecting a new event (112) in the scene, determining a new event area (114) in the scene within which the new event is detected, checking whether a prior event has been detected within the new event area during a predetermined time period preceding the new event, upon no prior event being detected during the predetermined time period, adding a visual indicator (116) to an image frame (103) temporally corresponding to the detection of the new event and to a number of subsequent image frames (103) of the video stream, wherein the visual indicator coincides with the new event area, and wherein the step of adding the visual indicator comprises gradually changing an appearance of the visual indicator throughout the number of subsequent image frames, and displaying the video stream with the added visual indicator on the display of the client device. There is also provided a related client device and a non-transitory computer-readable storage medium.