Surveillance Video Processing Selective Resolution Segmentation

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current video surveillance systems face high resource demands and costs due to processing and storing high-resolution image data, necessitating efficient data processing techniques to reduce bandwidth and storage requirements.

Innovation Solution

A method and apparatus that utilize a detection and identification engine to process video data from high-resolution cameras, selectively applying higher resolution to areas of interest (e.g., faces or vehicles) while maintaining lower resolution for the rest of the scene, allowing for fine control over image processing parameters via user input.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If high resolution image data is transmitted and stored, then image quality is improved, but bandwidth and storage capacity requirements increase significantly

Engineering Contradiction:
Improveimage qualityVSAvoiddata volume
Core Design Contradiction:
Measurement precisionVSQuantity of substance

Solution Approach 1:

The image data stream is segmented into multiple resolutions based on spatial importance. The scene is divided into regions of interest (ROI) that contain detected objects or events, and non-ROI background areas. ROI portions are transmitted at high resolution while background areas are transmitted at lower resolution, thereby maintaining image quality for important elements while reducing overall data volume.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

Different quality levels are applied to different regions of the image based on their importance. High resolution is applied locally to regions containing detected objects or events where detailed analysis is needed, while lower resolution is applied to background regions where detailed information is less critical. This selective quality approach optimizes the balance between image quality and data transmission/storage requirements.

Inventive Principle:
Principle #3Local quality

2Quantity of substance

If motion detection is used to transmit only changed areas, then data transmission is reduced, but complete scene information is lost

Engineering Contradiction:
Improvedata transmission volumeVSAvoidscene information
Core Design Contradiction:
Quantity of substanceVSLoss of information

Solution Approach 1:

The system performs preliminary low-resolution analysis of the entire scene to detect objects or events of interest before finalizing the transmission strategy. This preliminary detection phase identifies regions that require high-resolution transmission, ensuring that no important scene information is missed while still optimizing the overall data transmission volume through selective high-resolution transmission.

Inventive Principle:
Principle #10Preliminary action

3Loss of information

If entire high resolution frames are transmitted at regular intervals, then complete scene coverage is achieved, but resource consumption is prohibitive

Engineering Contradiction:
Improvescene coverageVSAvoidresource consumption
Core Design Contradiction:
Loss of informationVSLoss of energy

Solution Approach 1:

Instead of transmitting complete high-resolution frames, the system applies partial action by transmitting only the necessary portions of the scene at high resolution. The detected objects or events and their surrounding context are transmitted in high resolution, while the remainder of the scene is transmitted at lower resolution or omitted, thereby achieving adequate scene coverage with significantly reduced resource consumption.

Inventive Principle:
Principle #16Partial or excessive action

Data Source

PatentEP3420544B1A method and apparatus for conducting surveillance
Publication Date: 2024.02.07 IOMNISCIENT
  • EP3420544B1 patent drawingFigure 1
  • EP3420544B1 patent drawingFigure 2
  • EP3420544B1 patent drawingFigure 3

AI summary

The present invention relates to a method and apparatus for processing video image data, so as to apply different types of processing to different aspects of video image data. A detection process is arranged to detect a item, object or event appearing or occurring in a scene being viewed by an image device. An image data process is responsive to the detection of the object or event and to control information to process the image data for a portion of the scene where the object or event appears or occurs, differently from the processing of the image data associated with the rest of scene. For example, the object may be a person's face, and the face image data may be processed to produce high resolution data, the rest of the scene being provided in low resolution. This saves on processing, transmission and storage.