Dynamic High Sampling Rate for Region of Interest in Imaging Systems

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing imaging systems face challenges in balancing computation resources and time while processing high-resolution image frames, particularly when only a selected region of interest (ROI) is processed, which may miss important details and increase computational load.

Innovation Solution

A system and method that enhance the sampling rate for a selected region of interest (SROI) by defining SROI in image frames, acquiring partial datasets during residual time within image frame handling cycles, and using a tracking module to detect rails and define safety zones, allowing for increased resolution without altering frame rate or computational load.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If high resolution computation is applied to the entire image frame, then measurement precision is improved, but computation resources increase and computation time increases

Engineering Contradiction:
Improvedetection precisionVSAvoidcomputation speed
Core Design Contradiction:
Measurement precisionVSProductivity

Solution Approach 1:

The image frame is segmented into multiple regions of interest (ROIs) based on detected features such as rails, obstacles, or areas with motion. Only these segmented ROIs are processed at high resolution, while the rest of the frame is processed at lower resolution or skipped, thereby maintaining detection precision for critical areas while reducing overall computation resources and time.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

Different regions of the image frame are assigned different processing qualities. High-resolution computation is applied locally to ROIs that contain important features or potential obstacles, while other regions receive lower-resolution processing. This local quality differentiation maintains measurement precision where needed while improving overall productivity.

Inventive Principle:
Principle #3Local quality

2Productivity

If high resolution computation is applied to a selected region of interest, then computation time is reduced, but important image details may be missed

Engineering Contradiction:
Improvecomputation speedVSAvoidloss of important data
Core Design Contradiction:
ProductivityVSLoss of information

Solution Approach 1:

A low-resolution pre-processing stage is performed on the entire image frame before selecting ROIs for high-resolution computation. This preliminary action identifies potential regions of interest containing important features or obstacles, ensuring that no critical data is missed before applying the computationally intensive high-resolution processing only to those identified areas.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system uses feedback from initial low-resolution analysis and ongoing detection results to dynamically adjust and expand ROIs. If important features or obstacles are detected at the boundaries of current ROIs, the ROI selection is updated to include these areas, ensuring that no significant information is lost while maintaining computational efficiency.

Inventive Principle:
Principle #23Feedback

3Reliability

If the frame rate is increased to improve obstacle detection, then probability of detection is improved, but computation resources increase

Engineering Contradiction:
Improveprobability of detectionVSAvoidcomputation load
Core Design Contradiction:
ReliabilityVSProductivity

Solution Approach 1:

Instead of processing the entire frame at high frame rates, the system segments the frame into ROIs and applies high-frame-rate processing only to these segmented regions. This maintains a high probability of detecting obstacles in critical areas while reducing the overall computation load by excluding processed regions from further high-frequency analysis.

Inventive Principle:
Principle #1Segmentation

Data Source

PatentEP3787953B1System and method for dynamic selection of high sampling rate for a selected region of interest
Publication Date: 2025.07.30 RAIL VISION LTD
  • EP3787953B1 patent drawingFigure 1A
  • EP3787953B1 patent drawingFigure 1B
  • EP3787953B1 patent drawingFigure 2

AI summary

Generally, a system including an imaging device and a processing unit is disclosed. The imaging device may be configured to acquire a plurality of datasets of corresponding plurality of image frames by performing corresponding plurality of image frame handling cycles. The processing unit may be configured to define a special region of interest (SROI) in each of at least some of the plurality of the image frames acquired by the imaging device, based on the datasets of the respective image frames. The imaging device may be further configured to acquire at least one partial dataset of the SROI, during each of at least some of the plurality of image frame handling cycles and within a residual time between an end of an image frame acquiring time and an end of the respective image frame handling cycle.