Image Processing Device for Accurate Object Counting

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing object detection systems often suffer from false detections or missed detections, making it difficult to accurately count objects in images, particularly in congested scenes.

Innovation Solution

An image processing device with a display control unit that allows users to visually correct detection marks and adjust the number of detected objects by adding or deleting marks, and a detection unit that uses multiple conditions to identify and display detected and non-detected objects, enabling user intervention for accurate counting.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If object detection is performed automatically in congested scenes, then productivity is improved, but measurement precision deteriorates due to false detections or un-detections

Engineering Contradiction:
Improveobject counting speedVSAvoiddetection accuracy
Core Design Contradiction:
ProductivityVSMeasurement precision

Solution Approach 1:

The system displays detection marks on the image and provides feedback to the user about detected objects. The user can visually verify the detection results and provide correction feedback by adding or deleting marks, which improves measurement precision while maintaining automated detection for productivity

Inventive Principle:
Principle #23Feedback

Solution Approach 2:

The system allows users to easily correct detection errors through simple operations like adding or deleting marks directly on the displayed image. This self-service correction mechanism enables users to fix false detections or un-detections without requiring complex manual counting, thus improving precision while preserving the efficiency of automated detection

Inventive Principle:
Principle #25Self-service

2Measurement precision

If multiple detection conditions are applied to improve detection accuracy, then measurement precision is improved, but device complexity increases

Engineering Contradiction:
Improvedetection accuracyVSAvoiddetection system complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The detection system is segmented into an automated detection unit that applies multiple detection conditions and a user correction unit that allows manual adjustment. This segmentation enables the system to handle complex detection requirements while providing a simple interface for users to correct errors, thus improving precision without overwhelming the user with complexity

Inventive Principle:
Principle #1Segmentation

3Measurement precision

If manual correction of detection marks is allowed, then measurement precision is improved, but ease of operation deteriorates due to additional operations required

Engineering Contradiction:
Improvedetection accuracyVSAvoidcorrection operation simplicity
Core Design Contradiction:
Measurement precisionVSEase of operation

Solution Approach 1:

The system enables users to perform self-service correction by allowing direct addition or deletion of detection marks through simple operations. Users can easily adjust detection results by interacting with the displayed marks without requiring complex procedures, thus improving precision while maintaining ease of operation

Inventive Principle:
Principle #25Self-service

Data Source

PatentUS10922864B2Image processing device, image processing method and program, for object detection in an image
Publication Date: 2021.02.16 CANON KK
  • US10922864B2 patent drawing
  • US10922864B2 patent drawing
  • US10922864B2 patent drawing

AI summary

An image processing device includes: a display control unit configured to cause a display unit to display an image, and to cause the display unit to display a mark corresponding to a detection object detected in the image; and an output unit configured to output a number of the marks displayed on the display unit, wherein the display control unit adds or deletes a mark according to a user operation, and the output unit outputs the number of marks after the addition or after the deletion.