Object Tracking Apparatus Using Template and Histogram Matching

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing object tracking techniques face challenges in accurately tracking objects with significant changes in posture or appearance, as template matching struggles with correct region estimation when appearance changes are great, while histogram matching is less accurate in detailed position adjustment.

Innovation Solution

An object tracking apparatus that combines template matching and histogram matching, using a first registering unit for template registration, a second registering unit for histogram registration, and an object region determination unit that selects the appropriate region based on estimation results from both methods, within a predetermined range, to enhance tracking robustness and accuracy.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If template matching is used for object tracking, then position estimation accuracy is improved when object appearance changes are small, but tracking reliability deteriorates when object posture changes significantly

Engineering Contradiction:

Improveposition estimation accuracyVSAvoidtracking reliability

Core Design Contradiction:

Measurement precisionVSReliability

Solution Approach 1:

The patent combines template matching and histogram matching into a unified object tracking system. Template matching provides high position estimation accuracy when object appearance is stable, while histogram matching ensures tracking reliability when object posture changes significantly. The system integrates both methods to achieve both precision and reliability simultaneously.

Inventive Principle:

Principle #5Merging (Combining)

Solution Approach 2:

The patent changes the matching parameters by using different evaluation standards for different scenarios. Template matching uses image data as evaluation standard for high precision, while histogram matching uses histogram data as evaluation standard for robustness against posture changes. The system dynamically selects or combines these parameter approaches based on tracking conditions.

Inventive Principle:

Principle #35Parameter changes

2Reliability

If histogram matching is used for object tracking, then tracking robustness against posture changes is improved, but position estimation accuracy deteriorates

Engineering Contradiction:

Improvetracking robustnessVSAvoidposition estimation accuracy

Core Design Contradiction:

ReliabilityVSMeasurement precision

Solution Approach 1:

The patent merges histogram matching with template matching to compensate for the weakness of histogram matching in position estimation accuracy. While histogram matching provides robust tracking under posture changes, the integration with template matching restores the high position estimation accuracy that histogram matching alone cannot achieve.

Inventive Principle:

Principle #5Merging (Combining)

3Measurement precision

If only template matching is used, then detailed position estimation accuracy is improved, but tracking stability under appearance changes deteriorates

Engineering Contradiction:

Improveposition estimation accuracyVSAvoidtracking stability

Core Design Contradiction:

Measurement precisionVSStability of the object's composition

Solution Approach 1:

The patent combines template matching and histogram matching to achieve both detailed position estimation accuracy and tracking stability. Template matching delivers precise position estimates, while histogram matching ensures stability under appearance changes by providing alternative matching capability when object appearance varies.

Inventive Principle:

Principle #5Merging (Combining)

4Stability of the object's composition

If only histogram matching is used, then tracking stability under appearance changes is improved, but detailed position estimation accuracy deteriorates

Engineering Contradiction:

Improvetracking stabilityVSAvoidposition estimation accuracy

Core Design Contradiction:

Stability of the object's compositionVSMeasurement precision

Solution Approach 1:

The patent integrates histogram matching with template matching to resolve the accuracy deficiency. While histogram matching ensures tracking stability under appearance changes, the combination with template matching restores detailed position estimation accuracy that histogram matching alone cannot provide.

Inventive Principle:

Principle #5Merging (Combining)

Data Source

PatentUS10013632B2Object tracking apparatus, control method therefor and storage medium

Publication Date: 2018.07.03 CANON KK

AI summary

An image capture apparatus functions as an object tracking apparatus for tracking an object included in provided images, registers a partial image indicating an object as a template, and performs template matching for estimating a region by using the template and histogram matching for registering a histogram of a partial image indicating the object and estimating a region by using the histogram. In a case where a distance between the estimation region based on the histogram matching and the estimation region based on the template matching is within a predetermined range, the estimation region based on the template matching is employed as an object region, and in a case where the distance between the estimation region based on the histogram matching and the estimation region based on the template matching is not within the predetermined range, the estimation region based on the histogram matching is employed as the object region.