Object Tracking Device Dual Search Range Transfer Prevention

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing object tracking technologies face challenges with the phenomenon of 'transfer,' where a tracking device mistakenly tracks a similar object instead of the intended target, especially when overlap or shielding occurs, making it difficult to return to the correct target.

Innovation Solution

An object tracking device is designed with an extraction mechanism to identify target candidates, a dual search range setting mechanism to refine and expand the search area based on target reliability, and a model updating mechanism that uses target candidates from both search ranges to refine the target model, preventing mistaken tracking.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If the search range is limited to improve tracking speed, then tracking efficiency is improved, but the ability to distinguish target from similar objects deteriorates

Engineering Contradiction:

Improvetracking speedVSAvoidtarget discrimination accuracy

Core Design Contradiction:

ProductivityVSMeasurement precision

Solution Approach 1:

The patent divides the search process into two distinct phases with different search ranges. The first phase uses a limited search range for speed, while the second phase uses an expanded search range for accuracy. This segmentation allows the system to optimize for both speed and discrimination accuracy at different stages of the tracking process.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent performs preliminary target candidate extraction within a limited first search range to quickly identify potential targets. This preliminary action enables fast initial tracking while subsequent verification in a broader second search range ensures accurate target discrimination, preventing transfer to similar objects.

Inventive Principle:

Principle #10Preliminary action

2Measurement precision

If the search range is expanded to improve target discrimination, then tracking accuracy is improved, but processing time increases

Engineering Contradiction:

Improvetarget discrimination accuracyVSAvoidprocessing time

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The patent segments the search range into a first search range for quick preliminary screening and a second search range for comprehensive verification. This allows the system to perform detailed target discrimination only when necessary, reducing overall processing time while maintaining high accuracy.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent applies partial action by first searching within a limited first search range to identify candidate targets quickly. Only after this preliminary screening does it expand to the second search range for verification, avoiding the need to always perform a complete exhaustive search and thus reducing processing time.

Inventive Principle:

Principle #16Partial or excessive action

3Adaptability or versatility

If the target model is continuously updated to improve tracking adaptability, then tracking robustness is improved, but the risk of learning similar object features increases

Engineering Contradiction:

Improvetracking robustnessVSAvoidtarget identification reliability

Core Design Contradiction:

Adaptability or versatilityVSReliability

Solution Approach 1:

The patent applies local quality by using different search ranges for different purposes: the first search range for general tracking and the second, expanded search range specifically for model updating. This ensures that the target model is updated using features from a broader context, making it more distinctive and less likely to confuse the target with similar objects.

Inventive Principle:

Principle #3Local quality

Solution Approach 2:

The patent introduces the second search range as an intermediary mechanism between the target and the model updating process. By extracting target candidates from the expanded second search range before updating the model, the system ensures that the model learns from more distinctive features, acting as a mediator that prevents similar object features from being incorrectly incorporated.

Inventive Principle:

Principle #24Intermediary (Mediator)

4Reliability

If dual search ranges are used to prevent transfer, then target tracking reliability is improved, but device complexity increases

Engineering Contradiction:

Improvetarget tracking reliabilityVSAvoidtracking system complexity

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The patent segments the tracking system into two main components operating with different search ranges: a tracking component using the first search range for speed and a model updating component using the second search range for accuracy. This segmentation achieves reliable target tracking while keeping each component relatively simple and focused on its specific function.

Inventive Principle:

Principle #1Segmentation

Data Source

PatentUS12254640B2Object tracking device, object tracking method, and recording medium

Publication Date: 2025.03.18 NEC CORP

AI summary

In an object tracking device, the extraction means extracts target candidates from images in a time-series. The first setting means sets a first search range based on frame information and reliability of a target in a previous image in the time-series. The tracking means searches the target from the target candidates extracted within the first search range using the reliability indicating similarity to a target model, and tracks the target. The second setting means sets a second search range which includes the first search range and which is larger than the first search range. The model updating means updates the target model using the target candidates extracted within the first search range and the target candidates extracted within the second search range.