Object Recognition Device Using Sensor Angle and Distance Resolution

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing object recognition devices struggle to accurately identify the position of a detection point on an object due to sensor resolution limitations, leading to decreased precision in track data.

Innovation Solution

An object recognition device that includes a temporary setting unit to set candidate points based on sensor specifications and an update processing unit to correct the detection point position and update track data accordingly.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Device complexity

If the sensor resolution is low, then the device complexity is reduced, but the measurement precision of the detection point position deteriorates

Engineering Contradiction:

Improvesensor resolutionVSAvoiddetection point position

Core Design Contradiction:

Device complexityVSMeasurement precision

Solution Approach 1:

The patent segments the object surface into multiple candidate points based on the detection point's angle and distance. Instead of treating the object as a single entity, the system divides it into discrete positional candidates, allowing precise identification even with low-resolution sensors by evaluating multiple segmented possibilities.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent introduces additional dimensional parameters (angle and distance from the sensor) to resolve the position identification problem. By adding these dimensional constraints, the system can uniquely identify the detection point position on the object surface even when the sensor resolution is insufficient for direct identification.

Inventive Principle:

Principle #17Another dimension (Dimensionality change)

2Device complexity

If the detection point position cannot be accurately identified, then the device complexity is reduced, but the reliability of the track data deteriorates

Engineering Contradiction:

Improveposition identification capabilityVSAvoidtrack data precision

Core Design Contradiction:

Device complexityVSReliability

Solution Approach 1:

The patent implements a feedback mechanism where the system iteratively tests candidate points by fitting the detection point to the shape model. The track data is continuously refined by comparing detected positions with model predictions, allowing the system to achieve reliable tracking even when initial position identification is ambiguous due to sensor resolution limits.

Inventive Principle:

Principle #23Feedback

Solution Approach 2:

The patent performs preliminary action by pre-establishing the shape model of the object and pre-calculating candidate points before actual detection. This preparation allows the system to quickly and reliably identify detection point positions during tracking by comparing against pre-computed reference data, improving both speed and reliability.

Inventive Principle:

Principle #10Preliminary action

Data Source

PatentUS12299919B2Object recognition device and object recognition method based on angle and distance resolution of a sensor

Publication Date: 2025.05.13 MITSUBISHI ELECTRIC CORP

AI summary

Provided is an object recognition device including a temporary setting unit and an update processing unit. The temporary setting unit sets, based on specifications of an external information sensor that has detected an object, a position of at least one candidate point on the object. The update processing unit corrects a position of a detection point with respect to the external information sensor at a time when the external information sensor has detected the object based on the position of the candidate point on the object, and updates track data indicating a track of the object based on a position of the detection point with respect to the external information sensor after the correction.