Vehicle Object Detection Using Stop Points for 3D Accuracy

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing obstacle detection systems in vehicles suffer from increased errors in three-dimensional position detection when encountering moving objects, which can lead to unsuitable object detection results for vehicle control.

Innovation Solution

An object detection device mounted on a vehicle that uses a combination of imaging sections, sonar sensors, and radar sensors to acquire and process images and ranging information, employing a motion stereo technique to calculate three-dimensional positions of stationary objects while distinguishing them from moving objects using stop points instead of movement points.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If motion stereo technique is used to detect three-dimensional position of objects, then object detection capability is improved, but detection precision deteriorates when moving objects are present

Engineering Contradiction:

Improveobject detection capabilityVSAvoidthree-dimensional position detection precision

Core Design Contradiction:

Adaptability or versatilityVSMeasurement precision

Solution Approach 1:

The detection space is segmented into two distinct categories: movement points (for moving objects) and stop points (for stationary objects). This segmentation allows the system to apply different detection methodologies to different object types, thereby maintaining high detection capability while ensuring precise position measurement for stationary objects by excluding moving object interference.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

Instead of trying to detect moving objects using motion stereo technique and accepting position errors, the invention inverts the approach by specifically using stop points (stationary objects) for accurate three-dimensional position detection. The system deliberately excludes movement points from stationary object detection, thereby achieving high precision by detecting what remains after removing moving object data.

Inventive Principle:

Principle #13The other way round (Inversion)

2Area of stationary object

If all detection points are used for object recognition, then detection coverage is improved, but detection accuracy deteriorates due to moving object interference

Engineering Contradiction:

Improvedetection coverageVSAvoidobject recognition accuracy

Core Design Contradiction:

Area of stationary objectVSMeasurement precision

Solution Approach 1:

The invention extracts and separates movement points corresponding to moving objects from the total set of detection points. By taking out these interfering movement points, the system can then use only the remaining stop points for stationary object recognition, thereby maintaining comprehensive detection coverage while eliminating accuracy degradation caused by moving object interference.

Inventive Principle:

Principle #2Taking out (Extraction)

3Productivity

If motion stereo technique is applied to moving objects, then object detection completeness is improved, but position coordinate accuracy deteriorates

Engineering Contradiction:

Improveobject detection completenessVSAvoidposition coordinate accuracy

Core Design Contradiction:

ProductivityVSMeasurement precision

Solution Approach 1:

The invention applies dynamic differentiation to the detection process by identifying and categorizing detection points based on their movement characteristics. Stop points (stationary objects) are dynamically separated from movement points (moving objects), allowing the system to maintain detection completeness for all objects while ensuring high position coordinate accuracy specifically for stationary objects by using only stop points for their detection.

Inventive Principle:

Principle #15Dynamics

Applied Scientific Principles

This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.

Function Achieved in This Case

Provides accurate object detection results suitable for vehicle controls by accurately distinguishing between stationary and moving objects, enhancing safety and operational efficiency.

Implementation Method 1

acquires position coordinates of a detection point corresponding to the object B on the basis of a plurality of images captured at different positions along with movement of the own vehicle (10) by one imaging section (21)

Methodology Applied

Scientific EffectMotion stereo technique: Parallax

Implementation Method 2

acquires ranging information corresponding to a distance to the object B by using a sonar sensor (22)

Methodology Applied

Scientific EffectSonar: Echo

Implementation Method 3

acquires ranging information corresponding to a distance to the object B by using a radar sensor (23)

Methodology Applied

Scientific EffectRadar: Radar

Data Source

PatentUS12469304B2Object detection device, object detection method, and storage medium

Publication Date: 2025.11.11 DENSO CORP

AI summary

An object detection device is configured to be mounted to an own vehicle to detect an object present around the own vehicle. The object detection device includes a coordinate acquisition section and an object recognition section. The coordinate acquisition section acquires position coordinates of a detection point corresponding to the object on the basis of a plurality of images captured at different positions along with movement of the own vehicle by one imaging section mounted to the own vehicle. The object recognition section recognizes the object without using position coordinates of a movement point that is a detection point corresponding to a moving object but using position coordinates of a stop point that is a detection point different from the movement point.