Vehicle Position Inference for Parking Space Detection Without Lines

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing image processing devices struggle to detect parking frames when there is no information of partition lines, such as white lines, making it difficult to suggest parking frames to drivers.

Innovation Solution

An information processing device that acquires environmental information around the vehicle, detects vacant spaces using the positional relationship between other vehicles, and determines if the vehicle can be parked in those spaces.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If partition line detection is used to identify parking frames, then parking frame detection accuracy is improved, but the system fails when partition line information is unavailable

Engineering Contradiction:
Improveparking frame detection accuracyVSAvoidsystem adaptability to various parking environments
Core Design Contradiction:
Measurement precisionVSAdaptability or versatility

Solution Approach 1:

The patent introduces other vehicles as intermediary objects to infer parking frame locations. Instead of directly detecting parking frames through partition lines, the system uses the positional relationships between multiple detected vehicles to indirectly identify vacant parking spaces, thereby overcoming the limitation of unavailable partition line information

Inventive Principle:
Principle #24Intermediary (Mediator)

Solution Approach 2:

The patent creates a virtual representation of the parking environment by detecting the positions and orientations of multiple vehicles. This copied spatial information is then processed to infer parking frame locations, allowing the system to replicate parking frame detection functionality without relying on actual partition line markings

Inventive Principle:
Principle #26Copying

2Ease of operation

If image processing is used to detect parking frames, then parking assistance functionality is provided, but the system cannot operate when partition lines are absent

Engineering Contradiction:
Improveparking assistance functionalityVSAvoidsystem reliability in partition line-less environments
Core Design Contradiction:
Ease of operationVSReliability

Solution Approach 1:

The patent makes the image processing system universal by enabling it to function through multiple detection methods: traditional partition line detection when available, and vehicle-based positional relationship detection when partition lines are absent. This multi-functionality ensures the system operates reliably across diverse parking environments without requiring partition line markings

Inventive Principle:
Principle #6Universality (Multi-functionality)

3Device complexity

If detection relies on partition line information, then detection simplicity is maintained, but detection capability is lost when partition lines are not present

Engineering Contradiction:
Improvedetection method simplicityVSAvoidparking frame detectability
Core Design Contradiction:
Device complexityVSDifficulty of detecting and measuring

Solution Approach 1:

The patent segments the detection task into two independent stages: first detecting multiple vehicles and their positional relationships, then using this information to infer parking frame locations. This segmentation allows the system to handle the complexity of partition line-less environments by breaking down the detection problem into manageable components that can be solved through vehicle positioning alone

Inventive Principle:
Principle #1Segmentation

Data Source

PatentUS12437639B2Information processing device, information processing method, and information processing program
Publication Date: 2025.10.07 SONY SEMICON SOLUTIONS CORP
  • US12437639B2 patent drawing
  • US12437639B2 patent drawing
  • US12437639B2 patent drawing

AI summary

An information processing device according to the present disclosure includes an acquisition unit, a detection unit (74), and a determination unit (75). The acquisition unit acquires environmental information around a host vehicle (1). The detection unit (74) detects a vacant space (Rv) in an interest area (R) set around the host vehicle (1) on the basis of a positional relationship between a plurality of other vehicles (100) included in the environmental information. The determination unit (75) determines whether or not the host vehicle (1) can be parked in the vacant space (Rv) that has been detected.