Parking Lot Depth Map Analysis and Flood Prediction

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current methods for determining parking lot fullness are costly and inefficient, and existing flood prediction technologies lack accuracy, leading to potential accidents and material losses due to unclear parking conditions and unpredictable flooding.

Innovation Solution

A method and electronic device using a depth map to analyze parking lot situations by generating binarized data from captured images and a learning model to predict flooding, allowing for real-time processing and communication of parking availability and flood risk.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If sensors are placed in parking areas to check vehicle presence, then parking lot fullness detection accuracy is improved, but system construction cost and management complexity increase

Engineering Contradiction:

Improveparking lot fullness detection accuracyVSAvoidsystem construction and management cost

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The patent replaces mechanical sensors and wired detection systems with a camera-based optical system. The camera captures images of the parking lot, and image processing algorithms automatically detect vehicle presence and count parked vehicles, eliminating the need for physical sensors in each parking space.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The patent creates a visual copy (image) of the parking lot scene using a camera, and processes this copy to extract information about vehicle presence. This allows detection without physical interaction with the parking spaces, reducing system complexity while maintaining detection accuracy.

Inventive Principle:

Principle #26Copying

2Ease of operation

If vehicles are allowed to circle around the parking lot when full, then drivers can search for parking spaces, but accident risk increases due to unclear entry/exit directions and narrow paths

Engineering Contradiction:

Improvedriver's ability to find parking spaceVSAvoidaccident risk

Core Design Contradiction:

Ease of operationVSObject-affected harmful factors

Solution Approach 1:

The system continuously monitors parking lot fullness using image processing and provides real-time feedback to drivers through display devices or mobile applications. When the parking lot is full, drivers receive immediate notification before entering, preventing unnecessary circulation and reducing accident risk while maintaining operational convenience when spaces are available.

Inventive Principle:

Principle #23Feedback

3Loss of time

If drivers who cannot find parking spaces are allowed to temporarily stop or park anywhere, then they can avoid circling the parking lot, but accident risk increases

Engineering Contradiction:

Improvetime spent searching for parking spaceVSAvoidaccident risk

Core Design Contradiction:

Loss of timeVSObject-affected harmful factors

Solution Approach 1:

The system performs preliminary detection of parking lot fullness conditions and provides advance information to drivers before they enter or while they are still outside the parking lot. This allows drivers to make informed decisions about whether to enter, eliminating the need for temporary illegal parking while minimizing time loss through early notification.

Inventive Principle:

Principle #10Preliminary action

Data Source

PatentUS20240394860A1Method and electronic device for parking lot operation based on depth map and for flooding prediction using learning model

Publication Date: 2024.11.28 SK PLANET CO LTD

AI summary

A captured image of a target area corresponding to a parking lot is captured through a camera and generate a depth map for the captured image. Binarized data for the generated depth map is produced. The number of vehicles parked in the target area is calculated based on the binarized data, and parking situation analysis is performed according to the number of parked vehicles. Processing is performed according to a result of the parking situation analysis. Also, flooding is predicted using a learning model.