Neural Boarding Area Detection From Driving Image Strips
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing systems fail to accurately provide information on safe vehicle boarding areas, leading to potential accidents and inefficiencies when pedestrians or drivers are unsure of suitable locations to enter or exit vehicles.
Innovation Solution
An apparatus using an artificial neural network to segment and classify vehicle driving images into boarding possible and impossible areas, generating reliable information for drivers and pedestrians through image segmentation, classification, and feature extraction modules.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If a driver stops a vehicle on a road adjacent to a sidewalk to pick up an acquaintance, then the driver can board the acquaintance, but the driver may cause accidents or waste time hovering around to find a boarding possible area
Solution Approach 1:
The system performs preliminary analysis of the road environment using image recognition technology to identify safe boarding areas before the driver arrives. The server sends boarding area information to the driver's terminal in advance, allowing the driver to directly navigate to the designated area without hovering or guessing, thus preventing accidents and saving time
Solution Approach 2:
A server acts as an intermediary between the driver and the boarding location. The server receives image data from the driver's terminal, analyzes the environment through image recognition, determines safe boarding areas, and provides this information back to the driver. This intermediary process ensures safety while maintaining ease of operation
2Loss of information
If geographic information of the boarding area is not accurately known, then the driver can call a taxi, but the driver cannot accurately select a safe boarding location
Solution Approach 1:
The system replaces manual geographic information collection and analysis with automated image recognition technology. The driver's terminal captures images of the surrounding environment, the server analyzes these images to automatically identify safe boarding areas, and provides precise location information. This substitution eliminates the need for manual geographic data while achieving high precision in boarding location identification
Solution Approach 2:
The system creates a visual copy of the real-world environment through images captured by the driver's terminal camera. This image copy is then analyzed by the image recognition system to identify boarding areas, effectively transferring spatial information from the physical world to the digital domain for accurate measurement and analysis
3Reliability
If the driver hovers around to find a boarding possible area, then the driver may find a safe location, but the driver wastes time and may cause accidents
Solution Approach 1:
The system performs preliminary identification of safe boarding areas through image recognition before the driver needs to stop the vehicle. The server analyzes the environment, determines safe areas, and provides this information in advance, allowing the driver to directly navigate to the identified location without hovering or searching, thus eliminating both time loss and safety risks
Solution Approach 2:
The system provides feedback to the driver about safe boarding areas based on real-time image analysis. The driver's terminal receives information about identified boarding areas, allowing the driver to adjust the vehicle's position accordingly. This feedback loop eliminates the need for trial-and-error hovering while ensuring safety
Data Source
AI summary
An embodiment provides an apparatus for determining a vehicle boarding possible area for a driving image using an artificial neural network, including: an image segmentation module that obtains a driving image for a driving direction of a vehicle from a camera module and segments the driving image into a plurality of image strips; a pre-trained boarding availability classification artificial neural network module that uses the image strip as input information and boarding availability information for the image strip as output information; a feature extraction module that extracts an activation map including feature information on the image strip from the boarding availability classification artificial neural network module; and an area information generation module that generates boarding possible area information for the image strip based on the feature information included in the activation map.