Rail Transit Vehicle Detection Using Laser Radar and Cameras

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing rail transit signal systems face inaccuracies in vehicle detection due to interference with axle counters, leading to safety risks from non-communicating trains on shared lines.

Innovation Solution

A vehicle detection method utilizing point cloud data and image information from laser radar and cameras to identify and classify vehicles, querying a legitimate-vehicle database to determine illegitimacy, and adjusting speed limits or sending alarms to ensure safe operation.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If axle counting devices are used for vehicle detection, then vehicle detection function is provided, but detection accuracy deteriorates due to interference requiring manual reset

Engineering Contradiction:

Improvevehicle detection reliabilityVSAvoiddetection accuracy

Core Design Contradiction:

ReliabilityVSMeasurement precision

Solution Approach 1:

The patent replaces the mechanical axle counting system with an optical detection system comprising laser radar and cameras. The laser radar emits laser beams to obtain point cloud data of vehicles, while cameras capture image information, eliminating the mechanical contact and interference issues of traditional axle counters. This substitution enables non-contact, interference-free vehicle detection with higher accuracy.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The patent introduces point cloud data and image information as intermediary data forms between the vehicle and the detection system. Instead of directly counting axles, the system uses laser radar to generate point cloud data and cameras to capture images, then processes these intermediary data forms to identify vehicle presence and characteristics, thereby avoiding direct mechanical interference.

Inventive Principle:

Principle #24Intermediary (Mediator)

2Reliability

If detection axle counter is disposed outside parking garage line, then non-communication train detection is enabled, but detection accuracy deteriorates due to interference from non-communication trains

Engineering Contradiction:

Improvesafety of vehicle-to-vehicle communication lineVSAvoiddetection result accuracy

Core Design Contradiction:

ReliabilityVSMeasurement precision

Solution Approach 1:

The patent changes the detection parameters from simple axle counting to multi-parameter analysis including point cloud data characteristics, image information, vehicle type classification, and vehicle identifier recognition. By analyzing multiple parameters simultaneously, the system can distinguish between legitimate vehicles and non-communication trains, improving detection accuracy while maintaining safety.

Inventive Principle:

Principle #35Parameter changes

Solution Approach 2:

The patent applies excessive action by using more detection resources (laser radar plus cameras) than the minimum required for simple vehicle detection. This redundant detection capability ensures that even when one detection method is interfered with, the other can provide accurate detection results, thereby overcoming the interference problem from non-communication trains.

Inventive Principle:

Principle #16Partial or excessive action

3Ease of operation

If manual reset is required for axle counter interference, then system complexity increases, but detection accuracy deteriorates due to inaccurate detection results

Engineering Contradiction:

Improvemanual reset operationVSAvoiddetection result accuracy

Core Design Contradiction:

Ease of operationVSMeasurement precision

Solution Approach 1:

The patent implements self-service by enabling the detection system to automatically recover from interference conditions without manual intervention. The optical detection system continuously monitors the environment and automatically adjusts to interference conditions, eliminating the need for manual reset operations while maintaining high detection accuracy through its inherent interference resistance.

Inventive Principle:

Principle #25Self-service

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

Accurately detects illegitimate vehicles, preventing safety risks by adjusting speed limits and communication responses, thereby enhancing the reliability of vehicle-to-vehicle communication systems.

Implementation Method 1

acquiring point cloud data of a target detection area by using a laser radar

Methodology Applied

Scientific EffectLaser: Laser

Implementation Method 2

acquiring image information of the target detection area by using a camera

Methodology Applied

Scientific EffectPhotography: Photography

Data Source

PatentUS20250104441A1Vehicle detection method, and controller, program and storage medium

Publication Date: 2025.03.27 BYD CO LTD

AI summary

A vehicle detection method includes: acquiring point cloud data of a target detection area and image information of the target detection area; in response to determining, according to the point cloud data, that there is a target vehicle in the target detection area, determining a target vehicle type of the target vehicle according to the point cloud data; determining a target vehicle identifier of the target vehicle according to the image information; and comparing the target vehicle type and the target vehicle identifier with a legitimate-vehicle information database, so as to determine whether the target vehicle is an illegitimate vehicle.