Block Motion Monitoring for Passenger Entrance-Exit Detection

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing technologies struggle to accurately detect human behavior in crowded or low-light environments, leading to potential inaccuracies in monitoring passenger alighting and boarding actions in vehicles.

Innovation Solution

A monitoring control device that divides captured images into blocks, detects motion vectors, and determines object movement based on vector direction and size without explicitly identifying the object, thereby reducing environmental influence on detection accuracy.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If human detection is performed based on video data, then passenger behavior can be monitored, but detection accuracy deteriorates in crowded or low-light environments

Engineering Contradiction:

Improvemonitoring reliabilityVSAvoiddetection accuracy

Core Design Contradiction:

ReliabilityVSMeasurement precision

Solution Approach 1:

The monitoring area is divided into multiple blocks, and motion detection is performed independently on each block. This segmentation allows the system to detect motion patterns in different regions without being affected by occlusions or poor lighting in specific areas, thereby maintaining detection accuracy in crowded or low-light environments.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

Instead of directly detecting human objects which is sensitive to environmental factors, the system uses motion vectors as an intermediary to infer object movement. The motion vectors derived from block-level analysis serve as a mediator that can reliably indicate passenger behavior without requiring direct visual identification, thus improving reliability in challenging environments.

Inventive Principle:

Principle #24Intermediary (Mediator)

2Measurement precision

If direct object detection is performed, then passenger identification is possible, but environmental factors like crowding and illumination significantly influence detection accuracy

Engineering Contradiction:

Improvedetection accuracyVSAvoidenvironmental influence

Core Design Contradiction:

Measurement precisionVSObject-affected harmful factors

Solution Approach 1:

The system extracts motion information from the video data by analyzing block-level changes between frames, rather than extracting object information directly. This extraction approach isolates the motion pattern from environmental干扰, allowing accurate detection of passenger movement regardless of crowding or lighting conditions.

Inventive Principle:

Principle #2Taking out (Extraction)

Solution Approach 2:

The system replaces the mechanical vision-based object detection approach with a motion-field analysis approach. Instead of relying on visual recognition of objects (which is affected by environment), it uses motion vector calculation based on pixel intensity changes, providing a more robust method that is less sensitive to environmental factors.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentEP4672171A1Monitoring control device, monitoring method, and non-transitory storage medium

Publication Date: 2025.12.31 TOYOTA JIDOSHA KK

Figure 1
Figure 2~3
Figure 4

AI summary

A monitoring control device (30) includes a processor (33). The processor (33) is configured to monitor the behavior of an object in a predetermined area, based on a captured image in which the area appears. The processor (33) is configured to divide a predetermined range in the captured image into a plurality of blocks, and is configured to detect a motion vector of each of the blocks. The processor (33) is configured to determine, based on a direction and a size of the motion vector of each of the blocks, whether the object moving toward an entrance-exit of the area is present in the captured image, without detecting the object appearing in the captured image.