3D Model Person Detection in Dam Water Zones

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing person detection systems, such as those using LiDAR, struggle to accurately distinguish between people and non-human objects in restricted areas, like water discharge zones around dams, making it difficult to detect individuals accurately.

Innovation Solution

A person detection device that generates a three-dimensional model of the restricted area using reflected laser light and employs pattern matching to identify human shapes within the model, allowing for precise detection of individuals regardless of their movement status.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Area of stationary object

If LiDAR is used to detect motion of objects, then detection coverage is improved, but ability to distinguish persons from non-human objects deteriorates

Engineering Contradiction:
Improvedetection coverageVSAvoidperson detection accuracy
Core Design Contradiction:
Area of stationary objectVSMeasurement precision

Solution Approach 1:

The patent transitions from two-dimensional motion detection to three-dimensional shape analysis by generating 3D models of detected objects. This dimensional enhancement allows the system to distinguish persons from non-human objects by analyzing their characteristic human-shaped geometry, thereby resolving the contradiction between broad detection coverage and accurate person identification.

Inventive Principle:
Principle #17Another dimension (Dimensionality change)

2Productivity

If motion detection is performed without object classification, then detection speed is improved, but detection accuracy for persons deteriorates

Engineering Contradiction:
Improvedetection speedVSAvoidperson detection accuracy
Core Design Contradiction:
ProductivityVSMeasurement precision

Solution Approach 1:

The system performs preliminary motion detection to identify potential targets, then immediately follows up with 3D model generation and shape-based classification. This two-stage approach maintains detection speed by quickly filtering out non-person objects through geometric analysis, while ensuring accurate person detection through subsequent detailed 3D shape examination.

Inventive Principle:
Principle #10Preliminary action

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

Enables accurate detection of people in restricted areas, ensuring safety by differentiating between human and non-human objects, and providing timely warnings for individuals in potentially dangerous zones.

Implementation Method 1

generating, in an area where water of a dam is discharged and an area in a periphery thereof, a three-dimensional model of a restricted area, based on reflected light associated with laser light with which the restricted area is irradiated

Methodology Applied
Scientific EffectLight reflection: Reflection

Data Source

PatentUS20240302496A1Person detection device, person detection system, and person detection method
Publication Date: 2024.09.12 NEC CORP
  • US20240302496A1 patent drawing
  • US20240302496A1 patent drawing
  • US20240302496A1 patent drawing

AI summary

A person detection device is provided with: a three-dimensional model generator which generates a three-dimensional model of a restricted area located in an area where water is discharged from a dam and in the surrounding area, on the basis of reflected light resulting from illumination of the restricted area with laser light; and a person detector which detects a person in the restricted area using the three-dimensional model.