Pet-Immune Human Detection Using Multi-Camera Aspect Ratio Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional security systems often generate false alarms due to the presence of pets or fail to detect humans when they crawl, and existing pet-immune sensors are ineffective in distinguishing between humans and large dogs or missing alarms when humans move in a crawling position.
Innovation Solution
A security system incorporating cameras sensitive to visible and near-infrared spectra, with image processors that analyze pixel changes to determine object size, aspect ratio, and motion, and a pet indicator switch to differentiate between pets and humans, reducing false alarms and improving detection speed.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If conventional motion detection sensors (PIR or Dual Tec) are used to detect intruders, then the system can detect moving objects, but false alarms are generated when pets are present in the protected area
Solution Approach 1:
The patent transitions from conventional 2D motion detection (PIR/Dual Tec sensors detecting infrared or microwave signals) to 3D spatial analysis using multiple cameras. By capturing images from multiple perspectives and analyzing depth information, the system can distinguish between pets and humans based on their spatial characteristics, body proportions, and movement patterns in three-dimensional space, thereby reducing false alarms while maintaining detection accuracy.
2Object-generated harmful factors
If pet-immune sensors are used to ignore pets, then false alarms from pets are reduced, but the system fails to detect humans when they crawl or when they resemble large dogs
Solution Approach 1:
The patent divides the detection task into multiple segments: first, motion detection triggers an event; second, multiple cameras capture images of the moving object; third, image processing analyzes body parts, proportions, and spatial relationships; fourth, classification algorithms distinguish between pets and humans based on segmented features. This segmented approach allows the system to maintain pet immunity while avoiding missed detections, as each segment contributes specific information that collectively enables accurate classification.
3Device complexity
If conventional sensors are used, then the system structure is simple, but the system cannot distinguish between crawling humans and dogs
Solution Approach 1:
The patent introduces image processing algorithms and artificial intelligence classifiers as intermediaries between the cameras and the detection decision. These intermediaries analyze the captured images, extract features such as body shape, limb proportions, and movement patterns, and use this information to accurately classify objects as humans or pets. This intermediary layer enables high measurement precision while keeping the overall system structure manageable by delegating complex analysis to software rather than hardware.
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
The system effectively reduces false alarms and enhances the speed of human intruder detection by accurately distinguishing between pets and humans, and differentiating between crawling humans and dogs, thereby improving overall security system performance.
Implementation Method 1
In one preferred embodiment, the cameras are sensitive to and collect images in the visible spectrum of 390-750 nm as well as the near infrared spectrum of up to 900 nm.
Data Source
AI summary
A method and apparatus are provided, wherein the apparatus performs the steps of detecting a moving object within a secured area, determining a size of the moving object, determining that the size exceeds a predetermined size threshold value associated with an animal, determining an aspect ratio of the moving object, determining that the aspect ratio meets a predetermined aspect ratio threshold value associated with an animal or crawling human, but not an upright human, retrieving an indicator from memory that establishes whether an animal is present or not present within the secured area, and setting an alarm upon detecting that the moving object exceeds the predetermined size threshold value, that the determined aspect ratio meets the predetermined aspect ratio threshold value of an animal or crawling human, and that the indicator establishes that there is no animal present in the secured area.