Fare Gate Radar Reflection Layout for ML Anomaly Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Fare evasion poses security threats and revenue loss in transit systems due to complex object detection at fare gates, particularly during peak congestion, with challenges including restricted coverage, integration of complex designs, power consumption, and viewpoint variations.
Innovation Solution
An object detection system using a radar and reflective surface with a machine learning engine to generate clustered point clouds, enhance field-of-view through anomalous reflections, and a forensic engine to capture media of anomalies.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional object detection methods are used at fare gates, then the system is simpler to implement, but detection accuracy and coverage are restricted
Solution Approach 1:
The detection system is segmented into multiple independent components: radar unit, reflective surface, machine learning engine, and forensic engine. Each component performs a specific function, allowing the system to achieve high detection accuracy through coordinated operation of simpler individual elements rather than requiring a single complex detection device.
Solution Approach 2:
A reflective surface is introduced as an intermediary element between the radar and the objects to be detected. This reflective surface redirects radar signals to improve detection coverage and accuracy, particularly for objects that would otherwise be in blind spots or have poor direct radar return characteristics.
2Area of stationary object
If radar and reflective surface are positioned to maximize coverage, then detection coverage is improved, but the system occupies more space and requires complex integration
Solution Approach 1:
The reflective surface is positioned and oriented at specific angles to redirect radar signals in three-dimensional space, effectively expanding detection coverage by utilizing spatial dimensions rather than simply increasing the physical footprint of the radar unit itself.
Solution Approach 2:
The system optimizes detection coverage by adjusting parameters such as radar frequency, transmit power, and reflective surface orientation angles, rather than increasing system size. These parameter changes allow coverage expansion without proportionally increasing physical footprint or integration complexity.
3Measurement precision
If multiple sensors are used to detect valid riders, then detection accuracy is improved, but power consumption increases
Solution Approach 1:
The radar system performs multiple detection functions simultaneously: identifying valid riders, detecting anomalies, and providing situational awareness. This multi-functionality eliminates the need for separate sensor systems for each function, reducing overall power consumption while maintaining high detection accuracy through the versatile radar platform.
4Reliability
If the system detects all objects including anomalies, then security is improved, but false positives may increase causing bottlenecks
Solution Approach 1:
The system replaces manual inspection and decision-making with automated machine learning algorithms that analyze radar data. This substitution enables rapid, consistent anomaly detection and classification, improving security reliability while maintaining high throughput by eliminating manual review bottlenecks. The forensic engine further refines this by providing contextual information to reduce false positives.
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
Enhances object detection capabilities beyond line-of-sight, reducing fare evasion by accurately identifying anomalies and capturing relevant media for security and revenue protection.
Implementation Method 1
The radar emits a signal and generates a primary clustered point cloud from the signal reflected back from the object
Implementation Method 2
The radar emits a signal and generates a primary clustered point cloud from the signal reflected back from the object
Implementation Method 3
The reflective surface reflects the signal at reflection angles and has a secondary FOV with a secondary clustered point cloud of the object
Implementation Method 4
enhance field-of-view through anomalous reflections
Data Source
AI summary
Systems and methods for object detection through a fare gate in a transit system is disclosed. The object detection system includes a radar positioned at a first position and a reflective surface positioned at a second position of the fare gate, a machine learning (ML) engine, and a forensic engine. The radar emits a signal and generates a primary clustered point cloud from the signal reflected back from the object in a primary field-of-view (FOV). The reflective surface has a secondary FOV with a secondary clustered point cloud of the object. The ML engine extracts features of the object from the primary clustered point cloud and the secondary clustered point cloud and correlates the features with object profiles. The ML engine further determines that an object profile corresponds with an anomaly and generates a flag. The forensic engine captures media corresponding to the object associated with the flag.