Mobile Device Vehicle Detection Using HMM Motion Classification
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for detecting whether a mobile device is in a vehicle are inadequate, particularly when satellite positioning systems are not functional or accurate, and often rely on sensors that struggle to distinguish between vehicular and pedestrian movements at low speeds or in environments with poor satellite reception.
Innovation Solution
A system and method using a Hidden Markov Model (HMM) and state machine to classify motion states based on accelerometer data, combined with additional sensor data like GPS and audio signatures, to accurately determine if a mobile device is in a vehicle, even in scenarios where satellite positioning is unreliable.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If sensor-based detection methods are used to determine vehicle state, then the system can operate without satellite positioning, but the accuracy deteriorates in environments with poor satellite reception or at low speeds
Solution Approach 1:
The patent segments the vehicle detection problem into distinct motion states (pedestrian, vehicular, stationary) with specific transition rules. By dividing the continuous motion spectrum into discrete states with defined characteristics, the system achieves reliable classification even when individual sensor measurements are ambiguous, directly resolving the contradiction between reliability and precision.
Solution Approach 2:
The patent implements a dynamic state machine that adapts to changing motion conditions in real-time. The system continuously updates the current state based on accelerometer patterns and transition probabilities, allowing it to maintain accurate vehicle detection despite varying speeds and environmental conditions, thus improving both reliability and precision simultaneously.
2Measurement precision
If multiple sensors and probabilistic models are combined to improve detection accuracy, then measurement precision improves, but device complexity increases
Solution Approach 1:
The patent creates a universal motion state machine that handles multiple detection scenarios (pedestrian, vehicular, stationary states and transitions) through a single integrated framework. This multi-functional approach consolidates what would otherwise require separate detection systems, achieving high precision while managing complexity through code reuse and unified logic.
Solution Approach 2:
The state machine acts as an intermediary layer between raw accelerometer data and final vehicle detection results. By introducing this intermediate processing layer with defined states and transition rules, the system simplifies the complexity of directly interpreting complex sensor patterns, making the overall system more manageable while improving detection precision.
3Measurement precision
If accelerometer data is processed continuously to maintain accurate state detection, then measurement precision is maintained, but energy consumption increases
Solution Approach 1:
The patent implements periodic state updates based on motion state transitions rather than continuous processing. The system evaluates accelerometer data at intervals and only updates the vehicle state when transition conditions are met, reducing computational load and energy consumption while maintaining detection precision through event-driven processing.
Solution Approach 2:
The motion state machine is self-regulating, automatically adjusting its processing intensity based on current motion patterns. When the device is stationary or in clear pedestrian/vehicular states, the system reduces processing frequency, while maintaining higher precision during transition periods, thus optimizing the balance between energy consumption and detection accuracy.
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
This approach improves the accuracy of vehicle detection by leveraging probabilistic reasoning and sensor fusion, enabling robust identification of vehicular states even in challenging environments, thus enabling enhanced functionality in mobile devices.
Implementation Method 1
obtain acceleration data from one or more accelerometers
Data Source
Figure 1
Figure 2A
Figure 2B
AI summary
Systems and methods herein enable a mobile device to detect that a user is traveling in association with a vehicle based at least on motion data. In some embodiments, accelerometer data is used. Motion data is leveraged in combination with various observations regarding vehicular movement to determine whether or not a mobile device is located in or on the vehicle. For instance, before entering the state of vehicular movement, it can be determined that the user is first in a walking state (e.g., walking to the car, bus, etc., and entering it). Likewise, after exiting the state of vehicular movement, the user re-enters the walking state (e.g., after stepping out of the car, bus, etc., the user again begins walking). Further, it can be determined that when the user is in the walking state, the accelerometer signals appear different to any accelerometer signals seen in the vehicular movement state.