Mobile Object Location via Motion Profile Comparison
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing systems face challenges in accurately predicting the location of actively moving mobile devices within small or enclosed spaces, such as buildings or parking garages, due to inaccuracies in existing location determination techniques.
Innovation Solution
The system determines the location of a mobile object by comparing motion profiles generated from sensor data and video frame sequences, using algorithms like Kalman filters and neural networks to correlate the motion of the object with candidate profiles, allowing for accurate identification even if the object is not parked in a designated space.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If traditional location determination techniques are used in enclosed spaces, then the system can operate in buildings or parking garages, but the location accuracy deteriorates significantly
Solution Approach 1:
The patent introduces motion profiles as an intermediary element that bridges the gap between limited sensor data and accurate location determination. By comparing motion profiles from multiple sources (sensor data, video frames, map data), the system can accurately identify vehicle locations even in enclosed spaces where traditional GPS fails. The motion profile acts as a mediator that correlates different data sources to resolve location ambiguity.
Solution Approach 2:
The system changes the parameters used for location determination from relying solely on GPS coordinates to using motion characteristics (acceleration, velocity, direction) as key parameters. By transforming the problem from coordinate-based location to motion-based identification, the system achieves accurate location tracking in enclosed spaces where GPS signals are unavailable or inaccurate.
2Productivity
If the system waits for vehicles to park in designated spaces before identification, then camera calibration remains stable, but the throughput and efficiency deteriorate
Solution Approach 1:
The system performs preliminary identification of vehicles while they are still in motion and approaching the parking area, rather than waiting until they are parked. By initiating the identification process early using motion profiles from sensor data and video frames, the system can prepare the identification result in advance, significantly reducing the time loss and improving throughput without requiring vehicles to be stationary for calibration.
3Measurement precision
If frequent camera recalibration is performed to maintain accuracy, then measurement precision improves, but device complexity and operational burden increase
Solution Approach 1:
The system uses feedback from motion profile comparisons to continuously refine location determination without requiring frequent camera recalibration. By comparing predicted motion profiles with actual observed motion, the system can detect and correct drift or inaccuracies in real-time, maintaining measurement precision while avoiding the operational burden of frequent manual recalibration procedures.
Data Source
AI summary
Techniques are disclosed for determining a location of an object based at least in part on a motion of the object. The techniques include generating a motion profile based at least in part on motion data received from a mobile device that is associated with the object. The techniques further include receiving, from a camera at a location, a plurality of images that identifies a candidate motion of a candidate object through at least a portion of the location. The techniques further include generating a candidate motion profile corresponding to the candidate motion of the candidate object based at least in part on the plurality of images. Based at least in part on a score generated by comparing the motion profile with the candidate motion profile, the techniques may determine that the candidate object is the object.