Blind Object Tracking Using Point Cloud Clusters
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing object tracking systems require continuous monitoring of objects in a physical environment, making it difficult to track objects that move out of view or change location over time without persistent surveillance.
Innovation Solution
A method using point clouds to represent a physical environment, where a handheld electronic device generates and spatially disambiguates point clouds into clusters, allowing for the association of points with cluster identifiers and spatial relationships, enabling blind object tracking by updating point clouds over time to account for object movement and occlusion.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If continuous monitoring is used to track objects, then tracking reliability is improved, but energy consumption and system complexity increase
Solution Approach 1:
The system performs tracking at discrete time periods rather than continuously. Point clouds are captured at specific intervals (first time period, second time period, etc.), and object locations are updated periodically by comparing point cloud data across these time periods, reducing energy consumption while maintaining tracking reliability.
Solution Approach 2:
The system performs preliminary spatial disambiguation and clustering of point cloud data to identify objects and their locations in advance. By pre-processing the point cloud data into clustered representations with spatial relationships, the system establishes a baseline for tracking that enables reliable object location determination without requiring continuous monitoring.
2Reliability
If continuous monitoring is used to track objects, then tracking reliability is improved, but device complexity increases
Solution Approach 1:
The system segments the point cloud data into multiple clusters, where each cluster represents a potential object or region of interest. By dividing the complex point cloud data into manageable clusters with unique identifiers and spatial relationships, the system simplifies tracking while maintaining reliability through organized data structures.
Solution Approach 2:
The system creates simplified representations (copies) of objects through point cloud clustering. Instead of tracking raw point cloud data directly, the system generates clustered point cloud data structures that capture essential object characteristics and spatial relationships, reducing computational complexity while preserving tracking accuracy.
3Measurement precision
If point clouds are updated over time to account for object movement, then tracking accuracy is improved, but data processing complexity increases
Solution Approach 1:
The system uses feedback by comparing point cloud data across multiple time periods. Object locations are determined by analyzing changes in point cloud clusters between the first time period, second time period, and subsequent periods. This feedback mechanism enables accurate tracking of object movement and occlusion while managing processing complexity through systematic comparison protocols.
Solution Approach 2:
The system adds the time dimension to point cloud data by capturing and comparing point clouds at multiple time periods. By incorporating temporal information into the spatial point cloud data structure, the system achieves accurate tracking of moving objects without requiring overly complex processing, as the time dimension provides natural ordering and comparison opportunities.
Data Source
AI summary
In one implementation, a method of blind object tracking is performed at a device including one or more processors and non-transitory memory. The method includes obtaining a first three-dimensional scene model of a physical environment during a first time period including a first plurality of points, wherein each of the first plurality of points is associated with a set of coordinates in a three-dimensional space, wherein a subset of the first plurality of points is associated with a particular cluster identifier. The method includes obtaining a second three-dimensional scene model of the physical environment during a second time period subsequent to the first time period including a second plurality of points, wherein each of the second plurality of points is associated with a set of coordinates the three-dimensional space. The method includes associating a subset of the second plurality of points with the particular cluster identifier, wherein the subset of the second plurality of points includes points with different sets of coordinates in the three-dimensional space than the points of the subset of the first plurality of points.