Point Cloud Motion Detection Using Recursive Occlusion Checks
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing systems struggle to efficiently and timely detect moving objects from point clouds captured by ranging sensors, particularly in dynamic environments, leading to challenges in real-time processing and accurate differentiation between static and dynamic points.
Innovation Solution
A moving object detection system that utilizes depth images to determine occlusion relationships between current and previous points in point clouds, employing spherical or perspective projections to efficiently identify moving objects by checking for occlusions and recursive occlusions, and utilizing odometry data for sensor pose correction.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If occlusion checking is performed between current and previous points to detect moving objects, then detection accuracy is improved, but computational complexity increases
Solution Approach 1:
The patent segments the point cloud data into current points and previous points, and further segments the comparison process into occlusion checking and recursive occlusion checking. This segmentation allows the system to manage computational complexity by breaking down the detection task into manageable parts while maintaining high detection accuracy through systematic comparison of point depths across different time frames.
Solution Approach 2:
The patent performs preliminary action by maintaining a history of previous points and their depth information before current detection. By pre-storing this reference data and establishing the occlusion checking mechanism in advance, the system enables rapid real-time detection without requiring complex computations during the actual detection moment, thus resolving the contradiction between accuracy and computational complexity.
2Reliability
If recursive occlusion checking is performed to improve detection reliability, then false positives are reduced, but processing time increases
Solution Approach 1:
The patent applies local quality by performing recursive occlusion checking selectively rather than uniformly across all points. The system focuses computational resources on points that exhibit occlusion characteristics, applying deeper recursive analysis only where needed to reduce false positives. This localized approach maintains high detection reliability while minimizing unnecessary processing time for points that do not require extensive verification.
3Productivity
If depth images are used to project and compare points, then detection speed is improved, but data storage requirements increase
Solution Approach 1:
The patent extracts only the essential depth information from the point cloud data and stores it in depth images, rather than storing complete point cloud data. By taking out and storing only the critical depth values needed for occlusion checking, the system achieves fast detection speed through efficient depth image projection and comparison, while keeping data storage requirements manageable by eliminating redundant information.
Data Source
AI summary
A moving object detection system and method is provided. The system includes an input module capturing a point cloud comprising measurements of distances to points on one or more objects and a detection module receiving the point cloud captured by the input module and configured to determine whether the objects are moving objects. The determination of moving objects is performed by determining whether currently measured points occlude any previously measured points, and/or whether the currently measured points recursively occlude any previously measured points, and/or whether the currently measured points are recursively occluded by any previously measured points.