Static Occupancy Grid Tracking for Camera-Based 3D Object Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing systems face challenges in accurately detecting and tracking unexpected static objects, particularly in autonomous driving and robotics, where camera-based systems struggle to detect static objects compared to light-based sensors, impacting navigation and motion planning.
Innovation Solution
The implementation of a static occupancy tracking system using boundary information, point maps, and machine learning models to determine the probability of occupancy of static objects in a three-dimensional space, employing a Bayesian filter for grid-based tracking and updating probabilities.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If camera-based systems are used for object detection, then the system can operate with optical sensing capabilities, but the detection accuracy of static objects deteriorates compared to light-based sensors
Solution Approach 1:
The patent introduces an intermediary processing system that combines camera-based detection with additional processing techniques including boundary information analysis, point map integration, and machine learning models to compensate for the inherent limitations of camera-based static object detection
Solution Approach 2:
The system employs a composite approach by integrating multiple data sources and processing methods (boundary information, point maps, machine learning models) to enhance the detection capability of camera-based systems for static objects
2Device complexity
If traditional object detection methods are used, then the system structure remains simple, but the ability to detect and track unexpected static objects deteriorates
Solution Approach 1:
The patent segments the detection process into distinct components: boundary information extraction, point map generation, machine learning model application, and probability calculation, allowing each component to be optimized independently while improving overall detection reliability
Solution Approach 2:
The system dynamically updates occupancy probabilities as new data becomes available, allowing the detection system to adapt to changing environments and improve reliability without requiring a completely complex static structure
3Measurement precision
If occupancy probability tracking is implemented, then navigation and motion planning accuracy is improved, but computational requirements increase
Solution Approach 1:
The patent applies partial action by focusing computational resources on tracking occupancy probabilities only in relevant regions of interest rather than calculating probabilities for the entire environment, reducing overall computational energy requirements while maintaining navigation accuracy
Data Source
AI summary
Techniques and systems are provided for determining static occupancy. For example, an apparatus can be configured to determine one or more pixels associated with one or more static objects depicted in one or more images of a three-dimensional space. The apparatus can be configured to obtain a point map including a plurality of map points, the plurality of map points corresponding to a portion of the three-dimensional space. The apparatus can be configured to determine, based on the point map and the one or more pixels associated with the one or more static objects, a probability of occupancy by the one or more static objects in the portion of the three-dimensional space. The apparatus can be configured to combine information across multiple images of the three-dimensional space, and can determine probabilities of occupancy for all cells in a static occupancy grid that is associated with the three-dimensional space.