3D Bitmap Object Tracking for Autonomous Vehicles
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current computer systems for object tracking require significant processing power, making them unsuitable for real-time performance in applications like autonomous vehicle navigation, which necessitates efficient data aggregation and analysis from multiple sensors.
Innovation Solution
A system and method that convert sensor data into three-dimensional bitmap representations, allowing for efficient object tracking by identifying intensity peaks corresponding to object locations and determining longitudinal velocity using radar sensors, thereby updating the environmental state in real-time.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional computer systems are used for object tracking with multiple sensors, then object tracking accuracy is improved, but processing power requirements increase significantly
Solution Approach 1:
The patent replaces traditional CPU-based processing with GPU-based parallel processing. The graphics processing unit is leveraged to perform pixel-level operations on three-dimensional bitmaps simultaneously, substituting sequential mechanical processing with parallel graphical processing. This enables real-time object tracking by distributing computational load across thousands of GPU cores, dramatically reducing processing time while maintaining tracking accuracy.
Solution Approach 2:
The patent transforms sensor data into three-dimensional bitmaps where the third dimension represents velocity space. This dimensional transformation allows the system to represent both spatial position and velocity information in a unified data structure that can be processed efficiently by GPU pixel operations, enabling simultaneous tracking of multiple objects with different velocities.
2Loss of time
If real-time processing is implemented for autonomous vehicle navigation, then response time is improved, but processing complexity increases
Solution Approach 1:
The patent replaces complex sequential processing algorithms with parallel GPU-based pixel operations. By formulating object tracking as a bitmap manipulation problem, the system leverages the GPU's inherent parallel architecture to perform simultaneous computations across all pixels, dramatically reducing response time while simplifying the control logic.
Solution Approach 2:
The patent creates three-dimensional bitmap representations of the environmental state that can be efficiently copied and manipulated. These bitmaps serve as intermediate data structures that simplify complex sensor fusion operations, allowing the system to update environmental models by painting new sensor data into existing bitmap structures rather than performing complex calculations from scratch.
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 enables accurate and efficient object tracking and velocity determination, suitable for real-time applications like autonomous vehicle navigation, by leveraging graphics processing units for faster data processing and blending sensor data asynchronously.
Implementation Method 1
determining longitudinal velocity of an object located at the intensity peak using the radar sensor
Data Source
AI summary
Embodiments of a system and method for tracking objects are described herein. Aspects of this disclosure efficiently update object “belief” data by creating a bitmap representation of object locations and velocities. The bitmap provides a three-dimensional representation of the object as viewed by one or more sensors. The bitmap representations are blended with sensor data over time to determine a current object belief state which can accurately account for asynchronous sensor data. Peaks in the belief data, which may be represented by pixels with an intensity value above a threshold value, are identified as likely objects. Additional sensor data is used to detect longitudinal velocities located at one or more of the peaks.