Lidar Object Tracking Using Grid Maps for Static Object Recognition
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Lidar systems face challenges in accurately and quickly determining static objects, such as bushes, trees, and damaged guardrails, due to inaccurate shape information and misrecognition, leading to performance degradation.
Innovation Solution
An object tracking apparatus and method using a lidar sensor that generates and analyzes grid maps to determine the likelihood of an object being stationary or moving, employing a scoring system and weight calculations to differentiate between static and dynamic objects, and classifying shapes into types for accurate identification.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Speed
If lidar systems use shape information to determine static objects, then determination speed may be improved, but accuracy deteriorates due to various types of static objects having similar shapes
Solution Approach 1:
The patent segments the determination process into multiple independent features: shape information, speed information, and classification information. Each feature is evaluated separately and combined to make the final determination, allowing the system to leverage shape for speed while using other features to maintain accuracy.
Solution Approach 2:
The patent changes the parameters used for determination from relying solely on shape to incorporating multiple parameters including speed thresholds and classification categories. This multi-parameter approach allows the system to accurately distinguish between static and dynamic objects even when shapes are similar.
2Measurement precision
If lidar systems combine multiple characteristic information to determine static objects, then accuracy is improved, but determination speed deteriorates
Solution Approach 1:
The patent implements a dynamic determination process that adapts to different object types and scenarios. The system dynamically selects and weights different features based on the situation, allowing for both speed and accuracy by adjusting the determination strategy in real-time.
Solution Approach 2:
The patent replaces complex mechanical analysis of object shapes with a more efficient information-processing approach using multiple sensors and feature extraction. This substitution allows for faster processing while maintaining or improving accuracy through the use of classification and speed data.
3Ease of operation
If lidar systems rely on speed information to determine dynamic objects, then determination simplicity is improved, but reliability deteriorates when box variable is large
Solution Approach 1:
The patent creates a composite determination approach that combines multiple information sources (classification, shape, speed) into a unified decision-making framework. This composite method maintains the simplicity of speed-based determination while adding layers of verification to ensure reliability even when speed measurements are uncertain.
Data Source
AI summary
There is provided an object tracking apparatus comprising a light detection and ranging (lidar) sensor, one or more processors, and memory storing instructions. The object tracking apparatus receives lidar data from the lidar sensor and track an object using the received lidar data, determine, based on a predetermined criterion and information about the object, at least one of: a first score indicating a likelihood that the object is moving, or a second score indicating a likelihood that the object is stationary, output a comparison result value of a comparison between the first score and the second score, and determine, based on the comparison result value, whether the object is moving or stationary.