Panorama Point Cloud Building System for Obstacle Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current driver and mobile assistance systems rely on ultra-sound radar, infrared radar, and two-dimensional image sensors, which have limitations such as small working range, low detection angles, and difficulty in precise three-dimensional measurements within 0.5-5 meters, especially in adverse weather conditions, leading to potential misjudgment of obstacles and inadequate safety assurance.
Innovation Solution
A building method and system for panorama point cloud data using point cloud registration and real-time capturing, involving three-dimensional capturing devices, a feature processing unit, and a coordinate processing unit to obtain a coordinate transformation matrix, combining real-time point cloud sets to achieve high-precision panorama point cloud data suitable for driver/mobile assistance systems.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If ultra-sound radar is used, then the system can detect obstacles, but the working range is small and multiple sensors are required to eliminate blind spots
Solution Approach 1:
The patent combines multiple three-dimensional capturing devices (ToF sensors) into a unified panorama point cloud system that captures data from multiple directions simultaneously. By merging the data from multiple sensors through point cloud registration and coordinate transformation, the system achieves extended working range and eliminates blind spots while maintaining reliable obstacle detection.
2Reliability
If infrared radar sensors are used, then the system can detect obstacles, but the detection angle is low and obstacles may be misjudged in rain or fog
Solution Approach 1:
The patent replaces infrared radar sensors with three-dimensional capturing devices (ToF sensors) that use time-of-flight measurement principles. This substitution provides higher detection angles and better performance in adverse weather conditions like rain and fog, while maintaining obstacle detection reliability through precise three-dimensional point cloud data acquisition.
3Loss of information
If two-dimensional image sensors are used, then the system can capture images, but distance detection is inaccurate and obstacles may be misjudged at night, in rain or fog
Solution Approach 1:
The patent transitions from two-dimensional image sensors to three-dimensional capturing devices that acquire depth information through time-of-flight measurement. This dimensional enhancement provides accurate distance detection and three-dimensional spatial positioning, enabling reliable obstacle detection and distance measurement even in adverse weather conditions and at night.
4Ease of operation
If conventional sensors are used, then the system can function, but precise three-dimensional measurement within 0.5-5 meters cannot be achieved
Solution Approach 1:
The patent employs three-dimensional capturing devices with time-of-flight measurement capability that are specifically optimized for short-range precise measurement. By changing the measurement parameter approach from conventional sensors to ToF-based depth sensing, the system achieves high-precision three-dimensional measurement within the 0.5-5 meter range while maintaining full system functionality.
Data Source
AI summary
A building method and a building system for panorama point cloud data are provided. The building method for panorama point cloud data includes the following steps. At least one reference geometric object located at an overlap region of two adjacent three-dimensional capturing devices is captured by the two adjacent three-dimensional capturing devices to obtain two reference point cloud sets. A reference feature plane is obtained from each of the reference point cloud sets. A coordinate transformation matrix is obtained according to the reference feature planes. A plurality of real-time point cloud sets are obtained by the three-dimensional capturing devices. The coordinate transformation of the real-time point cloud sets are performed according to the coordinate transformation matrix, and the real-time point cloud sets are combined to obtain the panorama point cloud data.