Stereo Camera Person Detection With 2D-Guided 3D Localization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing sensor systems struggle with efficient and fast detection of people in three-dimensional space, particularly in industrial settings where computing power is limited and processing speed is crucial, especially distinguishing between people and other objects.
Innovation Solution
A sensor system utilizing a stereo camera to generate 3D data and 2D data, employing artificial intelligence-based person detection methods on 2D data to determine 2D position data, which is then used to assign and derive 3D position data for detected persons, optimizing computing power usage and enabling real-time detection.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If person detection is performed on 3D data, then detection accuracy in three-dimensional space is improved, but computing power consumption increases and processing speed decreases
Solution Approach 1:
The detection process is segmented into two stages: first performing person detection on 2D data to identify potential persons and obtain 2D position data, then using this information to guide 3D data processing only for relevant regions. This segmentation allows the system to leverage the speed advantage of 2D processing while maintaining 3D detection accuracy where needed.
Solution Approach 2:
2D position data serves as an intermediary that bridges between 2D and 3D processing. The 2D detection results are used to select and process corresponding 3D data points, enabling the system to achieve accurate 3D person detection without directly processing all 3D data, thus reducing computational burden while maintaining precision.
2Measurement precision
If person detection is performed on 3D data, then detection accuracy in three-dimensional space is improved, but computing power consumption increases
Solution Approach 1:
The detection process is segmented into two stages: first performing person detection on 2D data to identify potential persons and obtain 2D position data, then using this information to guide 3D data processing only for relevant regions. This segmentation allows the system to leverage the speed advantage of 2D processing while maintaining 3D detection accuracy where needed.
Solution Approach 2:
2D position data serves as an intermediary that bridges between 2D and 3D processing. The 2D detection results are used to select and process corresponding 3D data points, enabling the system to achieve accurate 3D person detection without directly processing all 3D data, thus reducing computational burden while maintaining precision.
3Reliability
If full 3D data processing is used for person detection, then detection reliability is improved, but device complexity increases
Solution Approach 1:
The sensor system generates both 2D and 3D data using the same sensor array, making the system multi-functional. The 2D data is used for initial person detection while 3D data provides depth information for accurate spatial localization. This multi-functionality allows the system to achieve reliable person detection with reduced complexity by leveraging the strengths of both data types.
Solution Approach 2:
2D position data serves as an intermediary that bridges between 2D and 3D processing. The 2D detection results are used to select and process corresponding 3D data points, enabling the system to achieve accurate 3D person detection without directly processing all 3D data, thus reducing computational burden while maintaining precision.
Data Source
Figure 1~2
Figure 3
AI summary
The invention relates to a sensor system for monitoring a spatial area outdoors or in an industrial plant, for example for use on a manned vehicle or an autonomously driving industrial truck, comprising a sensor arrangement, wherein the sensor system is configured to generate 3D data of the spatial area and also to generate 2D data of the spatial area. The sensor system includes a computing unit configured to execute a person detection method on the 2D data of the spatial area in order to detect persons in the spatial area, whereby 2D position data is determined for a detected person, wherein the computing unit is further configured to assign 3D data belonging to the detected person based on the 2D position data for the detected person, and wherein the computing unit is further configured to determine 3D position data for the detected person from the 3D data belonging to the detected person.