Monocular UAV Positioning with Virtual Floors and Marking Zones
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Unmanned aerial vehicles (UAVs) face challenges in precise positioning in areas with poor satellite signal reception, and existing methods like GNSS and SLAM are inefficient or costly.
Innovation Solution
A positioning system using monocular environmental cameras generates environmental positioning information with varying accuracy levels for virtual floors, divided into work zones, and fuses sensing information to enhance precision, reducing hardware and computing costs.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If GNSS information is used for positioning, then positioning can be achieved, but positioning accuracy deteriorates in areas with poor satellite signal reception
Solution Approach 1:
The patent introduces marking objects as intermediary elements placed at known positions in the environment. These marking objects serve as mediators between the monocular camera and the positioning system, providing reference points that enable accurate positioning without requiring satellite signals. The marking objects with known coordinates allow the system to establish a coordinate transformation relationship, resolving the contradiction by providing a reliable positioning method that works independently of GNSS signal quality.
2Measurement precision
If multiple high-speed cameras are disposed to shoot marks from different angles, then positioning accuracy is improved, but device complexity and hardware cost increase
Solution Approach 1:
The patent extracts the positioning function from complex multi-camera systems and implements it using a single monocular camera combined with marking objects. By taking out the essential positioning capability and separating it from the complex hardware arrangement, the system achieves the same positioning accuracy with significantly reduced hardware complexity. The marking objects carry the positioning information that would otherwise require multiple cameras to capture and process.
Solution Approach 2:
The patent uses marking objects as copies or representations of known position references. Instead of using multiple physical cameras to capture marks from different angles, the system uses marking objects that encode position information, which can be detected by a single camera. This copying approach simplifies the hardware while maintaining the ability to determine precise positions through image processing and coordinate transformation.
3Reliability
If SLAM function is used for positioning, then positioning can be performed without GNSS, but computing resource consumption increases
Solution Approach 1:
The patent applies preliminary action by pre-placing marking objects at known positions in the environment before the positioning operation begins. These pre-positioned marking objects serve as ready-to-use reference points that eliminate the need for real-time complex computations. The system only needs to detect the marking objects in images and apply pre-established coordinate transformations, significantly reducing computing resource consumption compared to real-time SLAM processing.
4Device complexity
If monocular environmental camera is used for positioning, then hardware cost is reduced, but positioning accuracy deteriorates
Solution Approach 1:
The patent applies local quality by placing marking objects at specific known positions throughout the environment. These localized reference points provide high-accuracy positioning information at their locations, while the monocular camera captures images that can be processed to determine positions of these marked points. The local quality of the marking objects compensates for the limitations of monocular vision, enabling accurate positioning without requiring expensive multi-camera hardware.
Data Source
AI summary
A positioning system for providing an environmental positioning information of a field using monocular vision is disclosed. The positioning system is configured to provide an environmental positioning information of a field having a plurality of virtual floors corresponding to different heights, wherein each of the virtual floors has a plurality of marking positions. The positioning system includes a computing device configured to generate an environmental positioning information according to a first environmental image. The environmental positioning information has a positioning accuracy having various levels corresponding to the marking positions of each of the virtual floors. The computing device is further configured to divide each of the virtual floors into a plurality of work zones according to the positioning accuracy corresponding to the making positions.