This technology is a structural feature-based visual odometry method that estimates a camera's 6-DOF trajectory in orthogonal environments by combining line information from color images with plane information from depth images. It constructs a Manhattan frame by extracting vanishing directions from line information and surface normal vectors from plane information.
Existing image-based odometry techniques suffer from cumulative errors when estimating rotational movement, and methods relying solely on plane information often fail or produce inaccurate results in environments where planar surfaces are insufficient.
By utilizing line and plane information in a complementary manner, this technology recognizes spatial orientation and estimates rotational movement first to eliminate errors. It then employs the Levenberg-Marquardt algorithm to minimize feature point residuals based on depth availability, enabling precise 6-DOF trajectory estimation without cumulative drift. Applicable to indoor autonomous robots, AR/VR devices, and drone navigation, it provides an economical solution for achieving precise localization using only a camera, without the need for expensive additional sensors.
This invention was developed with support from the Ministry of Trade, Industry and Energy for the development of an integrated multi-robot control system for complex disaster response.
N/A
