Heterogeneous image pose estimation and registration method, device and medium based on neural network
A neural network and pose estimation technology, applied in the field of image processing, can solve the problem of difficult to achieve pose estimation and registration of heterogeneous images, achieve good interpretability and generalization ability, short time, high accuracy and real-time effects
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0028] The present invention will be further elaborated and described below with reference to the accompanying drawings and specific embodiments. The technical features of the various embodiments of the present invention can be combined correspondingly on the premise that there is no conflict with each other.
[0029] Heterogeneous sensors are limited by the characteristics of the sensor itself, and the two images obtained by it are heterogeneous images with differences in angle, scale, and viewing angle. Moreover, the sensor is also subject to different forms of interference such as lighting, shadows, and occlusions when acquiring graphics, and these interferences can make pose estimation extremely difficult. For example, O 1 was acquired in the early morning by the drone's bird's-eye camera, while O 2 It is a local elevation map constructed by a ground robot using lidar. These two types of images are heterogeneous images and cannot be directly matched. To address this pro...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


