Monocular infrared video three-dimensional reconstruction method based on visual odometer

Abstract

The invention provides a monocular infrared video three-dimensional reconstruction method based on a visual odometer. Firstly, a thermal infrared imager is calibrated; then, a direct method and sparse method visual odometer model is constructed; then, frames are managed, a key frame is generated from a continuous infrared image sequence to be processed, and the key frame is marginalized; point management is conducted on the pixel on the key frame; finally, sliding window optimization is conducted on the key frame, a photometric error of the direct method and sparse method visual odometer model is minimized, the reverse depths of thermal infrared imager pose, internal references and spatial points are solved in an iterative algorithm by a gauss-newton method, and finally, three-dimensional point cloud of a scene is obtained. According to the monocular infrared video three-dimensional reconstruction method based on the visual odometer, the direct method is applied to photometric error minimization, traditional feature point detection and matching are skipped, through direction operation on a grey value of the pixel, all variables which the photometric error to be optimized depend on is calculated directly, and therefore three-dimensional reconstruction of a night vision scene is achieved, the real-time capability of the three-dimensional reconstruction is ensured, and the spaciousness of the scene is enhanced.

Description

technical field [0001] The invention relates to a three-dimensional reconstruction method of monocular infrared video based on the direct method and the sparse method visual odometer, through which the three-dimensional structure reconstruction of the scene in the infrared video can be carried out, so that the image has a sense of space, and the night vision image is significantly enhanced scene awareness. Background technique [0002] Three-dimensional reconstruction is to obtain image information from two-dimensional image information, and obtain three-dimensional information of the image by processing the information, which is an important part of computer vision. There are ideal algorithms for restoring the three-dimensional structure in color images, but for infrared images, because it reflects the temperature distribution of the scene, it has defects such as low signal-to-noise ratio, low contrast, and lack of texture. There are fewer 3D reconstruction algorithms. If...

AI Technical Summary

Problems solved by technology

At present, there is only a method based on machine learning for 3D reconstruction of monocular infrared images, and the acquisition of training sets increases hardware costs.

Images