Relative positioning technology of static target based on visual-inertial fusion

In this paper, the position of the target in the image is obtained by template matching, and then the feature points are tracked and extracted from the target image and the source image, and the initial value of the target depth is obtained by visual measurement. Then solve the nonlinear least squares problem based on visual constraints and inertia constraints to obtain the optimized target depth. Experiments show that the error of depth estimation is no more than 10% of the target distance.