Spacecraft pose estimation using computer vision has garnered increasing attention in research areas such as automation system theory, control theory, sensors and instruments, robot technology, and automation software. Confronted with the extreme environment of space, existing spacecraft pose estimation methods are predominantly multi-stage networks with complex operations. In this study, we propose an approach for spacecraft homography pose estimation with a single-stage deep convolutional neural network for the first time. We formulated a homomorphic geometric constraint equation for spacecraft with planar features. Additionally, we employed a single-stage 2D keypoint regression network to obtain homography 2D keypoint coordinates for spacecraft. After decomposition to obtain the rough spacecraft pose based on the homography matrix constructed according to the geometric constraint equation, a loss function based on pixel errors was employed to refine the spacecraft pose. We conducted extensive experiments using widely used spacecraft pose estimation datasets and compared our method with state-of-the-art techniques in the field to demonstrate its effectiveness.
High-accuracy rotary-angle measurement is critical for precise positioning and control of robots, machine arms, and machine tools in industry. Image-based measurement is a very promising technology for angle positioning owing to its simple system, low cost, and good robustness to environments. Image correlation, such as the zero-mean normalized cross correlation (ZNCC) method, can obtain high accuracy image-positioning results, but their efficiency is too low to directly use in industries. This paper proposes to measure the absolute rotary angle using a parameterized ZNCC (PZNCC) image correlation method. The PZNCC expresses the ZNCC coefficient by the image-shift parameters explicitly, so that the precise match point corresponding to the global ZNCC maximum can be efficiently obtained and no image-resampling process is required. As a result, PZNCC is approximately 5 times faster than the classic inverse compositional Gauss–Newton algorithm. Experiments show that rotary angle measurement based on PZNCC can obtain absolute angle positions with an accuracy of 1.16 arcsec (RMSE).