Related papers: Focal Surface Attitude Detection for LAMOST
We aim at estimating the fundamental matrix in two views from five correspondences of rotation invariant features obtained by e.g.\ the SIFT detector. The proposed minimal solver first estimates a homography from three correspondences…
Oblique plane microscopy is a method enabling light-sheet fluorescence imaging through a single microscope objective lens by focusing on a tilted plane within the sample. To focus the fluorescence emitted by the oblique plane on a camera,…
Recently, anchor-based methods have achieved great progress in face detection. Once anchor design and anchor matching strategy determined, plenty of positive anchors will be sampled. However, faces with extreme aspect ratio always fail to…
We present a novel solution to the camera pose estimation problem, where rotation and translation of a camera between two views are estimated from matched feature points in the images. The camera pose estimation problem is traditionally…
The off-axis location of the Advanced Camera for Surveys (ACS) is the chief (but not sole) cause of strong geometric distortion in all detectors: the Wide Field Camera (WFC), High Resolution Camera (HRC), and Solar Blind Camera (SBC).…
We propose an accurate and interpretable fine-grained cross-view localization method that estimates the 3 Degrees of Freedom (DoF) pose of a ground-level image by matching its local features with a reference aerial image. Unlike prior…
Lane detection is an important yet challenging task in autonomous driving, which is affected by many factors, e.g., light conditions, occlusions caused by other vehicles, irrelevant markings on the road and the inherent long and thin…
Flat-field reflects the non-uniformity of the photometric response at the focal plane of an instrument, which uses digital image sensors, such as Charge Coupled Device (CCD) and Complementary Metal-Oxide-Semiconductor (CMOS). This…
A novel method nicknamed ELASTIC is proposed for the alignment of multiple-aperture telescopes, in particular segmented telescopes. It only needs the acquisition of two diversity images of an unresolved source, and is based on the…
With the aim of paving the road for future accurate astrometry with MICADO at the European-ELT, we performed an astrometric study using two different but complementary approaches to investigate two critical components that contribute to the…
Camera-to-robot calibration is crucial for vision-based robot control and requires effort to make it accurate. Recent advancements in markerless pose estimation methods have eliminated the need for time-consuming physical setups for…
Extreme head postures pose a common challenge across a spectrum of facial analysis tasks, including face detection, facial landmark detection (FLD), and head pose estimation (HPE). These tasks are interdependent, where accurate FLD relies…
Face alignment is a crucial step in preparing face images for feature extraction in facial analysis tasks. For applications such as face recognition, facial expression recognition, and facial attribute classification, alignment is widely…
The tolerance analysis of freeform surfaces plays a crucial role in the development of advanced imaging systems. However, the intricate relationship between surface error and imaging quality poses significant challenges, necessitating dense…
In computer vision, the estimation of the fundamental matrix is a basic problem that has been extensively studied. The accuracy of the estimation imposes a significant influence on subsequent tasks such as the camera trajectory…
Multi-modal object detection in autonomous driving has achieved great breakthroughs due to the usage of fusing complementary information from different sensors. The calibration in fusion between sensors such as LiDAR and camera was always…
We explain and demonstrate a new method of force- and position-calibration for optical tweezers with back-focal-plane photo detection. The method combines power spectral measurements of thermal motion and the response to a sinusoidal motion…
We present a novel one-shot method for object detection and 6 DoF pose estimation, that does not require training on target objects. At test time, it takes as input a target image and a textured 3D query model. The core idea is to represent…
We study the challenging problem of estimating the relative pose of three calibrated cameras from four point correspondences. We propose novel efficient solutions to this problem that are based on the simple idea of using four…
Precise fiber positioning is crucial to a wide field, multi-fiber spectroscopic survey like LAMOST. Nowadays, most position error measurements are based on CCD photographic and imaging processing techniques. Those methods only work for…