Related papers: CNN-based local features for navigation near an as…

Small objects are difficult to detect because of their low resolution and small size. The existing small object detection methods mainly focus on data preprocessing or narrowing the differences between large and small objects. Inspired by…

The encoding of the target in object tracking moves from the coarse bounding-box to fine-grained segmentation map recently. Revisiting de facto real-time approaches that are capable of predicting mask during tracking, we observed that they…

The taxonomic classification of asteroids has been mostly based on spectroscopic observations with wavelengths spanning from the VIS to the NIR. VIS-NIR spectra of $\sim$2500 asteroids have been obtained since the 1970s; the SDSS MOC 4 was…

Asteroid modeling efforts in the last decade resulted in a comprehensive dataset of almost 400 convex shape models and their rotation states. This amount already provided a deep insight into physical properties of main-belt asteroids or…

The research about asteroids attracts more and more attention recently, especially focusing on their physical structures, such as the spin axis, the rotation period and the shape. The long distance between Earth observers and asteroids…

In the past decade, hundreds of asteroid shape models have been derived using the lightcurve inversion method. At the same time, a new framework of 3-D shape modeling based on the combined analysis of widely different data sources such as…

The apparent magnitude of elongated small bodies is time-dependent over their rotation phase. Therefore, previously undiscovered aspherical minor planets may experience a shape-driven selection effect in systematic surveys versus their…

In this paper we present an extensive evaluation of visual descriptors for the content-based retrieval of remote sensing (RS) images. The evaluation includes global hand-crafted, local hand-crafted, and Convolutional Neural Network (CNNs)…

Digital co-addition of astronomical images is a common technique for increasing signal-to-noise and image depth. A modification of this simple technique has been applied to the detection of minor bodies in the Solar System: first stationary…

Asteroid mining has been proposed as an approach to complement Earth-based supplies of rare earth metals and supplying resources in space, such as water. However, existing studies on the economic viability of asteroid mining have remained…

On-board estimation of the pose of an uncooperative target spacecraft is an essential task for future on-orbit servicing and close-proximity formation flying missions. However, two issues hinder reliable on-board monocular vision based pose…

Early detection and tracking of ejecta in the vicinity of small solar system bodies is crucial to guarantee spacecraft safety and support scientific observation. During the visit of active asteroid Bennu, the OSIRIS-REx spacecraft relied on…

Conventional training of a deep CNN based object detector demands a large number of bounding box annotations, which may be unavailable for rare categories. In this work we develop a few-shot object detector that can learn to detect novel…

Beneficial from Fully Convolutional Neural Networks (FCNs), saliency detection methods have achieved promising results. However, it is still challenging to learn effective features for detecting salient objects in complicated scenarios, in…

For the ore particle size detection, obtaining a sizable amount of high-quality ore labeled data is time-consuming and expensive. General object detection methods often suffer from severe over-fitting with scarce labeled data. Despite their…

This study examines various feature extraction techniques in computer vision, the primary focus of which is on Vision Transformers (ViTs) and other approaches such as Generative Adversarial Networks (GANs), deep feature models, traditional…

Finding obstacle-free paths in unknown environments is a big navigation issue for visually impaired people and autonomous robots. Previous works focus on obstacle avoidance, however they do not have a general view of the environment they…

The visual detection and tracking of surface terrain is required for spacecraft to safely land on or navigate within close proximity to celestial objects. Current approaches rely on template matching with pre-gathered patch-based features,…

Pedestrian detection methods have been significantly improved with the development of deep convolutional neural networks. Nevertheless, robustly detecting pedestrians with a large variant on sizes and with occlusions remains a challenging…

Accurate real-time pose estimation of spacecraft or object in space is a key capability necessary for on-orbit spacecraft servicing and assembly tasks. Pose estimation of objects in space is more challenging than for objects on Earth due to…