This paper introduces a novel framework which combines a Convolutional Neural Network (CNN) for feature detection with a Covariant Efficient Procrustes Perspective-n-Points (CEPPnP) solver and an Extended Kalman Filter (EKF) to enable robust monocular pose estimation for close-proximity operations around an uncooperative spacecraft. The relative pose estimation of an inactive spacecraft by an active servicer spacecraft is a critical task in the design of current and planned space missions, due to its relevance for close-proximity operations, such as In-Orbit Servicing and Active Debris Removal. The main contribution of this work stands in deriving statistical information from the Image Processing step, by associating a covariance matrix to the heatmaps returned by the CNN for each detected feature. This information is included in the CEPPnP to improve the accuracy of the pose estimation step during filter initialization. The derived measurement covariance matrix is used in a tightly-coupled EKF to allow an enhanced representation of the measurements error from the feature detection step. This increases the filter robustness in case of inaccurate CNN detections. The proposed method is capable of returning reliable estimates of the relative pose as well as of the relative translational and rotational velocities, under adverse illumination conditions and partial occultation of the target. Synthetic 2D images of the European Space Agency's Envisat spacecraft are used to generate datasets for training, validation and testing of the CNN. Likewise, the images are used to recreate representative close-proximity scenarios for the validation of the proposed method.

Automated industrial welding processes depend on a large number of factors interacting with high complexity resulting in some sporadic and random variability of the manufactured product that may affect its quality. It is therefore very important to have an accurate and stable quality control. In this work, a deep learning (DL) model is developed for semantic segmentation of weld seams using 3D stereo images of the seam. The objective is to correctly identify the shape and volume of the weld seam as this is the basic problem of quality control. To achieve this, a model called UNet $${\mathcal {L}}$$L ++ has been developed, based on the UNet and UNet++ architectures, with a more complex topology and a simple encoder to achieve a good adaptation to the specific characteristics of the 3D data. The proposed model receives as input a voxelized 3D point cloud of the freshly welded part where noise is abundantly visible, and generates as output another 3D voxel grid where each voxel is semantically labeled. The experiments performed with parts built by a real weld line show a correct identification of the weld seams, obtaining values between 0.935 and 0.941 for the Dice Similarity Coefficient (DSC). As far as the authors are aware, this is the first 3D analysis proposal capable of generating shape and volume information of weld seams with almost perfect noise filtering.

Galaxy edges or truncations are low-surface-brightness (LSB) features located in the galaxy outskirts that delimit the distance up to where the gas density enables efficient star formation. As such, they could be interpreted as a non-arbitrary means to determine the galaxy size and this is also reinforced by the smaller scatter in the galaxy mass-size relation when comparing them with other size proxies. However, there are several problems attached to this novel metric, namely, the access to deep imaging and the need to contrast the surface brightness, color, and mass profiles to derive the edge position. While the first hurdle is already overcome by new ultra-deep galaxy observations, we hereby propose the use of machine learning (ML) algorithms to determine the position of these features for very large datasets. We compare the semantic segmentation by our deep learning (DL) models with the results obtained by humans for HST observations of a sample of 1052 massive (M_stellar> 10¹⁰M_⊙) galaxies atz <1. In addition, the concept of astronomic augmentations is introduced to endow the inputs of the networks with a physical meaning. Our findings suggest that similar performances than humans could be routinely achieved, although in the majority of cases, the best results are obtained by combining (with a pixel-by-pixel democratic vote) the output of several neural networks using ensemble learning. Additionally, we find that using edge-aware loss functions allows for the networks to focus their optimization on the galaxy boundaries and, therefore, to provide estimates that are much more sensitive to the presence of neighboring bodies that may affect the shape of the truncation. The experiments reveal a great similarity between the semantic segmentation performed by the AI compared to the human model. For the best model, an average dice of 0.8969 is achieved, while an average dice of 0.9104 is reached by the best ensemble, where the dice coefficient represents the harmonic mean between the precision and the recall. This methodology will be profusely used in future datasets, such as that ofEuclid,to derive scaling relations that are expected to closely follow the galaxy mass assembly. We also offer to the community our DL algorithms in the author's github repository.

Context. Stellar disk truncations, also referred to as galaxy edges, are key indicators of galactic size, determined by the radial location of the gas density threshold for star formation. This threshold essentially marks the boundary of the luminous matter in a galaxy. Accurately measuring galaxy sizes for millions of galaxies is essential for understanding the physical processes driving galaxy evolution over cosmic time. Aims. We aim to explore the potential of the Segment Anything Model (SAM), a foundation model designed for image segmentation, to automatically identify disk truncations in galaxy images. With the Euclid Wide Survey poised to deliver vast datasets, our goal is to assess SAM’s capability to measure galaxy sizes in a fully automated manner. Methods. SAM was applied to a labeled dataset of 1,047 disk-like galaxies with M_* > 1010 M_⊙ at redshifts up to z ~ 1, sourced from the Hubble Space Telescope (HST) CANDELS fields. We “euclidized” the HST galaxy images by creating composite RGB images, using the F160W (H-band), F125W (J-band), and F814W + F606W (I-band + V -band) HST filters, respectively. Using these processed images as input for SAM, we retrieved various truncation masks for each galaxy image under different configurations of the input data. Results. We find excellent agreement between the galaxy sizes identified by SAM and those measured manually (i.e., by using the radial positions of the stellar disk edges in galaxy light profiles), with an average deviation of approximately 3%. This error reduces to about 1% when excluding problematic cases. Conclusions. Our results highlight the strong potential of SAM for detecting disk truncations and measuring galaxy sizes across large datasets in an automated way. SAM performs well without requiring extensive image preprocessing, labeled training datasets for truncations (used only for validation), fine-tuning, or additional domain-specific adaptations such as transfer learning.

Galaxy edges or truncations are low-surface-brightness (LSB) features located in the galaxy outskirts that delimit the distance up to where the gas density enables efficient star formation. As such, they could be interpreted as a non-arbitrary means to determine the galaxy size and this is also reinforced by the smaller scatter in the galaxy mass-size relation when comparing them with other size proxies. However, there are several problems attached to this novel metric, namely, the access to deep imaging and the need to contrast the surface brightness, color, and mass profiles to derive the edge position. While the first hurdle is already overcome by new ultra-deep galaxy observations, we hereby propose the use of machine learning (ML) algorithms to determine the position of these features for very large datasets. We compare the semantic segmentation by our deep learning (DL) models with the results obtained by humans for HST observations of a sample of 1052 massive (M$_{\rm stellar}$ > 10$^{10}$ M$_{\odot}$) galaxies at $z < 1$. In addition, the concept of astronomic augmentations is introduced to endow the inputs of the networks with a physical meaning. Our findings suggest that similar performances than humans could be routinely achieved. The best results are obtained by combining the output of several neural networks using ensemble learning. Additionally, we find that using edge-aware loss functions allows for the networks to focus their optimization on the galaxy boundaries. The experiments reveal a great similarity between the segmentation performed by the AI compared to the human model. For the best model, an average dice of 0.8969 is achieved, while an average dice of 0.9104 is reached by the best ensemble. This methodology will be profusely used in future datasets, such as that of Euclid, to derive scaling relations that are expected to closely follow the galaxy mass assembly.

Current functional safety mechanisms mainly control the access points and perimeters of manufacturing cells, without guaranteeing the integrity of their inner components or the absence of unauthorized humans or objects. In this work, we present a novel deep learning (DL)–based safety system that enhances the safety circuit designed according to functional safety principles, detecting with great reliability the presence of persons within the cell and, with high precision, anomalous elements of any kind. Our approach follows a two-stage DL methodology that combines contrastive learning with Bayesian clustering. First, a supervised contrastive scheme learns the characteristics of safe scenarios and distinguishes them from unsafe ones caused by workers remaining inside the cell. Then, a Bayesian mixture models the latent space of safe scenarios, quantifying deviations and enabling the detection of previously unseen anomalous objects without any specific fine-tuning. To further improve robustness, we introduce an ensemble-based hybrid latent space methodology that maximizes performance regardless of the underlying siamese encoders’ characteristics. Experiments were conducted on a real dataset captured in a belt-picking cell in production. The proposed system achieves 100% accuracy in distinguishing safe scenarios from those with the presence of workers, even in partially occluded cases, and an average area-under-curve of 0.9984 across seven types of anomalous objects commonly found in manufacturing environments. Finally, for interpretability analysis, we design a patch-based feature ablation framework that demonstrates the model’s reliability under uncertainty and the abscence of learning biases. The proposed techniques enables the deployment of an innovative, high-performance safety system that, to our knowledge, doesn´t exist in industry.