Feature Detection Method Research Articles

An improved YOLOv5 method for clam seedlings biological feature detection under the microscope

In order to monitor the early growth status of clam seedlings and meet the demands of precision seedling cultivation in a factory setting, this study improves the YOLOv5s model and proposes a high-precision and lightweight method for detecting biological features of clam seedlings. Firstly, dataset of clam seedlings under the microscope was constructed. Secondly, we established a clam seedling detection model based on four different attention mechanisms and analyzed the differences in the features focused on by different attention mechanisms in clam seedling detection. The accuracy of the anchors was optimized using the K-means++ algorithm, and the Soft-NMS method was employed to address the issue of missed detections caused by dense stacking of clam seedlings. The proposed approach has the optimal comprehensive performance by comparing various lightweight networks. The results show that the AP-health, AP-death and mAP of this approach are 98.15%, 93.87% and 96.01%, which can meet the standard for high precision. With a transmission speed of 86 FPS, an average response time of 11.54 ms, and a model size of 27.59 MB, the approach satisfies the requirements for efficiency and portability. Finally, a biological feature detection software of clam seedlings was developed, which can automatically calculate phenotypic information such as the number of clam seedlings, survival rate, and average size. This paper provides a basis for real-time and accurate assessment of clam seedlings biological features while offering technical support for the automation and intelligence of clam seedlings production in factories.

Enhancing Feature Detection and Matching in Low-Pixel-Resolution Hyperspectral Images Using 3D Convolution-Based Siamese Networks.

Today, hyperspectral imaging plays an integral part in the remote sensing and precision agriculture field. Identifying the matching key points between hyperspectral images is an important step in tasks such as image registration, localization, object recognition, and object tracking. Low-pixel resolution hyperspectral imaging is a recent introduction to the field, bringing benefits such as lower cost and form factor compared to traditional systems. However, the use of limited pixel resolution challenges even state-of-the-art feature detection and matching methods, leading to difficulties in generating robust feature matches for images with repeated textures, low textures, low sharpness, and low contrast. Moreover, the use of narrower optics in these cameras adds to the challenges during the feature-matching stage, particularly for images captured during low-altitude flight missions. In order to enhance the robustness of feature detection and matching in low pixel resolution images, in this study we propose a novel approach utilizing 3D Convolution-based Siamese networks. Compared to state-of-the-art methods, this approach takes advantage of all the spectral information available in hyperspectral imaging in order to filter out incorrect matches and produce a robust set of matches. The proposed method initially generates feature matches through a combination of Phase Stretch Transformation-based edge detection and SIFT features. Subsequently, a 3D Convolution-based Siamese network is utilized to filter out inaccurate matches, producing a highly accurate set of feature matches. Evaluation of the proposed method demonstrates its superiority over state-of-the-art approaches in cases where they fail to produce feature matches. Additionally, it competes effectively with the other evaluated methods when generating feature matches in low-pixel resolution hyperspectral images. This research contributes to the advancement of low pixel resolution hyperspectral imaging techniques, and we believe it can specifically aid in mosaic generation of low pixel resolution hyperspectral images.

Dam UAV Image Stitching Technology Studies Based on Weak Texture

Extraction of image feature point pairs is an important step in the image alignment process. In this paper, we propose a grid-based adaptive threshold feature detection method for weakly textured images using a single threshold extraction algorithm that cannot propose uniformly distributed feature points. Finally, the designed experiments show that the feature points extracted by this method have a lower dispersion than the traditional KAZE algorithm by 70% and a higher alignment accuracy than the traditional KAZE algorithm by 10%.

A Deep Recurrent Learning-Based Region-Focused Feature Detection for Enhanced Target Detection in Multi-Object Media.

Target detection in high-contrast, multi-object images and movies is challenging. This difficulty results from different areas and objects/people having varying pixel distributions, contrast, and intensity properties. This work introduces a new region-focused feature detection (RFD) method to tackle this problem and improve target detection accuracy. The RFD method divides the input image into several smaller ones so that as much of the image as possible is processed. Each of these zones has its own contrast and intensity attributes computed. Deep recurrent learning is then used to iteratively extract these features using a similarity measure from training inputs corresponding to various regions. The target can be located by combining features from many locations that overlap. The recognized target is compared to the inputs used during training, with the help of contrast and intensity attributes, to increase accuracy. The feature distribution across regions is also used for repeated training of the learning paradigm. This method efficiently lowers false rates during region selection and pattern matching with numerous extraction instances. Therefore, the suggested method provides greater accuracy by singling out distinct regions and filtering out misleading rate-generating features. The accuracy, similarity index, false rate, extraction ratio, processing time, and others are used to assess the effectiveness of the proposed approach. The proposed RFD improves the similarity index by 10.69%, extraction ratio by 9.04%, and precision by 13.27%. The false rate and processing time are reduced by 7.78% and 9.19%, respectively.

Real-time and robust feature detection of continuous marker pattern for dense 3-D deformation measurement

Visuotactile sensing technology has received much attention in recent years. This article proposes a feature detection method applicable to visuotactile sensors based on continuous marker patterns (CMP) to measure 3-d deformation. First, we construct the feature model of checkerboard-like corners under contact deformation, and design a novel double-layer circular sampler. Then, we propose the judging criteria and response function of corner features by analysing sampling signals’ amplitude-frequency characteristics and circular cross-correlation behavior. The proposed feature detection algorithm fully considers the boundary characteristics retained by the corners with geometric distortion, thus enabling reliable detection at a low calculation cost. The experimental results show that the proposed method has significant advantages in terms of real-time and robustness. Finally, we have achieved the high-density 3-d contact deformation visualization based on this detection method. This technique is able to clearly record the process of contact deformation, thus enabling inverse sensing of dynamic contact processes.

Alternately denoising and reconstructing unoriented point sets

We propose a new strategy to bridge point cloud denoising and surface reconstruction by alternately updating the denoised point clouds and the reconstructed surfaces. In Poisson surface reconstruction, the implicit function is generated by a set of smooth basis functions centered at the octnodes. When the octree depth is properly selected, the reconstructed surface is a good smooth approximation of the noisy point set. Our method projects the noisy points onto the surface and alternately reconstructs and projects the point set. We use the iterative Poisson surface reconstruction (iPSR) to support unoriented surface reconstruction. Our method iteratively performs iPSR and acts as an outer loop of iPSR. Considering that the octree depth significantly affects the reconstruction results, we propose an adaptive depth selection strategy to ensure an appropriate depth choice. To manage the oversmoothing phenomenon near the sharp features, we propose a λ-projection method, which means to project the noisy points onto the surface with an individual control coefficient λi for each point. The coefficients are determined through a Voronoi-based feature detection method. Experimental results show that our method achieves high performance in point cloud denoising and unoriented surface reconstruction within different noise scales, and exhibits well-rounded performance in various types of inputs. The source code is available at https://github.com/Submanifold/AlterUpdate.

Contour Information-Guided Multi-Scale Feature Detection Method for Visible-Infrared Pedestrian Detection.

Infrared pedestrian target detection is affected by factors such as the low resolution and contrast of infrared pedestrian images, as well as the complexity of the background and the presence of multiple targets occluding each other, resulting in indistinct target features. To address these issues, this paper proposes a method to enhance the accuracy of pedestrian target detection by employing contour information to guide multi-scale feature detection. This involves analyzing the shapes and edges of the targets in infrared images at different scales to more accurately identify and differentiate them from the background and other targets. First, we propose a preprocessing method to suppress background interference and extract color information from visible images. Second, we propose an information fusion residual block combining a U-shaped structure and residual connection to form a feature extraction network. Then, we propose an attention mechanism based on a contour information-guided approach to guide the network to extract the depth features of pedestrian targets. Finally, we use the clustering method of mIoU to generate anchor frame sizes applicable to the KAIST pedestrian dataset and propose a hybrid loss function to enhance the network's adaptability to pedestrian targets. The extensive experimental results show that the method proposed in this paper outperforms other comparative algorithms in pedestrian detection, proving its superiority.

Image-Processing-Based Subway Tunnel Crack Detection System.

With the increase in urban rail transit construction, instances of tunnel disease are on the rise, and cracks have become the focus of tunnel maintenance and management. Therefore, it is essential to carry out crack detection in a timely and efficient manner to not only prolong the service life of the tunnel but also reduce the incidence of accidents. In this paper, the design and structure of a tunnel crack detection system are analyzed. On this basis, this paper proposes a new method for crack identification and feature detection using image processing technology. This method fully considers the characteristics of tunnel images and the combination of these characteristics with deep learning, while a deep convolutional network (Single-Shot MultiBox Detector (SSD)) is proposed based on deep learning for object detection in complex images. The experimental results show that the test set accuracy and training set accuracy of the support vector machine (SVM) in the classification comparison test are up to 88% and 87.8%, respectively; while the test accuracy of Alexnet's deep convolutional neural network-based classification and identification is up to 96.7%, and the training set accuracy is up to 97.5%. It can be seen that this deep convolutional network recognition algorithm based on deep learning and image processing is better and more suitable for the detection of cracks in subway tunnels.

Not just select samples, but exploration[formula omitted] Genetic programming aided remote sensing target detection under deep learning

The data of target detection in remote sensing images are diverse, and the detection results of some categories with a small number of samples are poor. In order to solve this problem, most of the existing methods focus on the category with a small number of samples through data augmentation, but this will bring huge loss of original information, resulting in the decline of the effectiveness of some categories when improving the effectiveness. Additionally, since remote sensing image targets are small, numerous and densely distributed, the mixing degree of target and background is high, making them hardly distinguished. Therefore, a loss-based sample selection mechanism is proposed to enhance the category samples with low proportion. In the training process, we select between the original samples and enhanced samples through loss feedback, so as to retain the original sample information as much as possible and improve the detection performance. On this basis, an auxiliary feature detection module is proposed. First, the module detects the highly mixed area between the object to be detected and the background, and uses a series of image enhancement operations to build a genetic programming (GP) tree to separate the object from the background as much as possible, so that the detector can better extract and detect target features. Compared with other latest related algorithms, the loss-based sample selection mechanism and evolutionary auxiliary feature detection method proposed in this paper can improve the detection performance of low proportion categories through the sample selection mechanism, and improve the robustness to background clutter interference through evolutionary auxiliary feature detection. The proposed approach effectively improves the detection performance and performs well in remote sensing target detection.

GeoGlue: feature matching with self-supervised geometric priors for high-resolution UAV images

ABSTRACT We present GeoGlue, a novel method using high-resolution UAV imagery for accurate feature matching, which is normally challenging due to the complicated scenes. Current feature detection methods are performed without guidance of geometric priors (e.g., geometric lines), lacking enough attention given to salient geometric features which are indispensable for accurate matching due to their stable existence across views. In this work, geometric lines are firstly detected by a CNN-based geometry detector (GD) which is pre-trained in a self-supervised manner through automatically generated images. Then, geometric lines are naturally vectorized based on GD and thus non-significant features can be disregarded as judged by their disordered geometric morphology. A graph attention network (GAT) is utilized for final feature matching, spanning across the image pair with geometric priors informed by GD. Comprehensive experiments show that GeoGlue outperforms other state-of-the-art methods in feature-matching accuracy and performance stability, achieving pose estimation with maximum rotation and translation errors under 1% in challenging scenes from benchmark datasets, Tanks & Temples and ETH3D. This study also proposes the first self-supervised deep-learning model for curved line detection, generating geometric priors for matching so that more attention is put on prominent features and improving the visual effect of 3D reconstruction.

Simulation of big data mixed attribute feature detection for power system intelligent operation and maintenance based on improved random forest algorithm

The diversity of attribute categories brings certain difficulties to data feature detection. In order to improve the accuracy and efficiency of feature detection, a hybrid attribute feature detection method for power system intelligent operation and maintenance big data based on improved random forest algorithm is proposed. Clustering processing power system intelligent operation and maintenance big data, based on data clustering results to reduce the characteristics of data mixed attributes, reduce the scale of data processing, and discretize the data mixed attributes; BP neural network is used to preprocess the results. Make corrections to improve the accuracy of feature detection, use the improved random forest algorithm to classify the data, and improve the convergence speed of the method. Finally, the support vector machine method is used to realize the feature detection of data mixed attributes. The experimental results show that the feature detection accuracy and efficiency of the method designed in this paper are high, and more features can be detected, which verifies its effectiveness. The method designed in this paper has the minimum RMSE value and the maximum value is only 0.12, which is far lower than the RMSE value of the improved spectral clustering algorithm and multi-domain feature extraction method, and has high detection accuracy.

Malignant melanoma dermoscopy image classification method based on multi‐modal medical features

AbstractSkin cancer is one of the deadliest cancers, and it has been widely developed worldwide since the last decade. Malignant melanoma is currently the most deadly skin cancer. If malignant melanoma is diagnosed at an early stage, the probability of patients being cured will be greatly improved. At present, most existing skin lesion image classification methods only use deep learning. However, the multi‐modal features of skin lesions in the medical domain are not well utilized and integrated. To reduce the classification error of the skin lesion images caused by the complexity and subjectivity of visual interpretation, a malignant melanoma dermoscopy image classification method based on multi‐modal medical features is proposed in this paper which is inspired by the fuzzy decision‐making process of doctors. It can reduce the subjective difference in the image classification process and assist dermatologists to analyze the skin lesion area. Firstly, the feature detection method based on the extension theory can effectively quantify the difference between different colour features. Then, an interpretable segmentation edge of the skin lesion is established by using the neutrosophic theory which can convert the image into the neutrosophic space. The edge of the skin lesion is captured by applying the Hierarchical Gaussian Mixture Model (HGMM) method. Next, the edge sequence is established by segmenting the edge, and the contour regularity, symmetry, and uniformity of the edge of the skin lesion are analyzed. Finally, the extracted multi‐feature sets are used for dermoscopy image classification. Experiments are carried out on real datasets, and the classification accuracy of four kernel functions is verified. The experimental results show that the authors’ method can effectively improve the classification accuracy of benign dermoscopy images and malignant dermoscopy images.

A computer vision approach to identifying the manufacturer of posterior thoracolumbar instrumentation systems.

Knowledge of the manufacturer of the previously implanted pedicle screw systems prior to revision spinal surgery may facilitate faster and safer surgery. Often, this information is unavailable because patients are referred by other centers or because of missing information in the patients' records. Recently, machine learning and computer vision have gained wider use in clinical applications. The authors propose a computer vision approach to classify posterior thoracolumbar instrumentation systems. Lateral and anteroposterior (AP) radiographs obtained in patients undergoing posterior thoracolumbar pedicle screw implantation for any indication at the authors' institution (2015-2021) were obtained. DICOM images were cropped to include both the pedicle screws and rods. Images were labeled with the manufacturer according to the operative record. Multiple feature detection methods were tested (SURF, MESR, and Minimum Eigenvalues); however, the bag-of-visual-words technique with KAZE feature detection was ultimately used to construct a computer vision support vector machine (SVM) classifier for lateral, AP, and fused lateral and AP images. Accuracy was tested using an 80%/20% training/testing pseudorandom split over 100 iterations. Using a reader study, the authors compared the model performance with the current practice of surgeons and manufacturer representatives identifying spinal hardware by visual inspection. Among the three image types, 355 lateral, 379 AP, and 338 fused radiographs were obtained. The five pedicle screw implants included in this study were the Globus Medical Creo, Medtronic Solera, NuVasive Reline, Stryker Xia, and DePuy Expedium. When the two most common manufacturers used at the authors' institution were binarily classified (Globus Medical and Medtronic), the accuracy rates for lateral, AP, and fused images were 93.15% ± 4.06%, 88.98% ± 4.08%, and 91.08% ± 5.30%, respectively. Classification accuracy decreased by approximately 10% with each additional manufacturer added. The multilevel five-way classification accuracy rates for lateral, AP, and fused images were 64.27% ± 5.13%, 60.95% ± 5.52%, and 65.90% ± 5.14%, respectively. In the reader study, the model performed five-way classification on 100 test images with 79% accuracy in 14 seconds, compared with an average of 44% accuracy in 20 minutes for two surgeons and three manufacturer representatives. The authors developed a KAZE feature detector with an SVM classifier that successfully identified posterior thoracolumbar hardware at five-level classification. The model performed more accurately and efficiently than the method currently used in clinical practice. The relative computational simplicity of this model, from input to output, may facilitate future prospective studies in the clinical setting.

A Hybrid Method for Ultrasound-Based Tracking of Skeletal Muscle Architecture.

Tracking skeletal muscle architecture using B-mode ultrasound is a widely used method in the field of human movement science and biomechanics. Sequential methods based on optical flow algorithms allow for smooth and coherent muscle tracking but are known to drift over time. Non-sequential feature detection methods on the other hand, do not suffer from drift, but are limited to tracking only lower-dimensional features. They are also known to be sensitive to image noise, and therefore often result in highly irregular tracking patterns. Building on the complimentary nature of both approaches, we present a novel automated hybrid muscle tracking approach that combines a sequential feature-point tracking method and a non-sequential method based on Hough transform. Tibialis anterior fascicle pennation angle and length, and central aponeurosis displacement, were measured in five healthy individuals during isometric contractions at five different ankle angles. Our hybrid method was demonstrated to significantly (p < 0.001) reduce drift compared to two sequential methods, and curve irregularity was significantly (p < 0.001) decreased compared to a non-sequential method. These findings suggest that the proposed hybrid approach can uniquely mitigate drift and irregularity limitation of individual methods used for tracking skeletal muscle architecture. Automated muscle tracking allows for convenient analysis of large datasets, whereas automatic drift correction opens the door for tracking muscle architecture in long ultrasound recordings during common movements, such as walking, running, and jumping without the need for manual intervention.

Identification of tidal features in deep optical galaxy images with convolutional neural networks

ABSTRACTInteractions between galaxies leave distinguishable imprints in the form of tidal features, which hold important clues about their mass assembly. Unfortunately, these structures are difficult to detect because they are low surface brightness features, so deep observations are needed. Upcoming surveys promise several orders of magnitude increase in depth and sky coverage, for which automated methods for tidal feature detection will become mandatory. We test the ability of a convolutional neural network to reproduce human visual classifications for tidal detections. We use as training ∼6000 simulated images classified by professional astronomers. The mock Hyper Suprime Cam Subaru (HSC) images include variations with redshift, projection angle, and surface brightness (μlim = 26–35 mag arcsec−2). We obtain satisfactory results with accuracy, precision, and recall values of Acc = 0.84, P = 0.72, and R = 0.85 for the test sample. While the accuracy and precision values are roughly constant for all surface brightness, the recall (completeness) is significantly affected by image depth. The recovery rate shows strong dependence on the type of tidal features: we recover all the images showing shell features and 87 per cent of the tidal streams; these fractions are below 75 per cent for mergers, tidal tails, and bridges. When applied to real HSC images, the performance of the model worsens significantly. We speculate that this is due to the lack of realism of the simulations, and take it as a warning on applying deep learning models to different data domains without prior testing on the actual data.

Wavelet Scattering Convolution Network-Based Detection Algorithm on Nondestructive Microcrack Electrical Signals of Eggs

The detection of poultry egg microcracks based on electrical characteristic models is a new and effective method. However, due to the disorder, mutation, nonlinear, time discontinuity, and other factors of the current data, detection algorithms such as support-vector machines (SVM) and random forest (RF) under traditional statistical characteristics cannot identify subtle defects. The detection system voltage is set to 1500 V in the existing method, and higher voltages may cause damage to the hatched eggs; therefore, how to reduce the voltage is also a focus of research. In this paper, to address the problem of the low signal-to-noise ratio of microcracks in current signals, a wavelet scattering transform capable of extracting translation-invariant and small deformation-stable features is proposed to extract multi-scale high-frequency feature vectors. In view of the time series and low feature scale of current signals, various convolutional networks, such as a one-dimensional convolutional neural network (1DCNN), long short-term memory (LSTM), bi-directional long short-term memory (Bi-LSTM), and gated recurrent unit (GRU) are adopted. The detection algorithm of the wavelet scattering convolutional network is implemented for electrical sensing signals. The experimental results show that compared with previous works, the accuracy, precision, recall, F1-score, and Matthews correlation coefficient of the proposed wavelet scattering convolutional network on microcrack datasets smaller than 3 μm at a voltage of 1000 V are 99.4393%, 99.2523%, 99.6226%, 99.4357%, and 98.8819%, respectively, with an average increase of 2.0561%. In addition, the promotability and validity of the proposed detection algorithm were verified on a class-imbalanced dataset and a duck egg dataset. Based on the good results of the above experiments, further experiments were conducted with different voltages. The new feature extraction and detection method reduces the sensing voltage from 1500 V to 500 V, which allows for achieving higher detection accuracy with a lower signal-to-noise ratio, significantly reducing the risk of high voltage damage to hatching eggs and meeting the requirements for crack detection.

Event-based feature tracking in a visual inertial odometry framework.

Introduction: Event cameras report pixel-wise brightness changes at high temporal resolutions, allowing for high speed tracking of features in visual inertial odometry (VIO) estimation, but require a paradigm shift, as common practices from the past decades using conventional cameras, such as feature detection and tracking, do not translate directly. One method for feature detection and tracking is the Eventbased Kanade-Lucas-Tomasi tracker (EKLT), an hybrid approach that combines frames with events to provide a high speed tracking of features. Despite the high temporal resolution of the events, the local nature of the registration of features imposes conservative limits to the camera motion speed. Methods: Our proposed approach expands on EKLT by relying on the concurrent use of the event-based feature tracker with a visual inertial odometry system performing pose estimation, leveraging frames, events and Inertial Measurement Unit (IMU) information to improve tracking. The problem of temporally combining high-rate IMU information with asynchronous event cameras is solved by means of an asynchronous probabilistic filter, in particular an Unscented Kalman Filter (UKF). The proposed method of feature tracking based on EKLT takes into account the state estimation of the pose estimator running in parallel and provides this information to the feature tracker, resulting in a synergy that can improve not only the feature tracking, but also the pose estimation. This approach can be seen as a feedback, where the state estimation of the filter is fed back into the tracker, which then produces visual information for the filter, creating a "closed loop". Results: The method is tested on rotational motions only, and comparisons between a conventional (not event-based) approach and the proposed approach are made, using synthetic and real datasets. Results support that the use of events for the task improve performance. Discussion: To the best of our knowledge, this is the first work proposing the fusion of visual with inertial information using events cameras by means of an UKF, as well as the use of EKLT in the context of pose estimation. Furthermore, our closed loop approach proved to be an improvement over the base EKLT, resulting in better feature tracking and pose estimation. The inertial information, despite prone to drifting over time, allows keeping track of the features that would otherwise be lost. Then, feature tracking synergically helps estimating and minimizing the drift.

A deep learning and full consistency approach to roadway safety scoring

The World Health Organization (WHO) estimated that worldwide road traffic crashes account for 1.35 million annual deaths in 2018. Most studies in road safety field have focused on studying road features effect on crash frequency and injury severity. However, limited studies use automatic road features detection methods to evaluate road safety. This research applies deep learning object detection to automatically identify roads features and Full Consistency Method (FUCOM) to rank the effect of road features on safety. A deep artificial network object detector is trained to efficiently detect road objects in a front-facing camera image, then FUCOM is applied to determine safety weights for ten Key Safety Indicators (KSIs). After determining final weights, the proposed approach is applied on a case study in Greater Cairo, in which 354 km of multi-class roads are divided to 1-km sections and assigned a road safety score (RSS). The resulting RSS identifies areas that exhibit low safety scores, enabling decision makers to focus their efforts on features that can attain highest improvement. This research contributes to supporting governments and roadway asset management agencies in prioritizing their efforts (and funding) in addressing roadway safety – especially where structured historical data collection programs are largely missing.

A survey of feature detection methods for localisation of plain sections of axial brain magnetic resonance imaging

Matching MRI brain images between patients or mapping patients’ MRI slices to the simulated atlas of a brain is key to the automatic registration of MRI of a brain. The ability to match MRI images would also enable such applications as indexing and searching MRI images among multiple patients or selecting images from the region of interest. In this work, we have introduced robustness, accuracy and cumulative distance metrics and methodology that allows us to compare different techniques and approaches in matching brain MRI of different patients or matching MRI brain slice to a position in the brain atlas. To that end, we have used feature detection methods AGAST, AKAZE, BRISK, GFTT, HardNet, and ORB, which are established methods in image processing, and compared them on their resistance to image degradation and their ability to match the same brain MRI slice of different patients. We have demonstrated that some of these techniques can correctly match most of the brain MRI slices of different patients. When matching is performed with the atlas of the human brain, their performance is significantly lower. The best performing feature detection method was a combination of SIFT detector and HardNet descriptor that achieved 93% accuracy in matching images with other patients and only 52% accurately matched images when compared to atlas.

AstroVision: Towards autonomous feature detection and description for missions to small bodies using deep learning

Missions to small celestial bodies rely heavily on optical feature tracking for characterization of and relative navigation around the target body. While deep learning has led to great advancements in feature detection and description, training and validating data-driven models for space applications is challenging due to the limited availability of large-scale, annotated datasets. This paper introduces AstroVision, a large-scale dataset comprised of 115,970 densely annotated, real images of 16 different small bodies captured during past and ongoing missions. We leverage AstroVision to develop a set of standardized benchmarks and conduct an exhaustive evaluation of both handcrafted and data-driven feature detection and description methods. Next, we employ AstroVision for end-to-end training of a state-of-the-art, deep feature detection and description network and demonstrate improved performance on multiple benchmarks. The full benchmarking pipeline and the dataset will be made publicly available to facilitate the advancement of computer vision algorithms for space applications.