Crater Detection Algorithm Research Articles

Crater identification by perspective cone alignment

Crater identification aims to match the craters of a planetary body observed in an image to the corresponding entries in a catalogue of known craters of the same body. It is a key step in crater-based navigation algorithms for planetary missions. Many crater identification methods extract descriptors from the observed craters and compare them to an index of descriptors constructed a priori from the crater catalogue. The need for viewpoint invariance motivates descriptors defined over crater tuples (e.g., crater triads for projective invariance). However, this implies a descriptor index that grows rapidly (e.g., cubically) with the size of the catalogue, which practically limits the spatial resolution and/or coverage of the catalogue. Another serious drawback is the sensitivity of the descriptors and the matching accuracy to noise and outliers in the crater detection result, which are inevitable due to imperfect crater detection algorithms. In this paper, we propose a novel descriptorless crater identification technique. At its core, our method solves the perspective cone alignment problem with geometric verification iteratively over the crater catalogue. We show that our simple algorithm, with time and space complexities that are linear in the catalogue size, is substantially more accurate than state-of-the-art descriptor-based methods in the presence of noise. Moreover, the availability of multi-core onboard processors raises the prospect of speeding up our method through parallelisation.

Crater Triangle Matching Algorithm Based on Fused Geometric and Regional Features

Craters are regarded as significant navigation landmarks during the descent and landing process in small body exploration missions for their universality. Recognizing and matching craters is a crucial prerequisite for visual and LIDAR-based navigation tasks. Compared to traditional algorithms, deep learning-based crater detection algorithms can achieve a higher recognition rate. However, matching crater detection results under various image transformations still poses challenges. To address the problem, a composite feature-matching algorithm that combines geometric descriptors and region descriptors (extracting normalized region pixel gradient features as feature vectors) is proposed. First, the geometric configuration map is constructed based on the crater detection results. Then, geometric descriptors and region descriptors are established within each feature primitive of the map. Subsequently, taking the salience of geometric features into consideration, composite feature descriptors with scale, rotation, and illumination invariance are generated through fusion geometric and region descriptors. Finally, descriptor matching is accomplished by computing the relative distances between descriptors and adhering to the nearest neighbor principle. Experimental results show that the composite feature descriptor proposed in this paper has better matching performance than only using shape descriptors or region descriptors, and can achieve a more than 90% correct matching rate, which can provide technical support for the small body visual navigation task.

Crater Detection and Population Statistics in Tianwen-1 Landing Area Based on Segment Anything Model (SAM)

Crater detection is useful for research into dating a planetary surface’s age and geological mapping. The high-resolution imaging camera (HiRIC) carried by the Tianwen-1 rover provides digital image model (DIM) datasets with a resolution of 0.7 m/pixel, which are suitable for detecting meter-scale craters. The existing deep-learning-based automatic crater detection algorithms require a large number of crater annotation datasets for training. However, there is currently a lack of datasets of optical images of small-sized craters. In this study, we propose a model based on the Segment Anything Model (SAM) to detect craters in Tianwen-1’s landing area and perform statistical analysis. The SAM network was used to obtain a segmentation mask of the craters from the DIM images. Then non-circular filtering was used to filter out irregular craters. Finally, deduplication and removal of false positives were performed to obtain accurate circular craters, and their center’s position and diameter were obtained through circular fitting analysis. We extracted 841,727 craters in total, with diameters ranging from 1.57 m to 7910.47 m. These data are useful for further Martian crater catalogs and crater datasets. Additionally, the crater size–frequency distribution (CSFD) was also analyzed, indicating that the surface ages of the Tianwen-1 landing area are ~3.25 billion years, with subsequent surface resurfacing events occurring ~1.67 billion years ago.

Cross-attention induced multilayer domain adaptation network for extraction of sub-kilometer craters from HiRIC images

Deep learning-based crater detection algorithms have made remarkable progress in the fields of space science and engineering, establishing themselves as the leading solutions for Mars geology exploration. However, achieving outstanding performance with deep networks requires extensive annotated data, resulting in time-consuming and labor-intensive labeling processes. In response to this challenge, we propose a novel approach, the Cross-Attention-Induced Multilayer Domain Adaptation Network (CAMDA-Net), specifically designed for crater detection. CAMDA-Net leverages domain adaptation techniques to transfer valuable crater knowledge from the Moon to Mars, effectively bypassing the need for manual labeling. In our network, we integrate CenterNet*, an anchor-free detector, to expedite and enhance the accuracy of crater detection. Furthermore, we implement crater feature alignment through adversarial training at both the image and instance levels. The dual cross-attention mechanism at the image level directs the network’s focus towards transferable crater features while suppressing noise effects. At the instance level, the foreground and background alignment model streamlines feature alignment and eliminates negative proposals. To assess the efficacy of our proposed method, we build the interplanetary domain-adaptive crater dataset (IDCD), which encompasses three subsets: the LRO WAC crater dataset, THEMIS crater dataset, and HiRIC crater dataset. This diverse dataset incorporates various shapes, lighting conditions, scales, and resolutions, making it an ideal resource for conducting transfer learning studies. We have made the IDCD publicly accessible on Github at https://github.com/PlanetaryScience3510. The experimental results on the IDCD subset from the LRO WAC to HiRIC demonstrate that our CAMDA-Net achieves precision and recall values of 0.77 and 0.79, respectively, slightly surpassing classic domain-adaptive detectors, DAF and SCDA. With encouraging performance, CAMDA-Net shows great promise for advancing crater detection and analysis on Mars, presenting exciting possibilities for future research and applications.

Comparison of Automated Crater Catalogs for Mars From Benedix et al. (2020) and Lee and Hogan (2021)

AbstractCrater mapping using neural networks and other automated methods has increased recently with automated Crater Detection Algorithms (CDAs) applied to planetary bodies throughout the solar system. A recent publication by Benedix et al. (2020, https://doi.org/10.1029/2019ea001005) showed high performance at small scales compared to similar automated CDAs but with a net positive diameter bias in many crater candidates. I compare the publicly available catalogs from Benedix et al. (2020, https://doi.org/10.1029/2019ea001005) and Lee and Hogan (2021, https://doi.org/10.1016/j.cageo.2020.104645) and show that the reported performance is sensitive to the metrics used to test the catalogs. I show how the more permissive comparison methods indicate a higher CDA performance by allowing worse candidate craters to match ground‐truth craters. I show that the Benedix et al. (2020, https://doi.org/10.1029/2019ea001005) catalog has a substantial performance loss with increasing latitude and identify an image projection issue that might cause this loss. Finally, I suggest future applications of neural networks in generating large scientific datasets be validated using secondary networks with independent data sources or training methods.

Lunar Surface Model Age Derivation: Comparisons Between Automatic and Human Crater Counting Using LRO‐NAC and Kaguya TC Images

AbstractDating young lunar surfaces, such as impact ejecta blankets and terrains associated with recent volcanic activities, provides critical information on the recent events that shaped the surface of the Moon. Model age derivation of young or small areas using a crater chronology is typically achieved through manual counting, which requires a lot of small impact craters to be tediously mapped. In this study, we present the use of a Crater Detection Algorithm (CDA) to extract crater populations on Lunar Reconnaissance Orbiter—Narrow Angle Camera (LRO‐NAC) and Kaguya Terrain Camera images. We applied our algorithm to images covering the ejecta blankets of four Copernican impact craters and across four young mare terrains, where manually derived model ages were already published. Across the eight areas, 10 model ages were derived. We assessed the reproducibility of our model using two populations for each site: (a) an unprocessed population and (b) a population adjusted to remove contaminations of secondary and buried craters. The results showed that unprocessed detections led to overestimating crater densities by 12%–48%, but “adjusted” populations produced consistent results within <20% of published values in 80% of cases. Regarding the discrepancies observed, we found no significant error in our detections that could explain the differences with crater densities manually measured. With careful processing, we conclude that a CDA can be used to determine model ages and crater densities for the Moon. We also emphasize that automated crater datasets need to be processed, interpreted and used carefully, in unity with geologic reasoning. The presented approach can offer a consistent and reproducible way to derive model ages.

English

Navigation of a lander craft to accurately soft land in a predetermined spot on an extra-terrestrial body is a challenging task. Due to the absence of GPS and real-time ground communication links, the lander craft has to navigate autonomously to the targeted landing site solely with the help of its onboard sensors. One of the major challenges in position estimation of the lander craft is the measurement inaccuracies associated with the inertial navigation systems. Optical landmark detection-based techniques are employed to aid the lander navigation and guidance system. In this technique, craters and their relative positions are used as landmarks for position estimation. Typical crater detection algorithms employ handcrafted feature extractors for crater identification. Recently deep learning-based approaches have been employed for crater detection, mainly for geomorphological studies and cataloguing. This paper proposes using deep learning-based object detection techniques applied to autonomous landing missions and their implementation on a Xilinx MPSoC FPGA device. Prototype hardware has been developed, and the YOLOv4-tiny algorithm has been implemented on it with an inference time of 471 ms per image. The results are presented, and their performance is evaluated.

ELCD: Efficient Lunar Crater Detection Based on Attention Mechanisms and Multiscale Feature Fusion Networks from Digital Elevation Models

The detection and counting of lunar impact craters are crucial for the selection of detector landing sites and the estimation of the age of the Moon. However, traditional crater detection methods are based on machine learning and image processing technologies. These are inefficient for situations with different distributions, overlaps, and crater sizes, and most of them mainly focus on the accuracy of detection and ignore the efficiency. In this paper, we propose an efficient lunar crater detection (ELCD) algorithm based on a novel crater edge segmentation network (AFNet) to detect lunar craters from digital elevation model (DEM) data. First, in AFNet, a lightweight attention mechanism module is introduced to enhance the feature extract capabilities of networks, and a new multiscale feature fusion module is designed by fusing different multi-level feature maps to reduce the information loss of the output map. Then, considering the imbalance in the classification and the distributions of the crater data, an efficient crater edge segmentation loss function (CESL) is designed to improve the network optimization performance. Lastly, the crater positions are obtained from the network output map by the crater edge extraction (CEA) algorithm. The experiment was conducted on the PyTorch platform using two lunar crater catalogs to evaluate the ELCD. The experimental results show that ELCD has a superior detection accuracy and inference speed compared with other state-of-the-art crater detection algorithms. As with most crater detection models that use DEM data, some small craters may be considered to be noise that cannot be detected. The proposed algorithm can be used to improve the accuracy and speed of deep space probes in detecting candidate landing sites, and the discovery of new craters can increase the size of the original data set.

Automatic Mapping of Small Lunar Impact Craters Using LRO‐NAC Images

AbstractImpact craters are the most common feature on the Moon’s surface. Crater size–frequency distributions provide critical insight into the timing of geological events, surface erosion rates, and impact fluxes. The impact crater size–frequency follows a power law (meter‐sized craters are a few orders of magnitude more numerous than kilometric ones), making it tedious to manually measure all the craters within an area to the smallest sizes. We can bridge this gap by using a machine learning algorithm. We adapted a Crater Detection Algorithm to work on the highest resolution lunar image data set (Lunar Reconnaissance Orbiter‐Narrow‐Angle Camera [NAC] images). We describe the retraining and application of the detection model to preprocessed NAC images and discussed the accuracy of the resulting crater detections. We evaluated the model by assessing the results across six NAC images, each covering a different lunar area at differing lighting conditions. We present the model’s average true positive rate for small impact craters (down to 20 m in diameter) is 93%. The model does display a 15% overestimation in calculated crater diameters. The presented crater detection model shows acceptable performance on NAC images with incidence angles ranging between ∼50° and ∼70° and can be applied to many lunar sites independent to morphology.

Lunar Crater Detection on Digital Elevation Model: A Complete Workflow Using Deep Learning and Its Application

Impact cratering process is the major geologic activity on the surface of the Moon, and the spatial distribution and size-frequency distribution of lunar craters are indicative to the bombardment history of the Solar System. The substantial efforts on the development of automated crater detection algorithms (CDAs) have been carried out on the images from the remote sensing observations. Recently, CDAs via convolutional neural network (CNN) on digital elevation model (DEM) has been developed as it can combine the discrimination ability of CNN with the robust characteristic of the DEM data. However, most of the existing algorithms adopt a traditional two-stage detection pipeline including an edge segmentation and a template matching step. In this paper, we attempt to reduce the gap between the existing DEM-based CDAs and the advanced CNN methods for object detection, and propose a complete workflow including an end-to-end deep learning pipeline for lunar crater detection, in particular for craters smaller than 50 km in diameter. Based on the workflow, we benchmark nine representative CNN models involving three popular types of detection architectures. Moreover, we elaborate on the practical application of the proposed workflow, and provide an example method to demonstrate the performance advantage in terms of the precision (82.97%) and recall (79.39%). Furthermore, we develop a crater verification tool to manually validate the detection results, and the visualization results show that our detected craters are reasonable and can be used as a supplement to the existing hand-labeled datasets.

Robust Crater Detection Algorithm Based on Maximum Entropy Threshold Segmentation

For future lunar exploration and planetary missions, the digital elevation model (DEM) of the target object may not be well prepared before the mission, so developing a new robust crater detection algorithm (CDA) without prepared high-precision DEM is needed to meet the requirements of a high-reliability and high-precision detection and navigation system. In this paper, we presented a new robust lunar CDA method based on maximum entropy threshold segmentation. By calculating the entropy distribution of the ternary image, the threshold for retaining the maximum amount of image information is selected adaptively, a variety of evaluation indicators are proposed, and a multiple-indicator constraint matrix is constructed to realize the extraction and fitting of the craters. The proposed method has the following advantages: (1) it has strong robustness and is capable of extracting complete craters under multiple illumination conditions, which makes it suitable for the extraction of large-scale planetary and lunar images; (2) the extracted crater edges are clear and complete and do not merge with the surrounding environment edge; and (3) it avoids the problem of parameter sensitivity that is present in a traditional CDA algorithm. The proposed method was verified using an image taken by the Chang’e-2 lunar probe, and a comparison with the traditional method based on morphology and adaptive Canny edge detection shows that the number of craters detected increases by more than 35%, while the computational efficiency is improved by more than 40%.

A Novel Approach for Multiscale Lunar Crater Detection by the Use of Path-Profile and Isolation Forest Based on High-Resolution Planetary Images

Crater detection from planetary images is a challenging issue due to the complicated variations in geometry shape, illumination, and scale. An automatic crater detection algorithm (CDA) that is robust to these factors is, therefore, necessary. In this article, a novel automatic CDA that is robust to these factors is proposed to detect the multiscale craters of the Moon. The proposed method consists of two main steps: 1) in the hypothesis generation (HG) step, a novel feature operator called the path-profile, which is constructed based on the self-defined adjacency graph and a path descriptor, is presented to derive the highlight-shadow feature of craters for detecting candidate craters. 2) In the hypothesis verification (HV) step, based on the idea of anomaly detection, the isolation forest algorithm which is an unsupervised learning anomaly detection method is applied to eliminate falsely detected craters. Lunar Reconnaissance Orbiter Camera Wide Angle Camera and Narrow Angle Camera images and Chang’E-4 landing camera images were used to test the accuracy and robustness of the proposed method. The experimental results indicate that: on average, the accuracy of the detection result of the HG step is about 90%, and the HV step can further improve this by 3%–4%. The proposed method is a reliable way to detect multiscale lunar craters for various resolutions images with diameters ranging from five pixels to hundreds of pixels, and it is robust to the different terrains and illumination conditions on the Moon.

The Tharsis mantle source of depleted shergottites revealed by 90 million impact craters

The only martian rock samples on Earth are meteorites ejected from the surface of Mars by asteroid impacts. The locations and geological contexts of the launch sites are currently unknown. Determining the impact locations is essential to unravel the relations between the evolution of the martian interior and its surface. Here we adapt a Crater Detection Algorithm that compile a database of 90 million impact craters, allowing to determine the potential launch position of these meteorites through the observation of secondary crater fields. We show that Tooting and 09-000015 craters, both located in the Tharsis volcanic province, are the most likely source of the depleted shergottites ejected 1.1 million year ago. This implies that a major thermal anomaly deeply rooted in the mantle under Tharsis was active over most of the geological history of the planet, and has sampled a depleted mantle, that has retained until recently geochemical signatures of Mars’ early history.

Crater Detection and Recognition Method for Pose Estimation

A crater detection and recognition algorithm is the key to pose estimation based on craters. Due to the changing viewing angle and varying height, the crater is imaged as an ellipse and the scale changes in the landing camera. In this paper, a robust and efficient crater detection and recognition algorithm for fusing the information of sequence images for pose estimation is designed, which can be used in both flying in orbit around and landing phases. Our method consists of two stages: stage 1 for crater detection and stage 2 for crater recognition. In stage 1, a single-stage network with dense anchor points (dense point crater detection network, DPCDN) is conducive to dealing with multi-scale craters, especially small and dense crater scenes. The fast feature-extraction layer (FEL) of the network improves detection speed and reduces network parameters without losing accuracy. We comprehensively evaluate this method and present state-of-art detection performance on a Mars crater dataset. In stage 2, taking the encoded features and intersection over union (IOU) of craters as weights, we solve the weighted bipartite graph matching problem, which is matching craters in the image with the previously identified craters and the pre-established craters database. The former is called “frame-frame match”, or FFM, and the latter is called “frame-database match”, or FDM. Combining the FFM with FDM, the recognition speed is enabled to achieve real-time on the CPU (25 FPS) and the average recognition precision is 98.5%. Finally, the recognition result is used to estimate the pose using the perspective-n-point (PnP) algorithm and results show that the root mean square error (RMSE) of trajectories is less than 10 m and the angle error is less than 1.5 degrees.

Split-Attention Networks with Self-Calibrated Convolution for Moon Impact Crater Detection from Multi-Source Data

Impact craters are the most prominent features on the surface of the Moon, Mars, and Mercury. They play an essential role in constructing lunar bases, the dating of Mars and Mercury, and the surface exploration of other celestial bodies. The traditional crater detection algorithms (CDA) are mainly based on manual interpretation which is combined with classical image processing techniques. The traditional CDAs are, however, inefficient for detecting smaller or overlapped impact craters. In this paper, we propose a Split-Attention Networks with Self-Calibrated Convolution (SCNeSt) architecture, in which the channel-wise attention with multi-path representation and self-calibrated convolutions can generate more prosperous and more discriminative feature representations. The algorithm first extracts the crater feature model under the well-known target detection R-FCN network framework. The trained models are then applied to detecting the impact craters on Mercury and Mars using the transfer learning method. In the lunar impact crater detection experiment, we managed to extract a total of 157,389 impact craters with diameters between 0.6 and 860 km. Our proposed model outperforms the ResNet, ResNeXt, ScNet, and ResNeSt models in terms of recall rate and accuracy is more efficient than that other residual network models. Without training for Mars and Mercury remote sensing data, our model can also identify craters of different scales and demonstrates outstanding robustness and transferability.

Semi-Supervised Deep Learning for Lunar Crater Detection Using CE-2 DOM

Lunar craters are very important for estimating the geological age of the Moon, studying the evolution of the Moon, and for landing site selection. Due to a lack of labeled samples, processing times due to high-resolution imagery, the small number of suitable detection models, and the influence of solar illumination, Crater Detection Algorithms (CDAs) based on Digital Orthophoto Maps (DOMs) have not yet been well-developed. In this paper, a large number of training data are labeled manually in the Highland and Maria regions, using the Chang’E-2 (CE-2) DOM; however, the labeled data cannot cover all kinds of crater types. To solve the problem of small crater detection, a new crater detection model (Crater R-CNN) is proposed, which can effectively extract the spatial and semantic information of craters from DOM data. As incomplete labeled samples are not conducive for model training, the Two-Teachers Self-training with Noise (TTSN) method is used to train the Crater R-CNN model, thus constructing a new model—called Crater R-CNN with TTSN—which can achieve state-of-the-art performance. To evaluate the accuracy of the model, three other detection models (Mask R-CNN, no-Mask R-CNN, and Crater R-CNN) based on semi-supervised deep learning were used to detect craters in the Highland and Maria regions. The results indicate that Crater R-CNN with TTSN achieved the highest precision (of 91.4% and 88.5%, respectively) in the Highland and Maria regions, even obtaining the highest recall and F1 score. Compared with Mask R-CNN, no-Mask R-CNN, and Crater R-CNN, Crater R-CNN with TTSN had strong robustness and better generalization ability for crater detection within 1 km in different terrains, making it possible to detect small craters with high accuracy when using DOM data.

Knowledge-Driven GeoAI: Integrating Spatial Knowledge into Multi-Scale Deep Learning for Mars Crater Detection

This paper introduces a new GeoAI solution to support automated mapping of global craters on the Mars surface. Traditional crater detection algorithms suffer from the limitation of working only in a semiautomated or multi-stage manner, and most were developed to handle a specific dataset in a small subarea of Mars’ surface, hindering their transferability for global crater detection. As an alternative, we propose a GeoAI solution based on deep learning to tackle this problem effectively. Three innovative features are integrated into our object detection pipeline: (1) a feature pyramid network is leveraged to generate feature maps with rich semantics across multiple object scales; (2) prior geospatial knowledge based on the Hough transform is integrated to enable more accurate localization of potential craters; and (3) a scale-aware classifier is adopted to increase the prediction accuracy of both large and small crater instances. The results show that the proposed strategies bring a significant increase in crater detection performance than the popular Faster R-CNN model. The integration of geospatial domain knowledge into the data-driven analytics moves GeoAI research up to the next level to enable knowledge-driven GeoAI. This research can be applied to a wide variety of object detection and image analysis tasks.

Model Age Derivation of Large Martian Impact Craters, Using Automatic Crater Counting Methods

AbstractDetermining when an impact crater formed is a complex and tedious task. However, this knowledge is crucial to understanding the geological history of planetary bodies and, more specifically, gives information on erosion rate measurements, meteorite ejection location, impact flux evolution and the loss of a magnetic field. The derivation of an individual crater's age is currently performed through manual counting. Because crater size scales as a power law, this method is limited to small (and/or young) surface areas and, in the case of the derivation of crater emplacement age, to a small set of impact craters. Here, we used a Crater Detection Algorithm, specifically retrained to detect small impact craters on large‐ and high‐resolution imagery data set to solve this issue. We applied it to a global, 5 m/pixel resolution mosaic of Mars. Here, we test the use of this data set to date 10 large impact craters. We developed a cluster analysis tool in order to distinguish potential secondary crater clusters from the primary crater population. We then use this, filtered, crater population to date each large impact crater and evaluate our results against literature ages. We found that automated counting filtered through clustering analysis produced similar model ages to manual counts. This technique can now be expanded to much wider crater dating surveys, and by extension to any other kind of Martian surface. We anticipate that this new tool will considerably expand our knowledge of the geological events that have shaped the surface of Mars, their timing and duration.

Aerial Bombing Crater Identification: Exploitation of Precise Digital Terrain Models

Places of past conflicts and persistent objects that reflect such events often attract the attention of archaeological prospection which facilitates the construction of conflict narratives. Field prospection as a precise method for localization of aerial bombing craters (as an example of such persistent features) is a highly time- and resource-consuming task. Therefore, methods for automatic identification of such features are evolving. We present a comparison of three methods for possible automatic crater detection based on (a) extraterrestrial crater detection algorithms, (b) geomorphology-based edge extraction, and (c) image pattern recognition via a state-of-the-art convolutional neural network (CNN). All methods were preliminarily tested on a case study of eight Second World War (WWII) aerial bombing crater sites in NW Czechia via Airborne Laser Scanned LiDAR-derived digital terrain models with different spatial resolutions. We found that extraterrestrial crater detection algorithms and geomorphology-based edge extraction methods yield worse results given the standard indices of precision and recall. By comparison, the CNN method utilized for a particular task achieved satisfying results, predominantly with 0.5 m/px resolution (which is often available at the country level) of the input raster. Nevertheless, overall performance with this resolution varies significantly among the sites. Therefore, the quality and readability of the input data are crucial factors for the successful acquisition of precise ordinance location identification.

Automated crater detection with human level performance

Crater cataloging is an important yet time-consuming part of geological mapping. We present an automated Crater Detection Algorithm (CDA) that is competitive with expert-human researchers and hundreds of times faster.The CDA uses multiple neural networks to process digital terrain model and thermal infra-red imagery to identify and locate craters across the surface of Mars. We use additional post-processing filters to refine and remove potential false crater detections, improving our precision and recall by 10% compared to Lee (2019). We now find 80% of known craters above 3km in diameter, and identify 7,000 potentially new craters (13% of the identified craters). The median differences between our catalog and other independent catalogs is 2%–4% in location and diameter, in-line with other inter-catalog comparisons.The CDA has been used to process global terrain maps and infra-red imagery for Mars, and the software and generated global catalog are available at https://doi.org/10.5683/SP2/CFUNII.