Coupling Complementary Strategy to U-Net Based Convolution Neural Network for Detecting Lunar Impact Craters

Mao, Yuqing; Yuan, Ruozhen; Li, Wei; Liu, Yijing

doi:10.3390/rs14030661

Cited by 11 publications

(7 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…U-Net A common architecture for image segmentation tasks is U-Net. It comprises a decoder pathway that upsamples the features to regain the spatial resolution and an encoder pathway that progressively diminishes the spatial resolution while collecting high-level information 38 . U-Net joins equivalent levels of the encoder and decoder via skip links, allowing low-level and high-level information to be combined.…”

Section: Methodsmentioning

confidence: 99%

Automated Lunar Crater Identification with Chandrayaan-2 TMC-2 Images using Deep Convolutional Neural Networks

Sinha,

Paul,

Ghosh

et al. 2024

Sci Rep

View full text Add to dashboard Cite

Terrestrial planets and their moons have impact craters, contributing significantly to the complex geomorphology of planetary bodies in our Solar System. Traditional crater identification methods struggle with accuracy because of the diverse forms, locations, and sizes of the craters. Our main aim is to locate lunar craters using images from Terrain Mapping Camera-2 (TMC-2) onboard the Chandrayaan-II satellite. The crater-based U-Net model, a convolutional neural network frequently used in image segmentation tasks, is a deep learning method presented in this study. The task of crater detection was accomplished with the proposed model in two steps: initially, it was trained using Resnet18 as the backbone and U-Net based on Image Net as weights. Secondly, TMC-2 images from Chandrayaan-2 were used to detect craters based on the trained model. The model proposed in this study comprises a neural network, feature extractor, and optimization technique for lunar crater detection. The model achieves 80.95% accuracy using unannotated data and precision and recall are much better with annotated data with an accuracy of 86.91% in object detection with TMC-2 ortho images. 2000 images have been considered for the present work as manual annotation is a time-consuming process and the inclusion of more images can enhance the performance score of the model proposed.

show abstract

Section: Methodsmentioning

confidence: 99%

Automated Lunar Crater Identification with Chandrayaan-2 TMC-2 Images using Deep Convolutional Neural Networks

Sinha,

Paul,

Ghosh

et al. 2024

Sci Rep

View full text Add to dashboard Cite

show abstract

“…The work of using deep learning for crater detection can be divided into two categories: semantic segmentation-based and object detection-based. Silburt et al [23], Wang et al [24], Zhao et al [25] and Mao et al [26] consider lunar crater detection as a semantic segmentation task, where they detect craters on the lunar DEM data by improving the U-Net [27]. The core idea is to perform template matching on the mask predicted by the network and then extract the lunar craters.…”

Section: Introductionmentioning

confidence: 99%

LCDNet: An Innovative Neural Network for Enhanced Lunar Crater Detection Using DEM Data

Miao,

Yan,

et al. 2024

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

Lunar craters are essential for spacecraft landing navigation and lunar exploration missions. Deep learning holds great promise in the crater detection task, but still faces some challenges. One major issue is that using incomplete crater catalogs to create the crater dataset, which negatively impacts the training of deep learning models. Additionally, deep learning models are prone to missing detections in overlapping crater scenes. To address these challenges, we propose a novel Lunar Crater Detection Neural Network (LCD-Net), with two key innovations. The first innovation is the fusion of a Reserved Negative Sampling (RNS) module, which alleviates the problem of incomplete crater annotation in the dataset and detects a large number of potential new craters. The second innovation is the addition of an Adaptive Non-Maximum suppression (A-NMS) module, which optimizes the detection of overlapping craters and reduces the miss rate. We use lunar digital elevation model (DEM) to construct the crater dataset for training and evaluating the detection model. The experimental results demonstrate that LCD-Net achieves recall rates to 96% and 95% on the validation and the test sets, respectively. These results are significantly better than the state-of-the-art methods. Furthermore, LCD-Net also ables to detect tens of thousands of credible new lunar craters that can be used as an expansion to existing crater catalogs, making them more suitable for deep-learning dataset annotation. Overall, our work provides an efficient and reliable solution for lunar crater detection.

show abstract

“…By 2022, Tewari et al [23] adopted unsupervised and semi-supervised learning for crater identification, extracting crater morphology using a morphological approach. Moreover, algorithms based on various neural network architectures have been successfully applied to crater detection, yielding commendable results [24][25][26][27][28].…”

Section: Introductionmentioning

confidence: 99%

“…Automatic crater detection based on the DEM is commonly used to detect large craters [26,[28][29][30][31]. However, there are notable limitations in identifying small impact craters using DEM data.…”

Section: Introductionmentioning

confidence: 99%

Identification of Lunar Craters in the Chang’e-5 Landing Region Based on Kaguya TC Morning Map

Liu,

Lai,

Xie

et al. 2024

Remote Sensing

View full text Add to dashboard Cite

Impact craters are extensively researched geological features that contribute to various aspects of lunar science, such as evaluating the model age, regolith thickness, etc. The method for identifying impact craters has gradually transitioned from manual counting to automated identification. Automatic crater detection based on the digital elevation model (DEM) is commonly used to detect larger craters. However, using only DEM has limitations in discerning smaller craters (diameter < ~1 km). This study utilizes an improved Faster R-CNN algorithm and the Kaguya Terrain Camera (TC) morning map to detect small impact craters in the Chang’e-5 (CE-5) landing site. It uses model fusion to improve the precision of small crater identification. The results show a recall rate of 96.33% and a precision value of 90.19% for craters with diameters exceeding 200 m. The model found a total of 187,101 impact craters in the CE-5 region. The spatial distribution density of impact craters with diameters ranging from 100 m to 200 m is approximately 2.5706/km2. For craters with diameters ranging from 200 m to 1 km, the average spatial distribution density is about 0.9016/km2. By the unbiased impact crater density of chronological analysis, the model age of the Im2 and Em4 geological units in the CE-5 region is 3.78 Ga and 2.07 Ga, respectively.

show abstract

Coupling Complementary Strategy to U-Net Based Convolution Neural Network for Detecting Lunar Impact Craters

Cited by 11 publications

References 35 publications

Automated Lunar Crater Identification with Chandrayaan-2 TMC-2 Images using Deep Convolutional Neural Networks

Automated Lunar Crater Identification with Chandrayaan-2 TMC-2 Images using Deep Convolutional Neural Networks

LCDNet: An Innovative Neural Network for Enhanced Lunar Crater Detection Using DEM Data

Identification of Lunar Craters in the Chang’e-5 Landing Region Based on Kaguya TC Morning Map

Contact Info

Product

Resources

About