Crater detection, classification and contextual information extraction in lunar images using a novel algorithm

Vijayan, S.; Vani, K.; Sanjeevi, S.

doi:10.1016/j.icarus.2013.06.028

Cited by 29 publications

(14 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…While the automatic identification of lunar impact craters has been successfully achieved (Kang, Luo, Hu, & Gamba, 2015;Vijayan, Vani, & Sanjeevi, 2013;Li, Ling, et al, 2015), to date the detection and mapping of lunar landslides has been obtained only through visual inspection of images (e.g. Brunetti et al, 2015;.…”

Section: Visual Detection Of Landslides Within Simple Impact Cratersmentioning

confidence: 99%

Recognition of landslides in lunar impact craters

Scaioni

Yordanov

Brunetti

et al. 2017

European Journal of Remote Sensing

View full text Add to dashboard Cite

Landslides have been observed on several planets and minor bodies of the solar System, including the Moon. Notwithstanding different types of slope failures have been studied on the Moon, a detailed lunar landslide inventory is still pending. Undoubtedly, such will be in a benefit for future geological and morphological studies, as well in hazard, risk and suscept- ibility assessments. A preliminary survey of lunar landslides in impact craters has been done using visual inspection on images and digital elevation model (DEM) (Brunetti et al. 2015) but this method suffers from subjective interpretation. A new methodology based on polynomial interpolation of crater cross-sections extracted from global lunar DEMs is presented in this paper. Because of their properties, Chebyshev polynomials were already exploited for para- metric classification of different crater morphologies (Mahanti et al., 2014). Here, their use has been extended to the discrimination of slumps in simple impact craters. Two criteria for recognition have provided the best results: one based on fixing an empirical absolute thresholding and a second based on statistical adaptive thresholding. The application of both criteria to a data set made up of 204 lunar craters’ cross-sections has demonstrated that the former criterion provides the best recognition

show abstract

Section: Visual Detection Of Landslides Within Simple Impact Cratersmentioning

confidence: 99%

Recognition of landslides in lunar impact craters

Scaioni

Yordanov

Brunetti

et al. 2017

European Journal of Remote Sensing

View full text Add to dashboard Cite

show abstract

“…Representing the maximum and minimum curvature of the Bouguer gravity position. Normalize the two eigenvalues to obtain the maximum horizontal gradient value: 11 11 22…”

Section: Gravity and Terrain Datamentioning

confidence: 99%

“…However, due to the low resolution of early DEM data, the small crater recognition was very bad. For the remote sensing image, many scholars use edge detection [11], genetic search algorithms [12] to extract crater images. Then using hough transform or least squares to fit and match the crater.…”

Section: Introductionmentioning

confidence: 99%

The crater with gravity anomaly in the center may be the ancient volcanic crater and geothermal under it

Cui

et al. 2019

Therm sci

View full text Add to dashboard Cite

Lunar volcanism play an important role on studying the thermal and compositional evolution of the Moon. However, the studies on the relationships among composition, location and age of Lunar volcanos are still limit. The high-quality and multi-source remote sensing data offer the opportunity to obtain significant features of the Lunar volcanism and the evolution of the Moon. Specifically, the high-quality gravitational features of volcanic landforms of the Moon are observed by the Gravity Recovery and Interior Laboratory. Besides, the lunar reconnaissance orbiter camera provides detail morphologic features of Lunar volcanos based on high-resolution optical images. This paper aims to find the characteristic of lunar volcanos by observing the gravitational and morphologic features in the center of craters. The final results show that most of the craters with central peaks have gravity anomalies except the Mendeleev crater (5.7 °N and 140.9 °E) whose central area contains significant gravity anomalies but no central peaks. The area of gravity anomaly may indicate heat source under the ground.

show abstract

“…Sixty years of advances in lunar exploration projects (e.g., the Luna missions and NASA's Apollo programme) have accumulated various lunar data, including digital images, digital elevation models (DEM) and lunar samples. Visual inspection of images and/or DEM data by experts or automatic detection [6][7][8] has recognized a large number of lunar craters, and consequently, many crater databases [9][10][11][12][13] have been established. However, the subjectivity of manual detection and the limitations of automatic detection with different types of data have resulted in significant disagreement in crater number among existing databases 14,15 .…”

mentioning

confidence: 99%

“…The typical characteristics of a crater include large extents, differences in diameter on the scale of orders of magnitude, large variations in shape due to overlapping or filling, and variable and complex morphologies. Existing automatic detection algorithms [6][7][8] based on pattern recognition and machine learning (ML) can determine the large extent characteristic of craters from the general features of craters. Deep learning (DL), in particular convolutional neural networks (CNNs) applied for the extraction of fine-grained information, has been used for the identification of lunar craters 20,21 .…”

mentioning

confidence: 99%

Lunar impact crater identification and age estimation with Chang’E data by deep and transfer learning

et al. 2020

View full text Add to dashboard Cite

Impact craters, which can be considered the lunar equivalent of fossils, are the most dominant lunar surface features and record the history of the Solar System. We address the problem of automatic crater detection and age estimation. From initially small numbers of recognized craters and dated craters, i.e., 7895 and 1411, respectively, we progressively identify new craters and estimate their ages with Chang’E data and stratigraphic information by transfer learning using deep neural networks. This results in the identification of 109,956 new craters, which is more than a dozen times greater than the initial number of recognized craters. The formation systems of 18,996 newly detected craters larger than 8 km are estimated. Here, a new lunar crater database for the mid- and low-latitude regions of the Moon is derived and distributed to the planetary community together with the related data analysis.

show abstract

Crater detection, classification and contextual information extraction in lunar images using a novel algorithm

Cited by 29 publications

References 49 publications

Recognition of landslides in lunar impact craters

Recognition of landslides in lunar impact craters

The crater with gravity anomaly in the center may be the ancient volcanic crater and geothermal under it

Lunar impact crater identification and age estimation with Chang’E data by deep and transfer learning

Contact Info

Product

Resources

About