Survey of Visual Feature Extraction Algorithms in a Mars-like Environment

Oelsch, Martin; Opdenbosch, Dominik Van; Steinbach, Eckehard

doi:10.1109/ism.2017.58

Cited by 5 publications

(6 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Concerning the planetary-based scenes, several studies investigate feature extraction methodologies in extraterrestrial terrains using conventional algorithms. In [22,23], an evaluation of handcrafted feature extraction algorithms, in a Mars-like environment is presented. In [22], authors compare the algorithms' performance in terms of location recognition, using Devon Island dataset [24], concluding that SURF achieves the highest accuracy in non-vegetated and rocky unstructured environments.…”

Section: Related Workmentioning

confidence: 99%

Keypoint Detection and Description through Deep Learning in Unstructured Environments

Petrakis,

Partsinevelos

2023

Robotics

View full text Add to dashboard Cite

Feature extraction plays a crucial role in computer vision and autonomous navigation, offering valuable information for real-time localization and scene understanding. However, although multiple studies investigate keypoint detection and description algorithms in urban and indoor environments, far fewer studies concentrate in unstructured environments. In this study, a multi-task deep learning architecture is developed for keypoint detection and description, focused on poor-featured unstructured and planetary scenes with low or changing illumination. The proposed architecture was trained and evaluated using a training and benchmark dataset with earthy and planetary scenes. Moreover, the trained model was integrated in a visual SLAM (Simultaneous Localization and Maping) system as a feature extraction module, and tested in two feature-poor unstructured areas. Regarding the results, the proposed architecture provides a mAP (mean Average Precision) in a level of 0.95 in terms of keypoint description, outperforming well-known handcrafted algorithms while the proposed SLAM achieved two times lower RMSE error in a poor-featured area with low illumination, compared with ORB-SLAM2. To the best of the authors’ knowledge, this is the first study that investigates the potential of keypoint detection and description through deep learning in unstructured and planetary environments.

show abstract

Section: Related Workmentioning

confidence: 99%

Keypoint Detection and Description through Deep Learning in Unstructured Environments

Petrakis,

Partsinevelos

2023

Robotics

View full text Add to dashboard Cite

show abstract

“…It can be assumed there are n correspondences, hence 2n equations can be generated by (7). A natural idea of eliminatingt 1 and t 2 is to take the sum of each equation in (7) and get an average of the sum respectively, which is referred to in [18], [28]. Consequently, we subtract each equation in (7) from its average.…”

Section: B Variables Eliminationmentioning

confidence: 99%

“…Since s must be bigger than 0,t 3 is known when f 1 , f 2 , q 1 , q 2 are solved. Oncet 3 is obtained,t 1 andt 2 can be calculated by (7). Otherwise, we can eliminatẽ t 3 by the two denormalized equations, which are different from [28].…”

Section: B Variables Eliminationmentioning

confidence: 99%

See 1 more Smart Citation

A Robust Visual Localization Method With Unknown Focal Length Camera

Yin

Tan

et al. 2021

IEEE Access

View full text Add to dashboard Cite

PnP problem is well researched in many fields, such as computer vision. It is considered the fundamental method to solve the key problems of robot SLAM. However, in pedestrian visual localization, uncalibrated PnP (UPnP), specifically PnP with unknown focal length (PnPf) is more suitable for solving the problem. Recently, a few researchers proposed some methods to alleviate this problem. However, the localization accuracy of the existing methods is not satisfied when image pixel noise is larger. In other words, RANSAC should be running before solving the PnPf problem to get less noisy input, which means the localization delay increases inevitably. In this paper, we propose a more robust method for solving the PnPf problem without the help of RANSAC based on Gröbner basis and convex optimization. We build a Gröbner basis solver on the offline stage with one instance in the prime field. Then, we substitute the coefficients with real value and find multiple solutions on the online stage. Finally, we construct a convex optimization program to seek the final robust solution to PnPf problem. The other purpose of this paper is to provide a second-level localization experience for the end-user. The simulation result shows that our method can give a localization solution, which is more reliable than benchmark methods by both synthetic and real data verified.

show abstract

“…In addition, Martian soil is not only the main target of surface exploration activity of Mars but also one of the important factors to be considered in the design of surface detectors. Simulations of similar Martian soils help us understand the characteristics of Martian soil, which provides feasibility and reference for our next use of Earth's sand to experimentally analyze some of the characteristics of Martian soil [16][17][18][19].…”

Section: Introductionmentioning

confidence: 99%

BRDF Model of Mars Simulation Soil and Its Comparison with BRDF of Earth Sand

et al. 2021

View full text Add to dashboard Cite

In this paper, a seven-parameter BRDF model with double-peak characteristic, which could fit double-peak data, was adopted to fit the BRDF of Mars simulation soil. At the same time, the three-dimensional figure of the original data of the sample and the three-dimensional curve of the fitted curve were given. The results proved that the model worked well for this type of data. In addition, the experimental data of four kinds of earth sand samples with different roughness were also fitted and analyzed. It was found that the model still had a good fitting effect on such data. At last, the Mars simulation soil and the four kinds of earth sand samples with different roughness were compared horizontally and vertically. Moreover, the double-peak characteristics and other properties of the Mars simulation soil and the earth sand were analyzed under the same and different roughness.

show abstract

Survey of Visual Feature Extraction Algorithms in a Mars-like Environment

Cited by 5 publications

References 15 publications

Keypoint Detection and Description through Deep Learning in Unstructured Environments

Keypoint Detection and Description through Deep Learning in Unstructured Environments

A Robust Visual Localization Method With Unknown Focal Length Camera

BRDF Model of Mars Simulation Soil and Its Comparison with BRDF of Earth Sand

Contact Info

Product

Resources

About