The DOI matches its Crossref record; the references it cites are not checked yet.
Multi-scale Features for Detection and Segmentation of Rocks in Mars Images
Abstract
Geologists and planetary scientists will benefit from methods for accurate segmentation of rocks in natural scenes. However, rocks are poorly suited for current visual segmentation techniques - they exhibit diverse morphologies and have no uniform property to distinguish them from background soil. We address this challenge with a novel detection and segmentation method incorporating features from multiple scales. These features include local attributes such as texture, object attributes such as shading and two-dimensional shape, and scene attributes such as the direction of illumination. Our method uses a superpixel segmentation followed by region-merging to search for the most probable groups of superpixels. A learned model of rock appearances identifies whole rocks by scoring candidate superpixel groupings. We evaluate our method's performance on representative images from the Mars Exploration Rover catalog.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Rocks have significantly different appearances, and it is challenging to use unified properties to identify the background and rocks [59].”
From Semantic Terrain Segmentation in the Navigation Vision of Planetary Rovers—A Systematic Literature Review (2022) · cites this paper as [59]
In the citing paper
“Thus, it is easy to miss important geological information during planetary rover operations [59].”
From Semantic Terrain Segmentation in the Navigation Vision of Planetary Rovers—A Systematic Literature Review (2022) · cites this paper as [59]
In the citing paper
“Therefore, it is necessary to segment rocks to identify their geological properties [59].”
From Semantic Terrain Segmentation in the Navigation Vision of Planetary Rovers—A Systematic Literature Review (2022) · cites this paper as [59]
In the citing paper
“For example, the precision in reference [59] is only about 65%, while reference [65] achieved precision of more than 99% (see Table 3 for the quantitative results).”
From Semantic Terrain Segmentation in the Navigation Vision of Planetary Rovers—A Systematic Literature Review (2022) · cites this paper as [59]
Citations
The citation lists haven’t been fetched yet
References 22 · Cited by 55
Research works printed but not linked: 20
- varma, 2005, A statistical approach to texture classification from single images, International Journal of Computer Vision Special Issue on Texture Analysis and Synthesis, 62, 61
- peura, 1997, Efficiency of simple shape descriptors, Proceedings of the Third International Workshop on Visual Form, 443
- mikli, 2001, Characterization of powder particle morphology, Proc Estonian Acad Sci Eng, 7, 22
- shi, 2000, Normalized cuts and image segmentation, IEEE Trans PAMI, 22, 888, 10.1109/34.868688 · DOI
- 10.1109/TPAMI.2004.1273918 · DOI
- 10.1023/B:VISI.0000022288.19776.77 · DOI
- 10.1109/ICCV.2005.112 · DOI
- 10.1109/34.1000236 · DOI
- 10.1109/TPAMI.2002.1023800 · DOI
- chang, 2001, LIBSVM A library for support vector machines
- 10.1109/34.784284 · DOI · Paper page
- 10.1109/AERO.2002.1035371 · DOI · Paper page
- wettergreen, 2005, Second experiments in the robotic investigation of life in the atacama desert of chile, ISAIRAS, 8
- 10.1109/ICCV.2003.1238308 · DOI
- 10.1109/AERO.2005.1559329 · DOI
- castan?o, 2004, Intensity-based rock detection for acquiring on-board rover science, Lunar and Planetary Science
- gor, 2000, Autonomous rock detection for mars terrain, Proceedings of AIAA Space 2001
- 10.1109/AERO.2005.1559329 · DOI
- tu, 2002, Image segmentation by data-driven markov chain monte carlo, IEEE Transactions on Pattern Analysis and Machine Intelligence, 24, 5
- mori, 2004, Recovering human body configurations: Combining segmentation and recognition, IEEE International Conference on Computer Vision
Metadata
- Authors
- Dunlop, H., Thompson, D. R., & Wettergreen, D.
- Affiliations
- Carnegie Mellon University (US)
- Venue
- 2007 IEEE Conference on Computer Vision and Pattern Recognition
- Publisher
- IEEE
- Published
- 2007-06
- Pages
- 1-7
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W1972373069
- Cited by
- 55
- References
- 22
- Citations by year
- 2026: 2 · 2025: 5 · 2024: 7 · 2023: 7 · 2022: 4 · 2021: 4 · 2020: 1 · 2019: 3 · 2018: 2 · 2017: 2 · 2016: 1 · 2015: 1 · 2013: 3 · 2012: 3
- FWCI
- 1.92
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings (publishedVersion)
- Funders
- Jet Propulsion Laboratory
- European Regional Development Fund
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Remote-Sensing Image Classification
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Medical Image Segmentation Techniques
- Keywords
- rock detection, multi-scale features, superpixel segmentation, region merging, texture features, shading, light direction, shape features, Mars Exploration Rover, planetary image analysis
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Multi-scale Features for Detection and Segmentation of Rocks in Mars Images. https://app.cochat.ai/papers/10.1109/cvpr.2007.383257
- The paper
- Dunlop, H., Thompson, D. R., & Wettergreen, D. (2007). Multi-scale Features for Detection and Segmentation of Rocks in Mars Images. 2007 IEEE Conference on Computer Vision and Pattern Recognition. https://doi.org/10.1109/cvpr.2007.383257
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.
