Machine Vision based Sample-Tube Localization for Mars Sample Return
- URL: http://arxiv.org/abs/2103.09942v1
- Date: Wed, 17 Mar 2021 23:09:28 GMT
- Title: Machine Vision based Sample-Tube Localization for Mars Sample Return
- Authors: Shreyansh Daftry, Barry Ridge, William Seto, Tu-Hoa Pham, Peter
Ilhardt, Gerard Maggiolino, Mark Van der Merwe, Alex Brinkman, John Mayo,
Eric Kulczyski and Renaud Detry
- Abstract summary: A potential Mars Sample Return (MSR) architecture is being jointly studied by NASA and ESA.
In this paper, we focus on the fetch part of the MSR, and more specifically the problem of autonomously detecting and localizing sample tubes deposited on the Martian surface.
We study two machine-vision based approaches: First, a geometry-driven approach based on template matching that uses hard-coded filters and a 3D shape model of the tube; and second, a data-driven approach based on convolutional neural networks (CNNs) and learned features.
- Score: 3.548901442158138
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: A potential Mars Sample Return (MSR) architecture is being jointly studied by
NASA and ESA. As currently envisioned, the MSR campaign consists of a series of
3 missions: sample cache, fetch and return to Earth. In this paper, we focus on
the fetch part of the MSR, and more specifically the problem of autonomously
detecting and localizing sample tubes deposited on the Martian surface. Towards
this end, we study two machine-vision based approaches: First, a
geometry-driven approach based on template matching that uses hard-coded
filters and a 3D shape model of the tube; and second, a data-driven approach
based on convolutional neural networks (CNNs) and learned features.
Furthermore, we present a large benchmark dataset of sample-tube images,
collected in representative outdoor environments and annotated with ground
truth segmentation masks and locations. The dataset was acquired systematically
across different terrain, illumination conditions and dust-coverage; and
benchmarking was performed to study the feasibility of each approach, their
relative strengths and weaknesses, and robustness in the presence of adverse
environmental conditions.
Related papers
- UniMODE: Unified Monocular 3D Object Detection [70.27631528933482]
We build a detector based on the bird's-eye-view (BEV) detection paradigm.
We propose an uneven BEV grid design to handle the convergence instability caused by the challenges.
A unified detector UniMODE is derived, which surpasses the previous state-of-the-art on the challenging Omni3D dataset.
arXiv Detail & Related papers (2024-02-28T18:59:31Z) - Self-supervised Feature Adaptation for 3D Industrial Anomaly Detection [59.41026558455904]
We focus on multi-modal anomaly detection. Specifically, we investigate early multi-modal approaches that attempted to utilize models pre-trained on large-scale visual datasets.
We propose a Local-to-global Self-supervised Feature Adaptation (LSFA) method to finetune the adaptors and learn task-oriented representation toward anomaly detection.
arXiv Detail & Related papers (2024-01-06T07:30:41Z) - SSCBench: Monocular 3D Semantic Scene Completion Benchmark in Street
Views [89.8436375840446]
SSCBench is a benchmark that integrates scenes from widely used automotive datasets.
We benchmark models using monocular, trinocular, and cloud input to assess the performance gap.
We have unified semantic labels across diverse datasets to simplify cross-domain generalization testing.
arXiv Detail & Related papers (2023-06-15T09:56:33Z) - MV-JAR: Masked Voxel Jigsaw and Reconstruction for LiDAR-Based
Self-Supervised Pre-Training [58.07391711548269]
Masked Voxel Jigsaw and Reconstruction (MV-JAR) method for LiDAR-based self-supervised pre-training.
Masked Voxel Jigsaw and Reconstruction (MV-JAR) method for LiDAR-based self-supervised pre-training.
arXiv Detail & Related papers (2023-03-23T17:59:02Z) - City-scale Incremental Neural Mapping with Three-layer Sampling and
Panoptic Representation [5.682979644056021]
We build a city-scale continual neural mapping system with a panoptic representation that consists of environment-level and instance-level modelling.
Given a stream of sparse LiDAR point cloud, it maintains a dynamic generative model that maps 3D coordinates to signed distance field (SDF) values.
To realize high fidelity mapping of instance under incomplete observation, category-specific prior is introduced to better model the geometric details.
arXiv Detail & Related papers (2022-09-28T13:14:40Z) - Hardware-accelerated Mars Sample Localization via deep transfer learning
from photorealistic simulations [1.3075880857448061]
The goal of the Mars Sample Return campaign is to collect soil samples from the surface of Mars and return them to Earth for further study.
It is expected the Sample Fetch Rover will be in charge of localizing and gathering up to 35 sample tubes over 150 Martian sols.
This work proposes a novel approach for the autonomous detection and pose estimation of the sample tubes.
arXiv Detail & Related papers (2022-06-06T14:05:25Z) - TerrainMesh: Metric-Semantic Terrain Reconstruction from Aerial Images
Using Joint 2D-3D Learning [20.81202315793742]
This paper develops a joint 2D-3D learning approach to reconstruct a local metric-semantic mesh at each camera maintained by a visual odometry algorithm.
The mesh can be assembled into a global environment model to capture the terrain topology and semantics during online operation.
arXiv Detail & Related papers (2022-04-23T05:18:39Z) - A spatio-temporal LSTM model to forecast across multiple temporal and
spatial scales [0.0]
This paper presents a novel-temporal LSTM (SPATIAL) architecture for time series forecasting applied to environmental datasets.
The framework was evaluated across multiple sensors and for three different oceanic variables: current speed, temperature, and dissolved oxygen.
arXiv Detail & Related papers (2021-08-26T16:07:13Z) - Campus3D: A Photogrammetry Point Cloud Benchmark for Hierarchical
Understanding of Outdoor Scene [76.4183572058063]
We present a richly-annotated 3D point cloud dataset for multiple outdoor scene understanding tasks.
The dataset has been point-wisely annotated with both hierarchical and instance-based labels.
We formulate a hierarchical learning problem for 3D point cloud segmentation and propose a measurement evaluating consistency across various hierarchies.
arXiv Detail & Related papers (2020-08-11T19:10:32Z) - Benchmarking Unsupervised Object Representations for Video Sequences [111.81492107649889]
We compare the perceptual abilities of four object-centric approaches: ViMON, OP3, TBA and SCALOR.
Our results suggest that the architectures with unconstrained latent representations learn more powerful representations in terms of object detection, segmentation and tracking.
Our benchmark may provide fruitful guidance towards learning more robust object-centric video representations.
arXiv Detail & Related papers (2020-06-12T09:37:24Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.