Proprioception Is All You Need: Terrain Classification for Boreal Forests

• URL: http://arxiv.org/abs/2403.16877v2
• Date: Fri, 27 Sep 2024 17:14:26 GMT
• Title: Proprioception Is All You Need: Terrain Classification for Boreal Forests
• Authors: Damien LaRocque, William Guimont-Martin, David-Alexandre Duclos, Philippe Giguère, François Pomerleau,
• Abstract summary: BorealTC is a publicly available dataset for proprioceptive-based terrain classification (TC) Recorded with a Husky A200, our dataset contains 116 min of Inertial Measurement Unit (IMU), motor current, and wheel odometry data. We show that the combination of two TC datasets yields a latent space that can be interpreted with the properties of the terrains.
• Score: 4.703814941476968
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Recent works in field robotics highlighted the importance of resiliency against different types of terrains. Boreal forests, in particular, are home to many mobility-impeding terrains that should be considered for off-road autonomous navigation. Also, being one of the largest land biomes on Earth, boreal forests are an area where autonomous vehicles are expected to become increasingly common. In this paper, we address this issue by introducing BorealTC, a publicly available dataset for proprioceptive-based terrain classification (TC). Recorded with a Husky A200, our dataset contains 116 min of Inertial Measurement Unit (IMU), motor current, and wheel odometry data, focusing on typical boreal forest terrains, notably snow, ice, and silty loam. Combining our dataset with another dataset from the state-of-the-art, we evaluate both a Convolutional Neural Network (CNN) and the novel state space model (SSM)-based Mamba architecture on a TC task. Interestingly, we show that while CNN outperforms Mamba on each separate dataset, Mamba achieves greater accuracy when trained on a combination of both. In addition, we demonstrate that Mamba's learning capacity is greater than a CNN for increasing amounts of data. We show that the combination of two TC datasets yields a latent space that can be interpreted with the properties of the terrains. We also discuss the implications of merging datasets on classification. Our source code and dataset are publicly available online: https://github.com/norlab-ulaval/BorealTC.

Related papers

• Scaling Up Forest Vision with Synthetic Data [0.0]
  Accurate tree segmentation is a key step in extracting individual tree metrics from forest laser scans.<n>In place of expensive field data collection and annotation, we use synthetic data during pretraining.<n>We have produced a comprehensive, diverse, annotated 3D forest dataset on an unprecedented scale.
  arXiv  Detail & Related papers  (2025-09-14T10:00:59Z)
• Earth Observation Foundation Model PhilEO: Pretraining on the MajorTOM and FastTOM Datasets [25.69468673907913]
  We train our models on the pretraining dataset MajorTOM 23TB which includes all regions.<n>The additional data of oceans and ice do not decrease the performance on land-focused downstream tasks.<n>The second contribution is the exploration of U-Net Convolutional Neural Network (CNN), Vision Transformers (ViT), and Mamba State-Space Models (SSM) as FMs.
  arXiv  Detail & Related papers  (2025-06-17T17:58:08Z)
• RemoteSAM: Towards Segment Anything for Earth Observation [29.707796048411705]
  We aim to develop a robust yet flexible visual foundation model for Earth observation.<n>It should possess strong capabilities in recognizing and localizing diverse visual targets.<n>We present RemoteSAM, a foundation model that establishes new SoTA on several earth observation perception benchmarks.
  arXiv  Detail & Related papers  (2025-05-23T15:27:57Z)
• OAM-TCD: A globally diverse dataset of high-resolution tree cover maps [8.336960607169175]
  We present a novel open-access dataset for individual tree crown delineation (TCD) in high-resolution aerial imagery sourced from OpenMap (OAM) Our dataset, OAM-TCD, comprises 5072 2048x2048px images at 10 cm/px resolution with associated human-labeled instance masks for over 280k individual and 56k groups of trees. Using our dataset, we train reference instance and semantic segmentation models that compare favorably to existing state-of-the-art models.
  arXiv  Detail & Related papers  (2024-07-16T14:11:29Z)
• UniTraj: A Unified Framework for Scalable Vehicle Trajectory Prediction [93.77809355002591]
  We introduce UniTraj, a comprehensive framework that unifies various datasets, models, and evaluation criteria. We conduct extensive experiments and find that model performance significantly drops when transferred to other datasets. We provide insights into dataset characteristics to explain these findings.
  arXiv  Detail & Related papers  (2024-03-22T10:36:50Z)
• Training point-based deep learning networks for forest segmentation with synthetic data [0.0]
  We develop a realistic simulator that procedurally generates synthetic forest scenes. We conduct a comparative study of different state-of-the-art point-based deep learning networks for forest segmentation.
  arXiv  Detail & Related papers  (2024-03-21T04:01:26Z)
• Kick Back & Relax++: Scaling Beyond Ground-Truth Depth with SlowTV & CribsTV [50.616892315086574]
  This paper proposes two novel datasets: SlowTV and CribsTV. These are large-scale datasets curated from publicly available YouTube videos, containing a total of 2M training frames. We leverage these datasets to tackle the challenging task of zero-shot generalization.
  arXiv  Detail & Related papers  (2024-03-03T17:29:03Z)
• SegmentAnyTree: A sensor and platform agnostic deep learning model for tree segmentation using laser scanning data [15.438892555484616]
  This research advances individual tree crown (ITC) segmentation in lidar data, using a deep learning model applicable to various laser scanning types. It addresses the challenge of transferability across different data characteristics in 3D forest scene analysis. The model, based on PointGroup architecture, is a 3D CNN with separate heads for semantic and instance segmentation.
  arXiv  Detail & Related papers  (2024-01-28T19:47:17Z)
• Argoverse 2: Next Generation Datasets for Self-Driving Perception and Forecasting [64.7364925689825]
  Argoverse 2 (AV2) is a collection of three datasets for perception and forecasting research in the self-driving domain. The Lidar dataset contains 20,000 sequences of unlabeled lidar point clouds and map-aligned pose. The Motion Forecasting dataset contains 250,000 scenarios mined for interesting and challenging interactions between the autonomous vehicle and other actors in each local scene.
  arXiv  Detail & Related papers  (2023-01-02T00:36:22Z)
• Tree Detection and Diameter Estimation Based on Deep Learning [0.0]
  Tree perception is an essential building block toward autonomous forestry operations. Deep neural network models trained on our datasets achieve a precision of 90.4% for tree detection. Results offer promising avenues toward autonomous tree felling operations.
  arXiv  Detail & Related papers  (2022-10-31T15:51:32Z)
• Bamboo: Building Mega-Scale Vision Dataset Continually with Human-Machine Synergy [69.07918114341298]
  Large-scale datasets play a vital role in computer vision. Existing datasets are either collected according to label systems or blindly without differentiation to samples, making them inefficient and unscalable. We advocate building a high-quality vision dataset actively annotated and continually on a comprehensive label system.
  arXiv  Detail & Related papers  (2022-03-15T13:01:00Z)
• MSeg: A Composite Dataset for Multi-domain Semantic Segmentation [100.17755160696939]
  We present MSeg, a composite dataset that unifies semantic segmentation datasets from different domains. We reconcile the generalization and bring the pixel-level annotations into alignment by relabeling more than 220,000 object masks in more than 80,000 images. A model trained on MSeg ranks first on the WildDash-v1 leaderboard for robust semantic segmentation, with no exposure to WildDash data during training.
  arXiv  Detail & Related papers  (2021-12-27T16:16:35Z)
• Towards Optimal Strategies for Training Self-Driving Perception Models in Simulation [98.51313127382937]
  We focus on the use of labels in the synthetic domain alone. Our approach introduces both a way to learn neural-invariant representations and a theoretically inspired view on how to sample the data from the simulator. We showcase our approach on the bird's-eye-view vehicle segmentation task with multi-sensor data.
  arXiv  Detail & Related papers  (2021-11-15T18:37:43Z)
• Very High Resolution Land Cover Mapping of Urban Areas at Global Scale with Convolutional Neural Networks [0.0]
  This paper describes a methodology to produce a 7-classes land cover map of urban areas from very high resolution images and limited noisy labeled data. We created a training dataset on a few areas of interest aggregating databases, semi-automatic classification, and manual annotation to get a complete ground truth in each class. The final product is a highly valuable land cover map computed from model predictions stitched together, binarized, and refined before vectorization.
  arXiv  Detail & Related papers  (2020-05-12T10:03:20Z)

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.