Segment-Level Road Obstacle Detection Using Visual Foundation Model Priors and Likelihood Ratios

• URL: http://arxiv.org/abs/2412.05707v2
• Date: Sun, 19 Jan 2025 00:37:27 GMT
• Title: Segment-Level Road Obstacle Detection Using Visual Foundation Model Priors and Likelihood Ratios
• Authors: Youssef Shoeb, Nazir Nayal, Azarm Nowzard, Fatma Güney, Hanno Gottschalk,
• Abstract summary: Current road obstacle detection methods assign a score to each pixel and apply a threshold to generate final predictions. We propose a novel method that leverages segment-level features from visual foundation models and likelihood ratios to predict road obstacles directly. By focusing on segments rather than individual pixels, our approach enhances detection accuracy, reduces false positives, and offers increased robustness to scene variability.
• Score: 4.578773000079989
• License:
• Abstract: Detecting road obstacles is essential for autonomous vehicles to navigate dynamic and complex traffic environments safely. Current road obstacle detection methods typically assign a score to each pixel and apply a threshold to generate final predictions. However, selecting an appropriate threshold is challenging, and the per-pixel classification approach often leads to fragmented predictions with numerous false positives. In this work, we propose a novel method that leverages segment-level features from visual foundation models and likelihood ratios to predict road obstacles directly. By focusing on segments rather than individual pixels, our approach enhances detection accuracy, reduces false positives, and offers increased robustness to scene variability. We benchmark our approach against existing methods on the RoadObstacle and LostAndFound datasets, achieving state-of-the-art performance without needing a predefined threshold.

Related papers

• A Multi-Loss Strategy for Vehicle Trajectory Prediction: Combining Off-Road, Diversity, and Directional Consistency Losses [68.68514648185828]
  Trajectory prediction is essential for the safety and efficiency of planning in autonomous vehicles. Current models often fail to fully capture complex traffic rules and the complete range of potential vehicle movements. This study introduces three novel loss functions: Offroad Loss, Direction Consistency Error, and Diversity Loss.
  arXiv  Detail & Related papers  (2024-11-29T14:47:08Z)
• REG: Refined Generalized Focal Loss for Road Asset Detection on Thai Highways Using Vision-Based Detection and Segmentation Models [0.0]
  This paper introduces a novel framework for detecting and segmenting critical road assets on Thai highways. Integrated into state-of-the-art vision-based detection and segmentation models, the proposed method effectively addresses class imbalance and the challenges of localizing small, underrepresented road elements.
  arXiv  Detail & Related papers  (2024-09-15T22:04:33Z)
• Unsupervised Domain Adaptation for Self-Driving from Past Traversal Features [69.47588461101925]
  We propose a method to adapt 3D object detectors to new driving environments. Our approach enhances LiDAR-based detection models using spatial quantized historical features. Experiments on real-world datasets demonstrate significant improvements.
  arXiv  Detail & Related papers  (2023-09-21T15:00:31Z)
• View Consistent Purification for Accurate Cross-View Localization [59.48131378244399]
  This paper proposes a fine-grained self-localization method for outdoor robotics. The proposed method addresses limitations in existing cross-view localization methods. It is the first sparse visual-only method that enhances perception in dynamic environments.
  arXiv  Detail & Related papers  (2023-08-16T02:51:52Z)
• Improving Online Lane Graph Extraction by Object-Lane Clustering [106.71926896061686]
  We propose an architecture and loss formulation to improve the accuracy of local lane graph estimates. The proposed method learns to assign the objects to centerlines by considering the centerlines as cluster centers. We show that our method can achieve significant performance improvements by using the outputs of existing 3D object detection methods.
  arXiv  Detail & Related papers  (2023-07-20T15:21:28Z)
• Unsupervised Adaptation from Repeated Traversals for Autonomous Driving [54.59577283226982]
  Self-driving cars must generalize to the end-user's environment to operate reliably. One potential solution is to leverage unlabeled data collected from the end-users' environments. There is no reliable signal in the target domain to supervise the adaptation process. We show that this simple additional assumption is sufficient to obtain a potent signal that allows us to perform iterative self-training of 3D object detectors on the target domain.
  arXiv  Detail & Related papers  (2023-03-27T15:07:55Z)
• Spatio-Temporal Context Modeling for Road Obstacle Detection [12.464149169670735]
  A data-driven context-temporal model of the driving scene is constructed with the layouts of the training data. Obstacles are detected via state-of-the-art object detection algorithms, and the results are combined with the generated scene.
  arXiv  Detail & Related papers  (2023-01-19T07:06:35Z)
• Perspective Aware Road Obstacle Detection [104.57322421897769]
  We show that road obstacle detection techniques ignore the fact that, in practice, the apparent size of the obstacles decreases as their distance to the vehicle increases. We leverage this by computing a scale map encoding the apparent size of a hypothetical object at every image location. We then leverage this perspective map to generate training data by injecting onto the road synthetic objects whose size corresponds to the perspective foreshortening.
  arXiv  Detail & Related papers  (2022-10-04T17:48:42Z)
• An Active and Contrastive Learning Framework for Fine-Grained Off-Road Semantic Segmentation [7.035838394813961]
  Off-road semantic segmentation with fine-grained labels is necessary for autonomous vehicles to understand driving scenes. Fine-grained semantic segmentation in off-road scenes usually has no unified category definition due to ambiguous nature environments. This research proposes an active and contrastive learning-based method that does not rely on pixel-wise labels.
  arXiv  Detail & Related papers  (2022-02-18T03:16:31Z)
• Domain Adaptation for Outdoor Robot Traversability Estimation from RGB data with Safety-Preserving Loss [12.697106921197701]
  We present an approach based on deep learning to estimate and anticipate the traversing score of different routes in the field of view of an on-board RGB camera. We then enhance the model's capabilities by addressing domain shifts through gradient-reversal unsupervised adaptation. Experimental results show that our approach is able to satisfactorily identify traversable areas and to generalize to unseen locations.
  arXiv  Detail & Related papers  (2020-09-16T09:19:33Z)
• Unsupervised Pixel-level Road Defect Detection via Adversarial Image-to-Frequency Transform [8.644679871804872]
  We propose an unsupervised approach to detecting road defects, using Adversarial Image-to-Frequency Transform (AIFT) AIFT adopts the unsupervised manner and adversarial learning in deriving the defect detection model, so AIFT does not need annotations for road pavement defects.
  arXiv  Detail & Related papers  (2020-01-30T04:50:00Z)

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.