Semantic and Feature Guided Uncertainty Quantification of Visual Localization for Autonomous Vehicles

• URL: http://arxiv.org/abs/2506.15851v1
• Date: Wed, 18 Jun 2025 20:00:36 GMT
• Title: Semantic and Feature Guided Uncertainty Quantification of Visual Localization for Autonomous Vehicles
• Authors: Qiyuan Wu, Mark Campbell,
• Abstract summary: This paper develops an uncertainty quantification approach in the context of visual localization for autonomous driving.<n>Key to our approach is to learn the measurement uncertainty using light-weight sensor error model, which maps both image feature and semantic information to 2-dimensional error distribution.<n>We demonstrate the accuracy of our uncertainty prediction framework using the Ithaca365 dataset, which includes variations in lighting and weather.
• Score: 2.4171019220503402
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The uncertainty quantification of sensor measurements coupled with deep learning networks is crucial for many robotics systems, especially for safety-critical applications such as self-driving cars. This paper develops an uncertainty quantification approach in the context of visual localization for autonomous driving, where locations are selected based on images. Key to our approach is to learn the measurement uncertainty using light-weight sensor error model, which maps both image feature and semantic information to 2-dimensional error distribution. Our approach enables uncertainty estimation conditioned on the specific context of the matched image pair, implicitly capturing other critical, unannotated factors (e.g., city vs highway, dynamic vs static scenes, winter vs summer) in a latent manner. We demonstrate the accuracy of our uncertainty prediction framework using the Ithaca365 dataset, which includes variations in lighting and weather (sunny, night, snowy). Both the uncertainty quantification of the sensor+network is evaluated, along with Bayesian localization filters using unique sensor gating method. Results show that the measurement error does not follow a Gaussian distribution with poor weather and lighting conditions, and is better predicted by our Gaussian Mixture model.

Related papers

• Uncertainty-Aware AB3DMOT by Variational 3D Object Detection [74.8441634948334]
  Uncertainty estimation is an effective tool to provide statistically accurate predictions. In this paper, we propose a Variational Neural Network-based TANet 3D object detector to generate 3D object detections with uncertainty.
  arXiv  Detail & Related papers  (2023-02-12T14:30:03Z)
• NUQ: Nonparametric Uncertainty Quantification for Deterministic Neural Networks [151.03112356092575]
  We show the principled way to measure the uncertainty of predictions for a classifier based on Nadaraya-Watson's nonparametric estimate of the conditional label distribution. We demonstrate the strong performance of the method in uncertainty estimation tasks on a variety of real-world image datasets.
  arXiv  Detail & Related papers  (2022-02-07T12:30:45Z)
• Multi-Camera Sensor Fusion for Visual Odometry using Deep Uncertainty Estimation [34.8860186009308]
  We propose a deep sensor fusion framework which estimates vehicle motion using both pose and uncertainty estimations from multiple on-board cameras. We evaluate our approach on the publicly available, large scale autonomous vehicle dataset, nuScenes.
  arXiv  Detail & Related papers  (2021-12-23T19:44:45Z)
• CertainNet: Sampling-free Uncertainty Estimation for Object Detection [65.28989536741658]
  Estimating the uncertainty of a neural network plays a fundamental role in safety-critical settings. In this work, we propose a novel sampling-free uncertainty estimation method for object detection. We call it CertainNet, and it is the first to provide separate uncertainties for each output signal: objectness, class, location and size.
  arXiv  Detail & Related papers  (2021-10-04T17:59:31Z)
• PDC-Net+: Enhanced Probabilistic Dense Correspondence Network [161.76275845530964]
  Enhanced Probabilistic Dense Correspondence Network, PDC-Net+, capable of estimating accurate dense correspondences. We develop an architecture and an enhanced training strategy tailored for robust and generalizable uncertainty prediction. Our approach obtains state-of-the-art results on multiple challenging geometric matching and optical flow datasets.
  arXiv  Detail & Related papers  (2021-09-28T17:56:41Z)
• Prediction Surface Uncertainty Quantification in Object Detection Models for Autonomous Driving [5.784950275336468]
  Object detection in autonomous cars is commonly based on camera images and Lidar inputs, which are often used to train prediction models. We propose a novel method called PURE (Prediction sURface uncErtainty) for measuring prediction uncertainty of such regression models.
  arXiv  Detail & Related papers  (2021-07-11T08:31:15Z)
• Learning Uncertainty For Safety-Oriented Semantic Segmentation In Autonomous Driving [77.39239190539871]
  We show how uncertainty estimation can be leveraged to enable safety critical image segmentation in autonomous driving. We introduce a new uncertainty measure based on disagreeing predictions as measured by a dissimilarity function. We show experimentally that our proposed approach is much less computationally intensive at inference time than competing methods.
  arXiv  Detail & Related papers  (2021-05-28T09:23:05Z)
• Learning Accurate Dense Correspondences and When to Trust Them [161.76275845530964]
  We aim to estimate a dense flow field relating two images, coupled with a robust pixel-wise confidence map. We develop a flexible probabilistic approach that jointly learns the flow prediction and its uncertainty. Our approach obtains state-of-the-art results on challenging geometric matching and optical flow datasets.
  arXiv  Detail & Related papers  (2021-01-05T18:54:11Z)
• Uncertainty Intervals for Graph-based Spatio-Temporal Traffic Prediction [0.0]
  We propose a Spatio-Temporal neural network that is trained to estimate a density given the measurements of previous timesteps, conditioned on a quantile. Our method of density estimation is fully parameterised by our neural network and does not use a likelihood approximation internally. This approach produces uncertainty estimates without the need to sample during inference, such as in Monte Carlo Dropout.
  arXiv  Detail & Related papers  (2020-12-09T18:02:26Z)
• Camera-Lidar Integration: Probabilistic sensor fusion for semantic mapping [8.18198392834469]
  An automated vehicle must be able to perceive and recognise object/obstacles in a three-dimensional world while navigating in a constantly changing environment. We present a probabilistic pipeline that incorporates uncertainties from the sensor readings (cameras, lidar, IMU and wheel encoders), compensation for the motion of the vehicle, and label probabilities for the semantic images.
  arXiv  Detail & Related papers  (2020-07-09T07:59:39Z)

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.