首页/论文/2003.03644

arXiv 2003.036442020-03cs.CVcs.LGcs.RO

Inferring Spatial Uncertainty in Object Detection

University of California, Berkeley（加州大学伯克利分校）；Robert Bosch GmbH（罗伯特·博世有限公司）；Ulm University（乌尔姆大学）

Zining Wang, Di Feng, Yiyang Zhou, Lars Rosenbaum, Fabian Timm, Klaus Dietmayer, Masayoshi Tomizuka, Wei Zhan

英文摘要：

The availability of real-world datasets is the prerequisite for developing object detection methods for autonomous driving. While ambiguity exists in object labels due to error-prone annotation process or sensor observation noises, current object detection datasets only provide deterministic annotations without considering their uncertainty. This precludes an in-depth evaluation among different object detection methods, especially for those that explicitly model predictive probability. In this work, we propose a generative model to estimate bounding box label uncertainties from LiDAR point clouds, and define a new representation of the probabilistic bounding box through spatial distribution. Comprehensive experiments show that the proposed model represents uncertainties commonly seen in driving scenarios. Based on the spatial distribution, we further propose an extension of IoU, called the Jaccard IoU (JIoU), as a new evaluation metric that incorporates label uncertainty. Experiments on the KITTI and the Waymo Open Datasets show that JIoU is superior to IoU when evaluating probabilistic object detectors.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

阅读原文

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

本文内容

英文摘要相关论文

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

继续探索

相关论文

Labels Are Not Perfect: Inferring Spatial Uncertainty in Object Detection

University of California, Berkeley（加州大学伯克利分校）；Ulm University（乌尔姆大学）；Robert Bosch GmbH（罗伯特·博世有限公司）

The availability of many real-world driving datasets is a key reason behind the recent progress of object detection algorithms in autonomous driving. However, there exist ambiguity or even failures in object labels due to error-prone annotation process or sensor observation noise. Current public object detection datasets only provide deterministic object labels without considering their inherent uncertainty, as does the common training process or evaluation metrics for object detectors. As a result, an in-depth evaluation among different object detection methods remains challenging, and the tr…

2020-12-18cs.CVcs.RO

Inferring Distributions Over Depth from a Single Image

Carnegie Mellon University（卡内基梅隆大学）；Argo AI

When building a geometric scene understanding system for autonomous vehicles, it is crucial to know when the system might fail. Most contemporary approaches cast the problem as depth regression, whose output is a depth value for each pixel. Such approaches cannot diagnose when failures might occur. One attractive alternative is a deep Bayesian network, which captures uncertainty in both model parameters and ambiguous sensor measurements. However, estimating uncertainties is often slow and the distributions are often limited to be uni-modal. In this paper, we recast the continuous problem of de…

2019-12-12cs.CVcs.RO

3秒前发生了什么？利用热成像推断过去

What Happened 3 Seconds Ago? Inferring the Past with Thermal Imaging

Tsinghua University（清华大学）；MIT（麻省理工学院）；Shanghai Qi Zhi Institute（上海期智研究院）

本文构建首个RGB-热成像人体运动分析数据集Thermal-IM，并提出三阶段神经网络，利用环境热残留推断过去人体姿态，显著降低任务不确定性。

2023-04-26cs.CV

Inferring bias and uncertainty in camera calibration

Robert Bosch GmbH（罗伯特·博世有限公司）；Karlsruher Institute of Technology (KIT)（卡尔斯鲁厄理工学院（KIT））

Accurate camera calibration is a precondition for many computer vision applications. Calibration errors, such as wrong model assumptions or imprecise parameter estimation, can deteriorate a system's overall performance, making the reliable detection and quantification of these errors critical. In this work, we introduce an evaluation scheme to capture the fundamental error sources in camera calibration: systematic errors (biases) and uncertainty (variance). The proposed bias detection method uncovers smallest systematic errors and thereby reveals imperfections of the calibration setup and prov…

2021-07-28cs.CV

Reducing Drift in Visual Odometry by Inferring Sun Direction Using a Bayesian Convolutional Neural Network

University of Toronto Institute for Aerospace Studies（多伦多大学航空航天研究所）

We present a method to incorporate global orientation information from the sun into a visual odometry pipeline using only the existing image stream, where the sun is typically not visible. We leverage recent advances in Bayesian Convolutional Neural Networks to train and implement a sun detection model that infers a three-dimensional sun direction vector from a single RGB image. Crucially, our method also computes a principled uncertainty associated with each prediction, using a Monte Carlo dropout scheme. We incorporate this uncertainty into a sliding window stereo visual odometry pipeline wh…

2019-08-18cs.CVcs.RO

Inferring a Third Spatial Dimension from 2D Histological Images

Eindhoven University of Technology（埃因霍温理工大学）

Histological images are obtained by transmitting light through a tissue specimen that has been stained in order to produce contrast. This process results in 2D images of the specimen that has a three-dimensional structure. In this paper, we propose a method to infer how the stains are distributed in the direction perpendicular to the surface of the slide for a given 2D image in order to obtain a 3D representation of the tissue. This inference is achieved by decomposition of the staining concentration maps under constraints that ensure realistic decomposition and reconstruction of the original …

2018-01-10cs.CV

更多相关论文收起更多论文

Uncertainty-Aware Vehicle Orientation Estimation for Joint Detection-Prediction Models

Uber Advanced Technologies Group（优步先进技术集团）

Object detection is a critical component of a self-driving system, tasked with inferring the current states of the surrounding traffic actors. While there exist a number of studies on the problem of inferring the position and shape of vehicle actors, understanding actors' orientation remains a challenge for existing state-of-the-art detectors. Orientation is an important property for downstream modules of an autonomous system, particularly relevant for motion prediction of stationary or reversing actors where current approaches struggle. We focus on this task and present a method that extends …

2020-11-05cs.CV

Learning a Model for Inferring a Spatial Road Lane Network Graph using Self-Supervision

Tier IV Inc.（Tier IV公司）；Institute of Innovation for Future Society, Nagoya University（名古屋大学未来社会创新研究所）；Graduate School of Informatics, Nagoya University（名古屋大学信息学研究科）

Interconnected road lanes are a central concept for navigating urban roads. Currently, most autonomous vehicles rely on preconstructed lane maps as designing an algorithmic model is difficult. However, the generation and maintenance of such maps is costly and hinders large-scale adoption of autonomous vehicle technology. This paper presents the first self-supervised learning method to train a model to infer a spatially grounded lane-level road network graph based on a dense segmented representation of the road scene generated from onboard sensors. A formal road lane network model is presented …

2021-07-05cs.CVcs.LGstat.ML

ProbNeRF: Uncertainty-Aware Inference of 3D Shapes from 2D Images

Google Research（谷歌研究院）；MIT（麻省理工学院）

The problem of inferring object shape from a single 2D image is underconstrained. Prior knowledge about what objects are plausible can help, but even given such prior knowledge there may still be uncertainty about the shapes of occluded parts of objects. Recently, conditional neural radiance field (NeRF) models have been developed that can learn to infer good point estimates of 3D models from single 2D images. The problem of inferring uncertainty estimates for these models has received less attention. In this work, we propose probabilistic NeRF (ProbNeRF), a model and inference strategy for le…

2022-10-27cs.CVcs.LG

Sequential Image-based Attention Network for Inferring Force Estimation without Haptic Sensor

Ajou University（亚洲大学）；Dongguk University（东国大学）

Humans can infer approximate interaction force between objects from only vision information because we already have learned it through experiences. Based on this idea, we propose a recurrent convolutional neural network-based method using sequential images for inferring interaction force without using a haptic sensor. For training and validating deep learning methods, we collected a large number of images and corresponding interaction forces through an electronic motor-based device. To concentrate on changing shapes of a target object by the external force in images, we propose a sequential im…

2019-10-20cs.CV

Human 3D keypoints via spatial uncertainty modeling

Google Research（谷歌研究院）；NYU（纽约大学）；Stanford University（斯坦福大学）；NVIDIA（英伟达）；University of Toronto（多伦多大学）

We introduce a technique for 3D human keypoint estimation that directly models the notion of spatial uncertainty of a keypoint. Our technique employs a principled approach to modelling spatial uncertainty inspired from techniques in robust statistics. Furthermore, our pipeline requires no 3D ground truth labels, relying instead on (possibly noisy) 2D image-level keypoints. Our method achieves near state-of-the-art performance on Human3.6m while being efficient to evaluate and straightforward to

2020-12-18cs.CV

Blurs Behave Like Ensembles: Spatial Smoothings to Improve Accuracy, Uncertainty, and Robustness

NAVER AI Lab（NAVER人工智能实验室）；Yonsei University（延世大学）

Neural network ensembles, such as Bayesian neural networks (BNNs), have shown success in the areas of uncertainty estimation and robustness. However, a crucial challenge prohibits their use in practice. BNNs require a large number of predictions to produce reliable results, leading to a significant increase in computational cost. To alleviate this issue, we propose spatial smoothing, a method that spatially ensembles neighboring feature map points of convolutional neural networks. By simply adding a few blur layers to the models, we empirically show that spatial smoothing improves accuracy, un…

2022-07-14cs.AIcs.CVcs.LG

面向图像复原问题的具有空间相关性的主成分不确定性量化

Principal Uncertainty Quantification with Spatial Correlation for Image Restoration Problems

Verily Life Sciences（Verily生命科学公司）；Technion - Israel Institute of Technology（以色列理工学院）

针对图像逆问题中逐像素不确定性忽略空间相关、区域体积过大的问题，提出PUQ，利用生成模型和后验主成分构建高置信、更紧凑的不确定性区域。

2024-01-20cs.CV

无需 ever 看到一个推断组合性4D场景

Inferring Compositional 4D Scenes without Ever Seeing One

INSAIT, Sofia University “St. Kliment Ohridski”（INSAIT，索非亚大学“圣克莱门特·奥赫里德斯基”）

COM4D通过设计空间和时间注意力训练，仅用静态多物体或动态单物体监督，一致预测4D/3D对象的结构和时空配置，无需4D组合训练数据，实现从单目视频重建完整持久的4D场景。

2026-03-25cs.CV

基于空间与尺度不确定性感知网络的细长生理结构分割

Elongated Physiological Structure Segmentation via Spatial and Scale Uncertainty-aware Network

University of Nottingham Ningbo China（宁波诺丁汉大学）；Southern University of Science and Technology（南方科技大学）；Agency for Science, Technology and Research (A*STAR)（新加坡科技研究局）；Institute of High Performance Computing（高性能计算研究所）；Tomey Corporation（多美株式会社）

本文提出SSU-Net，通过空间与尺度不确定性感知模块突出模糊区域并融合层次结构上下文，在角膜内皮细胞和视网膜血管分割中取得最优且更鲁棒的性能。

2023-05-30cs.CVeess.IV

A spatial compositional model (SCM) for linear unmixing and endmember uncertainty estimation

University of Florida（佛罗里达大学）

The normal compositional model (NCM) has been extensively used in hyperspectral unmixing. However, most of the previous research has focused on estimation of endmembers and/or their variability. Also, little work has employed spatial information in NCM. In this paper, we show that NCM can be used for calculating the uncertainty of the estimated endmembers with spatial priors incorporated for better unmixing. This results in a spatial compositional model (SCM) which features (i) spatial priors that force neighboring abundances to be similar based on their pixel similarity and (ii) a posterior t…

2015-09-30cs.CV

RaUF: 学习雷达的时空不确定性场

RaUF: Learning the Spatial Uncertainty Field of Radar

Huazhong University of Science and Technology（华中科技大学）；Wuhan University（武汉大学）

RaUF通过学习雷达测量的各向异性特性，解决方位模糊和虚假回波问题，提升空间检测的可靠性与不确定性校准。

2026-03-01cs.CV