Surround-view Fisheye BEV-Perception for Valet Parking: Dataset, Baseline and Distortion-insensitive Multi-task Framework

• URL: http://arxiv.org/abs/2212.04111v1
• Date: Thu, 8 Dec 2022 07:06:08 GMT
• Title: Surround-view Fisheye BEV-Perception for Valet Parking: Dataset, Baseline and Distortion-insensitive Multi-task Framework
• Authors: Zizhang Wu, Yuanzhu Gan, Xianzhi Li, Yunzhe Wu, Xiaoquan Wang, Tianhao Xu, Fan Wang
• Abstract summary: Surround-view fisheye perception under valet parking scenes is fundamental and crucial in autonomous driving. We introduce a new large-scale fisheye dataset called Fisheye Parking dataset. We also propose our real-time distortion-insensitive multi-task framework Fisheye Perception Network (FPNet)
• Score: 14.165082243555988
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Surround-view fisheye perception under valet parking scenes is fundamental and crucial in autonomous driving. Environmental conditions in parking lots perform differently from the common public datasets, such as imperfect light and opacity, which substantially impacts on perception performance. Most existing networks based on public datasets may generalize suboptimal results on these valet parking scenes, also affected by the fisheye distortion. In this article, we introduce a new large-scale fisheye dataset called Fisheye Parking Dataset(FPD) to promote the research in dealing with diverse real-world surround-view parking cases. Notably, our compiled FPD exhibits excellent characteristics for different surround-view perception tasks. In addition, we also propose our real-time distortion-insensitive multi-task framework Fisheye Perception Network (FPNet), which improves the surround-view fisheye BEV perception by enhancing the fisheye distortion operation and multi-task lightweight designs. Extensive experiments validate the effectiveness of our approach and the dataset's exceptional generalizability.

Related papers

• Rethinking Camera Choice: An Empirical Study on Fisheye Camera Properties in Robotic Manipulation [53.27191803311681]
  We rigorously analyze the properties of wrist-mounted fisheye cameras for imitation learning.<n>Fisheye-trained policies unlock superior scene generalization when trained with sufficient environmental diversity.<n>Our findings provide concrete, actionable guidance for the large-scale collection and effective use of fisheye datasets in robotic learning.
  arXiv  Detail & Related papers  (2026-03-02T18:00:37Z)
• A Unified Detection Pipeline for Robust Object Detection in Fisheye-Based Traffic Surveillance [7.670666668651702]
  Fisheye cameras offer an efficient solution for wide-area traffic surveillance by capturing large fields of view from a single vantage point.<n>The strong radial distortion and nonuniform resolution inherent in fisheye imagery introduce substantial challenges for standard object detectors.<n>We present a detection framework designed to operate robustly under these conditions.
  arXiv  Detail & Related papers  (2025-10-22T20:38:34Z)
• FishBEV: Distortion-Resilient Bird's Eye View Segmentation with Surround-View Fisheye Cameras [12.001699443894504]
  We propose FishBEV, a novel BEV segmentation framework specifically tailored for fisheye cameras.<n>This framework introduces three complementary innovations, including a Distortion-Resilient Multi-scale Extraction (DRME) backbone that learns robust features under distortion while preserving scale consistency.<n>Experiments on the Synwoodscapes dataset demonstrate that FishBEV consistently outperforms SOTA baselines, regarding the performance evaluation of FishBEV on the surround-view fisheye BEV segmentation tasks.
  arXiv  Detail & Related papers  (2025-09-17T04:26:36Z)
• Advancing Real-World Parking Slot Detection with Large-Scale Dataset and Semi-Supervised Baseline [65.25540269603553]
  This study focuses on parking slot detection using surround-view cameras, which offer a comprehensive bird's-eye view of the parking environment.<n>We first construct a large-scale parking slot detection dataset (CRPS-D), which includes various lighting distributions, diverse weather conditions, and challenging parking slot variants.<n>We develop a semi-supervised baseline for parking slot detection, termed SS-PSD, to further improve performance by exploiting unlabeled data.
  arXiv  Detail & Related papers  (2025-09-16T14:50:19Z)
• Surround-View Fisheye Optics in Computer Vision and Simulation: Survey and Challenges [1.2673797373220104]
  The automotive industry has advanced in applying state-of-the-art computer vision to enhance road safety and provide automated driving functionality. One crucial challenge in surround-view cameras is the strong optical aberrations of the fisheye camera. A comprehensive dataset is needed for testing safety-critical scenarios in vehicle automation.
  arXiv  Detail & Related papers  (2024-02-19T10:56:28Z)
• PPD: A New Valet Parking Pedestrian Fisheye Dataset for Autonomous Driving [18.71208933251644]
  Parking Pedestrian dataset consists of several distinctive types of pedestrians captured with fisheye cameras. We present a pedestrian detection baseline on PPD dataset, and introduce two data augmentation techniques to improve the baseline.
  arXiv  Detail & Related papers  (2023-09-20T01:55:19Z)
• Towards Viewpoint Robustness in Bird's Eye View Segmentation [85.99907496019972]
  We study how AV perception models are affected by changes in camera viewpoint. Small changes to pitch, yaw, depth, or height of the camera at inference time lead to large drops in performance. We introduce a technique for novel view synthesis and use it to transform collected data to the viewpoint of target rigs.
  arXiv  Detail & Related papers  (2023-09-11T02:10:07Z)
• SimFIR: A Simple Framework for Fisheye Image Rectification with Self-supervised Representation Learning [105.01294305972037]
  We introduce SimFIR, a framework for fisheye image rectification based on self-supervised representation learning. To learn fine-grained distortion representations, we first split a fisheye image into multiple patches and extract their representations with a Vision Transformer. The transfer performance on the downstream rectification task is remarkably boosted, which verifies the effectiveness of the learned representations.
  arXiv  Detail & Related papers  (2023-08-17T15:20:17Z)
• FishDreamer: Towards Fisheye Semantic Completion via Unified Image Outpainting and Segmentation [33.71849096992972]
  This paper raises the new task of Fisheye Semantic Completion (FSC), where dense texture, structure, and semantics of a fisheye image are inferred even beyond the sensor field-of-view (FoV) We introduce the new FishDreamer which relies on successful ViTs enhanced with a novel Polar-aware Cross Attention module (PCA) to leverage dense context and guide semantically-consistent content generation.
  arXiv  Detail & Related papers  (2023-03-24T07:34:25Z)
• FisheyeEX: Polar Outpainting for Extending the FoV of Fisheye Lens [84.12722334460022]
  Fisheye lens gains increasing applications in computational photography and assisted driving because of its wide field of view (FoV) In this paper, we present a FisheyeEX method that extends the FoV of the fisheye lens by outpainting the invalid regions. The results demonstrate that our approach significantly outperforms the state-of-the-art methods, gaining around 27% more content beyond the original fisheye image.
  arXiv  Detail & Related papers  (2022-06-12T21:38:50Z)
• SurroundDepth: Entangling Surrounding Views for Self-Supervised Multi-Camera Depth Estimation [101.55622133406446]
  We propose a SurroundDepth method to incorporate the information from multiple surrounding views to predict depth maps across cameras. Specifically, we employ a joint network to process all the surrounding views and propose a cross-view transformer to effectively fuse the information from multiple views. In experiments, our method achieves the state-of-the-art performance on the challenging multi-camera depth estimation datasets.
  arXiv  Detail & Related papers  (2022-04-07T17:58:47Z)
• Disentangling and Vectorization: A 3D Visual Perception Approach for Autonomous Driving Based on Surround-View Fisheye Cameras [3.485767750936058]
  Multidimensional Vector is proposed to include the utilizable information generated in different dimensions and stages. The experiments of real fisheye images demonstrate that our solution achieves state-of-the-art accuracy while being real-time in practice.
  arXiv  Detail & Related papers  (2021-07-19T13:24:21Z)
• Fisheye Lens Camera based Autonomous Valet Parking System [3.461121828373003]
  This paper proposes an efficient autonomous valet parking system utilizing only cameras which are the most widely used sensor. Fisheye cameras which have a wider angle of view compared to pinhole cameras are used.
  arXiv  Detail & Related papers  (2021-04-27T11:36:03Z)
• Panoramic Panoptic Segmentation: Towards Complete Surrounding Understanding via Unsupervised Contrastive Learning [97.37544023666833]
  We introduce panoramic panoptic segmentation as the most holistic scene understanding. A complete surrounding understanding provides a maximum of information to the agent. We propose a framework which allows model training on standard pinhole images and transfers the learned features to a different domain.
  arXiv  Detail & Related papers  (2021-03-01T09:37:27Z)
• OmniSLAM: Omnidirectional Localization and Dense Mapping for Wide-baseline Multi-camera Systems [88.41004332322788]
  We present an omnidirectional localization and dense mapping system for a wide-baseline multiview stereo setup with ultra-wide field-of-view (FOV) fisheye cameras. For more practical and accurate reconstruction, we first introduce improved and light-weighted deep neural networks for the omnidirectional depth estimation. We integrate our omnidirectional depth estimates into the visual odometry (VO) and add a loop closing module for global consistency.
  arXiv  Detail & Related papers  (2020-03-18T05:52:10Z)

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.