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

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.

arXiv comment12 pages, 11 figures

References in corpus (8)

• DSSD : Deconvolutional Single Shot Detector
• Multi-Task Learning for Dense Prediction Tasks: A Survey
• Joint 2D-3D-Semantic Data for Indoor Scene Understanding
• Monocular 3D Object Detection with Sequential Feature Association and Depth Hint Augmentation
• FisheyeMODNet: Moving Object detection on Surround-view Cameras for Autonomous Driving
• Spherical formulation of geometric motion segmentation constraints in fisheye cameras
• Surround-view Fisheye Camera Perception for Automated Driving: Overview, Survey and Challenges
• Vehicle Re-ID for Surround-view Camera System

Cited by in corpus (1)

• Parking Spot Classification based on surround view camera system