PolarNet: Accelerated Deep Open Space Segmentation using Automotive Radar in Polar Domain

Nowruzi, Farzan Erlik; Kolhatkar, Dhanvin; Kapoor, Prince; Heravi, Elnaz Jahani; Hassanat, Fahed Al; Laganière, Robert; Rebut, Julien; Malik, Waqas Ahmed

doi:10.5220/0010434600002932

Cited by 4 publications

(1 citation statement)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Several studies have been conducted to evaluate or quantify the sim-to-real domain shift, using camera [15,16] or LiDAR [17,18] object detection networks for quantification. The authors train multiple networks on a source dataset and evaluate the trained networks on a target dataset to quantify the domain shift.…”

Section: Introductionmentioning

confidence: 99%

Towards Minimizing the LiDAR Sim-to-Real Domain Shift: Object-Level Local Domain Adaptation for 3D Point Clouds of Autonomous Vehicles

Huch,

Lienkamp

2023

Sensors

View full text Add to dashboard Cite

Perception algorithms for autonomous vehicles demand large, labeled datasets. Real-world data acquisition and annotation costs are high, making synthetic data from simulation a cost-effective option. However, training on one source domain and testing on a target domain can cause a domain shift attributed to local structure differences, resulting in a decrease in the model’s performance. We propose a novel domain adaptation approach to address this challenge and to minimize the domain shift between simulated and real-world LiDAR data. Our approach adapts 3D point clouds on the object level by learning the local characteristics of the target domain. A key feature involves downsampling to ensure domain invariance of the input data. The network comprises a state-of-the-art point completion network combined with a discriminator to guide training in an adversarial manner. We quantify the reduction in domain shift by training object detectors with the source, target, and adapted datasets. Our method successfully reduces the sim-to-real domain shift in a distribution-aligned dataset by almost 50%, from 8.63% to 4.36% 3D average precision. It is trained exclusively using target data, making it scalable and applicable to adapt point clouds from any source domain.

show abstract