融合2D与3D声呐，自动校准降噪，提升水下物体识别精度
Calibration and Comparative Analysis of Forward-Looking Sonar and 3D Sonar for Enhanced Underwater Object Recognition
- 用2D强度图与3D点云双模态声呐互补
- 自动校准使特征提取性能提升超40%
- 适合水下机器人导航与目标识别研究者
声呐生成大量噪声。随着新科技能生成完整3D点云，稀疏点云中的噪声被放大，给导航、识别或重建带来挑战。为此，本文提出使用两种不同声呐模态：一种生成2D强度图像，另一种生成3D点云。通过实现自动校准，可在模态间过滤噪声特征，从而增强特征提取。实验表明，自动校准相比人工校准性能提升5%，而滤波后特征提取效果比原始点云提升超过40%。代码与数据集见 https://theaprilab.org/fls-3d-calibrator
原文摘要 · Abstract (English)
Sonars generate a significant amount of noise. With the advent of new technology capable of producing full 3D point clouds, the noise is amplified in sparse point clouds, making it challenging to recognize features for navigation, recognition, or reconstruction. To address this challenge, we propose using two different sonar modalities: one that produces a 2D intensity image and another that generates a 3D point cloud. By implementing auto-calibration, we can filter out noisy features between the modalities to enhance feature extraction. Experiments demonstrate that auto-calibration improves performance over manual calibration by 5% and that filtering enhances feature extraction by more than 40% relative to the raw point cloud. Code and datasets are given at https://theaprilab.org/fls-3d-calibrator
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。