用MLP提升动态环境下的实时立体定位与地图构建精度
MLP-SLAM: Multilayer Perceptron-Based Simultaneous Localization and Mapping
- 用多层感知机区分动态与静态特征点，保留完整几何信息
- 在5万+特征点数据集上优于现有方法，室外KITTI数据集精度最高、速度最快
- 开源代码与数据集，适合做动态SLAM研究的开发者参考
近年来视觉同步定位与地图构建（V-SLAM）系统发展迅速，在动态物体较少的环境中表现出高精度。然而在行人、汽车、公交车等移动物体较多的户外场景中，性能显著下降。为此，本文提出一种基于多层感知机（MLP）的实时立体SLAM系统，利用完整几何信息避免信息丢失。目前尚无公开数据集可用于直接评估动态与静态特征点分类方法的有效性，为此我们构建了一个包含超过50,000个特征点的公开数据集。实验表明，所提出的MLP动态-静态特征点判别器在该数据集上优于其他方法。此外，该MLP-based实时立体SLAM系统在室外KITTI跟踪数据集上的平均精度最高，运行速度也最快。开源代码与数据集已发布于https://github.com/TaozheLi/MLP-SLAM。
原文摘要 · Abstract (English)
The Visual Simultaneous Localization and Mapping (V-SLAM) system has seen significant development in recent years, demonstrating high precision in environments with limited dynamic objects. However, their performance significantly deteriorates when deployed in settings with a higher presence of movable objects, such as environments with pedestrians, cars, and buses, which are common in outdoor scenes. To address this issue, we propose a Multilayer Perceptron (MLP)-based real-time stereo SLAM system that leverages complete geometry information to avoid information loss. Moreover, there is currently no publicly available dataset for directly evaluating the effectiveness of dynamic and static feature classification methods, and to bridge this gap, we have created a publicly available dataset containing over 50,000 feature points. Experimental results demonstrate that our MLP-based dynamic and static feature point discriminator has achieved superior performance compared to other methods on this dataset. Furthermore, the MLP-based real-time stereo SLAM system has shown the highest average precision and fastest speed on the outdoor KITTI tracking datasets compared to other dynamic SLAM systems.The open-source code and datasets are available at https://github.com/TaozheLi/MLP-SLAM.
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。