Multimodality Weight and Score Fusion for SLAM
Multimodality Weight and Score Fusion for SLAM
复制标题
DOI：
10.1109/ccece47787.2020.9255714
复制
发表时间：
2020-08
期刊：
影响因子：
--
通讯作者：
Thangarajah Akilan;E. Johnson;Gaurav Taluja;Japneet Sandhu;Ritika Chadha
中科院分区：
文献类型：
--
作者：
Thangarajah Akilan;E. Johnson;Gaurav Taluja;Japneet Sandhu;Ritika Chadha
同步定位和映射（SLAM）用于自动驾驶汽车（SDC）等自主导航机器人（ANR）的轨迹预测。它通过感知周围环境来计算轨迹，就像对环境的视觉感知一样。这项工作的重点是使用多模态学习提高SLAM模型的性能：(i)通过特征提取器的层权重增强进行早期融合，以及（ii）通过轨迹（姿态）回归器的分数细化进行后期融合。在Apolloscape数据集上的对比分析表明，所提出的融合策略显著提高了定位性能。这项工作还评估了各种深度卷积神经网络（DCNNs）在SLAM中的适用性。
Simultaneous Localization And Mapping (SLAM) is used to predict the trajectory by the Autonomous Navigation Robots (ANR), for instance Self-Driving Cars (SDC). It computes the trajectory through sensing the surroundings, like a visual perception of the environment. This work focuses on the performance improvements of a SLAM model using multimodal learning: (i), early fusion via layer weight enhancement of feature extractors, and (ii), late fusion via score refinement of the trajectory (pose) regressor. The comparative analysis on Apolloscape dataset shows that the proposed fusion strategies improve localization performance significantly. This work also evaluates applicability of various Deep Convolutional Neural Networks (DCNNs) for SLAM.