多传感器融合SLAM调研

感知任务

物体识别：

• 《Pointnet: Deep learning on point sets for 3d classification and segmentation》
• 《Voxelnet: End-to-end learning for point cloud based 3d object detection》

语义分割：

• 《An integrated framework for autonomous driving: object detection, lane detection, and free space detection》
• 《 Freespace detection with deepnets for autonomous driving》
• 《Overview of image segmentation and its application on free space detection》
• 《Road curb and lanes detection for autonomous driving on urban scenarios》
• 《Lanenet: Realtime lane detection networks for autonomous driving》

物体分类：

• 《Deep learning for lidar point clouds in autonomous driving: a review》

深度补全和预测：

• 《Are we ready for autonomous driving? the kitti vision benchmark suite》

多传感器融合

激光雷达/视觉融合：
从传统分类的角度来看，所有的多模态数据融合方法都可以分为数据级融合(前融合)、特征级融合(深度融合)和目标级融合(后融合)三种模式。

前融合方案：

1. 《Fast and Accurate 3D Object Detection for Lidar-Camera-Based Autonomous Vehicles Using One Shared Voxel-Based Backbone》
2. 《PointPainting: Sequential Fusion for 3D Object Detection》
3. 《PI-RCNN: An Efficient Multi-Sensor 3D Object Detector with Point-Based Attentive Cont-Conv Fusion Module》
4. 《Complexer-YOLO: Real-Time 3D Object Detection and Tracking on Semantic Point Clouds》
5. 《Mvxnet: Multimodal voxelnet for 3d object detection》

特征级融合方案：

1. 《RoIFusion: 3D Object Detection From LiDAR and Vision》
2. 《EPNet: Enhancing Point Features with Image Semantics for 3D Object Detection》
3. 《MAFF-Net: Filter False Positive for 3D Vehicle Detection with Multi-modal Adaptive Feature Fusion》
4. 《SemanticVoxels: Sequential Fusion for 3D Pedestrian Detection using LiDAR Point Cloud and Semantic Segmentation》
5. 《Multi-View Adaptive Fusion Network for 3D Object Detection》

超声波（uss）与图像融合：

1. 《Robust Sonar Feature Detection for the SLAM of Mobile Robot》
2. 《Metric SLAM in Home Environment with Visual Objects and Sonar Features》
3. 《SLAM with Visual Plane: Extracting Vertical Plane by Fusing Stereo Vision and Ultrasonic Sensor for Indoor Environment》
4. 《A practical approach for EKF-SLAM in an indoor environment: fusing ultrasonic sensors and stereo camera》