We present a novel way of odometry estimation from Velodyne LiDAR point cloud scans. The aim our work is to overcome the most painful issues data - sparsity and quantity points in an efficient way, enabling more precise registration. Alignment clouds which yields final based on random sampling using Collar Line Segments (CLS). closest line segment pairs are identified two sets segments obtained consequent From each pair correspondences, transformation aligning matched into 3D plane...

We introduce a novel method for odometry estimation using convolutional neural networks from 3D LiDAR scans. The original sparse data are encoded into 2D matrices the training of proposed and prediction. Our show significantly better precision in translational motion parameters comparing with state art LOAM, while achieving real-time performance. Together IMU support, high quality registration is realized. Moreover, we propose alternative CNNs trained prediction rotational results also...

This paper presents a novel method for ground segmentation in Velodyne point clouds. We propose an encoding of sparse 3D data from the sensor suitable training convolutional neural network (CNN). general purpose approach is used cloud into and non-ground points. The LiDAR are represented as multi-channel 2D signal where horizontal axis corresponds to rotation angle vertical represents channels - laser beams. Multiple topologies relatively shallow CNNs (i.e. 3-5 layers) trained evaluated,...

This paper presents a human-carried mapping backpack based on pair of Velodyne LiDAR scanners. Our system is universal solution for both large scale outdoor and smaller indoor environments. It benefits from combination two scanners, which makes the odometry estimation more precise. The scanners are mounted under different angles, thus larger space around scanned. By fusion with GNSS/INS sub-system, featureless environments georeferencing resulting point cloud possible. deploying SoA methods...

This paper proposes the use of change detection in a multi-view object recognition system order to improve its flexibility and effectiveness dynamic environments. Multi-view approaches are essential overcome problems related clutter, occlusion or camera noise, but existing systems usually assume static environment. The presence objects raises another issue - inconsistencies introduced internal scene model. We show that by incorporating correction inherent inconsistencies, we reduce false...

This paper presents a novel method for ground segmentation in Velodyne point clouds. We propose an encoding of sparse 3D data from the sensor suitable training convolutional neural network (CNN). general purpose approach is used cloud into and non-ground points. The LiDAR are represented as multi-channel 2D signal where horizontal axis corresponds to rotation angle vertical indexes channels (i.e. laser beams). Multiple topologies relatively shallow CNNs 3-5 layers) trained evaluated using...

We introduce a novel method for odometry estimation using convolutional neural networks from 3D LiDAR scans. The original sparse data are encoded into 2D matrices the training of proposed and prediction. Our show significantly better precision in translational motion parameters comparing with state art LOAM, while achieving real-time performance. Together IMU support, high quality registration is realized. Moreover, we propose alternative CNNs trained prediction rotational results also...