Transfer Learning Based Semantic Segmentation for 3D Object Detection from Point Cloud

Abstract

Three-dimensional object detection utilizing LiDAR point cloud data is an indispensable part of autonomous driving perception systems. Point cloud-based 3D object detection has been a better replacement for higher accuracy than cameras during nighttime. However, most LiDAR-based 3D object methods work in a supervised manner, which means their state-of-the-art performance relies heavily on a large-scale and well-labeled dataset, while these annotated datasets could be expensive to obtain and only accessible in the limited scenario. Transfer learning is a promising approach to reduce the large-scale training datasets requirement, but existing transfer learning object detectors are primarily for 2D object detection rather than 3D. In this work, we utilize the 3D point cloud data more effectively by representing the birds-eye-view (BEV) scene and propose a transfer learning based point cloud semantic segmentation for 3D object detection. The proposed model minimizes the need for large-scale training datasets and consequently reduces the training time. First, a preprocessing stage filters the raw point cloud data to a BEV map within a specific field of view. Second, the transfer learning stage uses knowledge from the previously learned classification task (with more data for training) and generalizes the semantic segmentation-based 2D object detection task. Finally, 2D detection results from the BEV image have been back-projected into 3D in the postprocessing stage. We verify results on two datasets: the KITTI 3D object detection dataset and the Ouster LiDAR-64 dataset, thus demonstrating that the proposed method is highly competitive in terms of mean average precision (mAP up to 70%) while still running at more than 30 frames per second (FPS).

Using LiDAR System as a Data Source for Agricultural Land Boundaries

“…The resulting digital terrain models and digital surface models depict the surrounding reality in detail. These features determine the multidirectional use of airborne laser scanning in various fields of science, such as engineering solutions-calculation 3D displacements of bridges [3], 3D object detection along the road [4,5], building extraction [6,7], land cover change detection, and forest succession monitoring [8,9] for heterogeneous land use urban mapping [10], coastal monitoring [11,12], or archeological research [13,14].…”

Automated Training Data Creation for Semantic Segmentation of 3d Point Clouds

“…For this purpose, point clouds cut from other real world point clouds can be used or they can be generated from 3D objects (Uggla and Horemuz, 2021). Some other approaches try to minimize the need for training data for example by the use of Transfer learning (Imad et al, 2021) and methods of active learning (Kölle et al, 2020;Lin et al, 2020). Instead of relying on large amounts of training data, these methods increase the efficiency of the already existing training data.…”

Obstacle Detection Using a Facet-Based Representation from 3-D LiDAR Measurements

“…Camera data is fused with LiDAR data in order to detect better objects [ 26 ]. In some works, the detection of objects is approached by performing semantic segmentation on LiDAR data [ 29 , 30 ] or camera-LiDAR fused data [ 31 ].…”