将激光雷达数据转为伪彩色图像，实现高精度车辆实例分割
LiCAR: pseudo-RGB LiDAR image for CAR segmentation
- 将激光雷达的反射率、近红外和信号强度合成伪彩色图像
- 在YOLO-v8大模型上达到88%框精度和81.5%掩码精度
- 适用于真实场景下车辆跟踪，适合自动驾驶感知系统
随着计算资源的发展，越来越多神经网络被用于图像检测与分割。然而，这些方法通常以RGB二维图像为输入。另一方面，多层激光雷达（LiDAR）传感器生成的图像类似于传统低分辨率RGB相机所得图像。基于此，本文构建了一个用于伪彩色图像中车辆分割的新数据集。该数据集将激光雷达提供的信息融合为球面距离图像（SRI），具体包括反射率、近红外和信号强度的二维图像。这些图像被输入实例分割神经网络进行车辆分割，获得边界框（BB）精度88%和掩码精度81.5%，使用YOLO-v8大模型。通过该分割网络，进一步应用追踪器对视频流中的每个车辆实例进行跟踪，在真实世界实验中表现优异。
原文摘要 · Abstract (English)
With the advancement of computing resources, an increasing number of Neural Networks (NNs) are appearing for image detection and segmentation appear. However, these methods usually accept as input a RGB 2D image. On the other side, Light Detection And Ranging (LiDAR) sensors with many layers provide images that are similar to those obtained from a traditional low resolution RGB camera. Following this principle, a new dataset for segmenting cars in pseudo-RGB images has been generated. This dataset combines the information given by the LiDAR sensor into a Spherical Range Image (SRI), concretely the reflectivity, near infrared and signal intensity 2D images. These images are then fed into instance segmentation NNs. These NNs segment the cars that appear in these images, having as result a Bounding Box (BB) and mask precision of 88% and 81.5% respectively with You Only Look Once (YOLO)-v8 large. By using this segmentation NN, some trackers have been applied so as to follow each car segmented instance along a video feed, having great performance in real world experiments.
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。