当前位置:网站首页>CNN-based Point Cloud De-Noising
CNN-based Point Cloud De-Noising
2022-08-11 06:17:00 【zhSunw】
CNN-based Lidar Point Cloud De-Noising in Adverse Weather
Key Knowledgeable:
- Autolabeling for Noise Caused by Rain or Fog
Judging the distance change of each pixel according to the range image to determine whether the pixel is noise caused by rain, fog and water droplets. Label the data:
Why the noise can be marked like this:
The author's understanding is that the rain and fog noise is often the reflection produced by the water droplets in the air, which is described in detail in the article "Fog Simulation on Real LiDAR Point Clouds".When the camera distance is at a certain value, the reflection intensity reaches its peak value. Therefore, there are often circular noise reflections next to the camera in rainy and foggy days. Therefore, when the scanning vehicle is moving, the distance from the non-noise point to the camera will change.There are dense water droplets in the middle, and there are always water droplets with the camera as the center of the circle reflecting noise, so the distance of the noise will not change much, so it can be preliminarily judged whether it is noise by judging whether the point has moved a threshold in each frame.
Of course, this is my personal opinion. The text does not describe this part too much. Corrections are welcome
- Network Architecture
Annotated, augmented data for denoising with WeatherNet for semantic segmentation: - Data Augmentation
Simulation rain and fog weather augmentation training set data: - Experiments
Quantitative denoising results for each weather:
Experiment1, 2, 3 represent three training sets respectivelyThe experimental results below:
Visualize qualitative results:
You can see that data enhancement and WeatherNet are denoising (semantic segmentation of rain and fog) work
边栏推荐
- GBase 8a技术特性-集群架构
- >>数据管理:读书笔记|第一章 数据管理
- 若依分离版—移动端开发通知公告功能
- Socket 网络协议 等
- Realize data exchange between kernel and userspace through character device virtual file system (passed based on kernel 5.8 test)
- Severe Weather 3D Object Detection Dataset Collection
- 梅科尔工作室-HarmonyOS应用开发的第二次培训
- 微信小程序canvas画图,保存页面为海报
- 安全帽识别系统-为安全生产保驾护航
- DNS外带注入SQLMAP
猜你喜欢
安全帽识别算法
Zhejiang University School of Software 2020 Guarantee Research Computer Real Question Practice
Severe Weather 3D Object Detection Dataset Collection
浙江大学软件学院2020年保研上机真题练习
SCNet:Semantic Consistency Networks for 3D Object Detection
2022年最新安全帽佩戴识别系统
梅科尔工作室-第四次PR培训笔记(字幕和标题动画,关键帧动画和声音处理)
梅科尔工作室-DjangoWeb 应用框架+MySQL数据库第三次培训
Reconstruction and Synthesis of Lidar Point Clouds of Spray
docker搭建redis主从和哨兵模式集群
随机推荐
GBase 8s分片技术介绍
梅科尔工作室-DjangoWeb 应用框架+MySQL数据库第二次培训
GBase数据库监控
BGP联邦实验
GBase 8s与Oracle存储对比
梅科尔工作室-DjangoWeb 应用框架+MySQL数据库第四次培训
GBase 8a技术特性-集群架构
【sqlyog】【mysql】csv导入问题
AI-based intelligent image recognition: 4 different industry applications
>>技术应用:用于 REST API 开发和测试的 10 大工具
如何修改严格模式让MySQL5.7插入用户表的方式新建用户成功?delete和drop的不同
若依分离版—增加通知公告预览功能
>>开发工具:开发工具排名对比
关于安全帽识别系统,你需要知道的选择要点
【mysql】查询不区分大小写(用户密码登录不区分大小写)
Toward a Unified Model
正则(三剑客和文本处理工具)
华为adb wifi调试断线问题解决
Use regex to verify whether the file name is legal
Fragment 和 CardView