Code Monkey home page Code Monkey logo

红外彩色化数据集

一种制备真实可信的红外彩色图像数据集的方法，为训练神经网络提供数据样本。

2022年数据效果：

alt

2023年数据效果：

alt

一、运行环境说明

本例程测试环境：硬件为联想Y9000P，操作系统为Ubuntu20.04，ROS版本为neotiic。

第三方库文件： octomap-1.9.0 、pcl-1.10 、 vtk-7.1 、 python3.8

二、编译和运行

  1. 使用QtCreator编译 OctomapTakeOut

  2. 使用PyCharm运行 InfraColor\scripts\color-image-ntd.py

三、工作流程

  1. 基础设备准备：相机、激光雷达和惯导的联合标定，相机和激光雷达的时空同步，激光雷达基于惯导的动态补偿

  2. 基础数据采集：在测试地点，白天场景采集惯导、激光雷达、可见光图像数据

​ 夜晚场景采集惯导、激光雷达、红外图像数据

（城市区域数据采集难度低于越野区域）

  1. 高精地图构建：通过两次采集数据，构建该测试地点的高精地图，获取对应图像帧和雷达帧的精准全局位姿数据

  2. 稠密点云选取：依据获得的全局位姿数据，从高精地图中求取该帧的激光雷达点云数据，并转换到激光雷达坐标系

  3. 点云和图像数据匹配：通过时间戳、欧式距离与偏航角计算，分别获取成对的白天彩色图像与点云数据，红外图像数据与点云数据

  4. 红外图像彩色化：将红外图像中的灰色像素，转换为可见光彩色像素

Downloads

DataSets 下载链接： Syncing

TO DO：

  1. 当前只实现了单帧的像素恢复，可通过多次匹配，优化恢复效果
  2. 通过不同的采样优化方法，例如BGK，分段提升点云恢复效果

注意：提供示例数据，不提供高精地图构建方法

2022-10-24-map 白天彩色图像、点云和惯导数据

2022-10-25-map 夜晚红外图像、点云和惯导数据

部分参考文献

  1. Research on Colorful Visualization and Object Detection in Low Illumination

  2. In Defense of Classical Image Processing: Fast Depth Completion on the CPU. [cs.CV 31 Jan 2018 ] (IP-Basic)

  3. Improving 3D Object Detection for Pedestrians with Virtual Multi-View Synthesis Orientation Estimation. [cs.CV 15 Jul 2019 ] (3D Scene Visualizer)

Contact

If you have any questions, feel free to open an issue or contact Jie Wang for [email protected].

ShiYuan's Projects

chatgpt_academic icon chatgpt_academic

科研工作专用ChatGPT拓展，特别优化学术Paper润色体验，支持自定义快捷按钮，支持markdown表格显示，Tex公式双显示，代码显示功能完善，新增本地Python工程剖析功能/自我剖析功能

clash-for-mac icon clash-for-mac

Clash for Windows for Mac，Clash for Windows for Mac教程，Clash for Windows for Mac配置说明，Clash for Mac

cnn-explainer icon cnn-explainer

Learning Convolutional Neural Networks with Interactive Visualization.

fast-livo icon fast-livo

A Fast and Tightly-coupled Sparse-Direct LiDAR-Inertial-Visual Odometry.

free icon free

翻墙、免费翻墙、免费科学上网、免费节点、免费梯子、免费ss/v2ray/trojan节点、蓝灯、谷歌商店、翻墙梯子

kalibr icon kalibr

The Kalibr visual-inertial calibration toolbox

mvision icon mvision

机器人视觉 移动机器人 VS-SLAM ORB-SLAM2 深度学习目标检测 yolov3 行为检测 opencv PCL 机器学习 无人驾驶

paddledetection icon paddledetection

Object Detection toolkit based on PaddlePaddle. It supports object detection, instance segmentation, multiple object tracking and real-time multi-person keypoint detection.

ral_non-learning_depthcompletion icon ral_non-learning_depthcompletion

A non-learning geometry-based LiDAR depth completion model with components including outlier removal, normal calculation, distance transform, etc. IEEE Robotics and Automation Letters

rootonnvme icon rootonnvme

Switch the rootfs to a NVMe SSD on the Jetson Xavier NX and Jetson AGX Xavier

tensorrt-alpha icon tensorrt-alpha

🔥🔥🔥TensorRT-Alpha supports YOLOv8、YOLOv7、YOLOv6、YOLOv5、YOLOv4、v3、YOLOX、YOLOR...🚀🚀🚀CUDA IS ALL YOU NEED.🍎🍎🍎It also supports end2end CUDA C acceleration and multi-batch inference.

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.