{"id":20768500,"url":"https://github.com/pieye/nimbus-perception","last_synced_at":"2025-10-14T18:40:16.266Z","repository":{"id":138742484,"uuid":"288045246","full_name":"pieye/nimbus-perception","owner":"pieye","description":"ROS based Nimbus 3D Perception Stack for Pointcloud Pose estimation, Semantic Segmenation and Object Detection.","archived":false,"fork":false,"pushed_at":"2021-01-18T19:10:52.000Z","size":104918,"stargazers_count":5,"open_issues_count":1,"forks_count":1,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-04-30T12:15:16.358Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"","language":"C++","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"gpl-3.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/pieye.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2020-08-17T00:02:28.000Z","updated_at":"2023-08-30T22:27:47.000Z","dependencies_parsed_at":null,"dependency_job_id":"a29c024f-8bed-40ac-b1e8-58b3ecba16bf","html_url":"https://github.com/pieye/nimbus-perception","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/pieye%2Fnimbus-perception","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/pieye%2Fnimbus-perception/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/pieye%2Fnimbus-perception/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/pieye%2Fnimbus-perception/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/pieye","download_url":"https://codeload.github.com/pieye/nimbus-perception/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":253544983,"owners_count":21925315,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":[],"created_at":"2024-11-17T11:39:13.113Z","updated_at":"2025-10-14T18:40:11.247Z","avatar_url":"https://github.com/pieye.png","language":"C++","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Nimbus-Perception\nNimbus-Perception is a ROS based perception stack for the Nimbus3D time-of-flight camera.\nThe deep learning (tensorflow) based algorithms are running on embedded systems liek a Raspberry Pi4 (64bit Raspberry OS) at ~10Hz. You need to install OpenCV 4.2 and and tensorflow light as well as ROS noetic (perception or desktop-full). The install scripts are given in the \"scripts\" folder. A 64bit OS is highly reccomended as it will reduce the runtime to about the half.\nA prepared Raspberry OS 64bit image can found [here](https://cloud.pieye.org/index.php/s/nimbus3D).\n\n## Nimbus-Detection\nNimbus-Detection is 3D object detection based on a [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://arxiv.org/pdf/1704.04861.pdf). This implementation can detect 91 different classes as shown in the COCO_labels.txt. Every detected object will have an estimated 3D postion and size. The bounding box and class will be visualized in RVIZ.\n\n```\nroslaunch nimbus_detection nimbus_detection.launch\n```\n\u003cimg src=\"assets/nimbus-detection.jpg\" width=\"500\" /\u003e\n\n\n## Nimbus-Pose\nNimbus-Pose is a 3D human pose estimation which extracts the keypoints of the human body. It is based on posenet [PersonLab: Person Pose Estimation and Instance Segmentation with a Bottom-Up, Part-Based, Geometric Embedding Model](https://arxiv.org/pdf/1803.08225.pdf). This implementation can extract all keypoints of a single person and estimate the 3D sceleton.\n```\nroslaunch nimbus_pose nimbus_pose.launch\n```\n\u003cimg src=\"assets/nimbus-pose.jpg\" width=\"500\" /\u003e\n\n\n## Nimbus-Segmentation\nNimbus-Segmentation is a semantic pointcloud segmentation based on [DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs](https://arxiv.org/pdf/1606.00915.pdf). It assigns one of 21 classes to every 3d point and publishes the colourized pointcloud.\n```\nroslaunch nimbus_segmentation nimbus_segmentation.launch\n```\n\u003cimg src=\"assets/nimbus-semantic.jpg\" width=\"500\" /\u003e\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fpieye%2Fnimbus-perception","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fpieye%2Fnimbus-perception","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fpieye%2Fnimbus-perception/lists"}