{"id":19140287,"url":"https://github.com/kk7nc/3d-object-detection","last_synced_at":"2025-05-06T23:16:40.978Z","repository":{"id":95592550,"uuid":"142369640","full_name":"kk7nc/3D-Object-Detection","owner":"kk7nc","description":"Weighted Unsupervised Learning for 3D Object Detection","archived":false,"fork":false,"pushed_at":"2018-08-01T01:09:54.000Z","size":8045,"stargazers_count":13,"open_issues_count":1,"forks_count":7,"subscribers_count":4,"default_branch":"master","last_synced_at":"2025-05-06T23:16:32.362Z","etag":null,"topics":["clustering","kinect","machine-learning","object-detection","unsupervised-machine-learning"],"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/kk7nc.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,"zenodo":null}},"created_at":"2018-07-26T00:58:59.000Z","updated_at":"2023-08-31T23:23:42.000Z","dependencies_parsed_at":"2023-05-21T00:15:13.390Z","dependency_job_id":null,"html_url":"https://github.com/kk7nc/3D-Object-Detection","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/kk7nc%2F3D-Object-Detection","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kk7nc%2F3D-Object-Detection/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kk7nc%2F3D-Object-Detection/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kk7nc%2F3D-Object-Detection/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/kk7nc","download_url":"https://codeload.github.com/kk7nc/3D-Object-Detection/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":252782835,"owners_count":21803410,"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":["clustering","kinect","machine-learning","object-detection","unsupervised-machine-learning"],"created_at":"2024-11-09T07:17:02.048Z","updated_at":"2025-05-06T23:16:40.970Z","avatar_url":"https://github.com/kk7nc.png","language":"C++","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Weighted Unsupervised Learning for 3D Object Detection\n\n[![DOI](https://img.shields.io/badge/DOI-10.14569/IJACSA.2016.070180-blue.svg?style=flat)](http://dx.doi.org/10.14569/IJACSA.2016.070180)\n[![DOI](https://img.shields.io/badge/Visual%20Studio-C%2B%2B-red.svg)](https://visualstudio.microsoft.com/)\n[![L](https://img.shields.io/aur/license/yaourt.svg)](https://github.com/kk7nc/3D-Object-Detection/blob/master/LICENSE)\n[![twitter](https://img.shields.io/twitter/url/http/shields.io.svg?style=social)](https://twitter.com/intent/tweet?text=Weighted%20Unsupervised%20Learning%20for%203D%20Object%20Detection%0aGitHub:\u0026url=https://github.com/kk7nc/3D-Object-Detection\u0026hashtags=3D,ObjectDetection,unsupervised,MachineLearning,Clustering,RGBD,Computer_Vision,Kinect)\n\n\n\n\nReferenced paper : [Weighted Unsupervised Learning for 3D Object Detection](https://arxiv.org/pdf/1602.05920.pdf)\n\n\n3D Object Detection:\n=====================\nThis paper introduces a novel weighted unsupervised\nlearning for object detection using an RGB-D camera. This\ntechnique is feasible for detecting the moving objects in the noisy\nenvironments that are captured by an RGB-D camera. The main\ncontribution of this paper is a real-time algorithm for detecting\neach object using weighted clustering as a separate cluster. In a\npreprocessing step, the algorithm calculates the pose 3D position\nX, Y, Z and RGB color of each data point and then it calculates\neach data point’s normal vector using the point’s neighbor. After\npreprocessing, our algorithm calculates k-weights for each data\npoint; each weight indicates membership. Resulting in clustered\nobjects of the scene.\n\n![Object_Detection](http://kowsari.net/onewebstatic/Overview_Object.png)\nPipeline of 3D Object detection using RGB-D camera has two main parts: 1) Preprocessing including Mapping, Back-Projection,  Normal  Generating,  Background  removal  and  2)  Clustering  including  assigned  initial  weight,  distance  calculation,update weight and assign color, and finally visualization to illustrate the results.\n\nResults:\n=====================\n\n![Object_Detection](http://kowsari.net/onewebstatic/OBJECT%20(1).jpg)\nKinect color frame (RGB) with resolution of 1920 X 1080; b) Kinect depth frame with resolution of 512 X 424; c) Proposed method object detection using k= 15 clusters, and after 15 iterations.\n\n\n![Object_Detection](http://kowsari.net/onewebstatic/OBJECT%20(3).jpg)\n\na) Kinect color frame (RGB) with resolution of 1920 X 1080; b) Kinect depth frame with resolution of 512 X 424; c)  Proposed  method  object  detection  using  k=  7  clusters,  and  after  10  iterations.  Memory  consumption  is  320  MB  and  framerate is 8.1±0.2FPS.\n\n\n\n![Object_Detection](http://kowsari.net/onewebstatic/OBJECT%20(2).jpg)\n\nResults  of  segmenting  scene  objects  using  proposed  algorithm;a)  Segmentation  of  small  duck;b)  Segmentation  anddetection  of  piece  of  red  paper;c)  Object  detection  of  a  box;d)  Shows  handy  bag;e)  Segmentation  of  box,  the  border  of  thebox  has  lower  weight  and  it  will  be  completed  after  several  iteration;f)  Representation  of  moving  object,  segmentation  of  aperson;g) Segmentation of basketball.\n\n\nCitations\n---------\n\n```\n\n@article{Kowsari2016,\ntitle = {Weighted Unsupervised Learning for 3D Object Detection},\njournal = {International Journal of Advanced Computer Science and Applications}\ndoi = {10.14569/IJACSA.2016.070180},\nurl = {http://dx.doi.org/10.14569/IJACSA.2016.070180},\nyear = {2016},\npublisher = {The Science and Information Organization},\nvolume = {7},\nnumber = {1},\nauthor = {Kamran Kowsari and Manal H. Alassaf},\n}\n\n```\n\n\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fkk7nc%2F3d-object-detection","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fkk7nc%2F3d-object-detection","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fkk7nc%2F3d-object-detection/lists"}