{"id":21205268,"url":"https://github.com/mabdh/mot-pf","last_synced_at":"2026-01-03T04:04:14.373Z","repository":{"id":87517210,"uuid":"64165137","full_name":"mabdh/mot-pf","owner":"mabdh","description":"🔎 Multiple Object Tracking with Particle Filter","archived":false,"fork":false,"pushed_at":"2020-07-04T05:41:20.000Z","size":2851,"stargazers_count":12,"open_issues_count":0,"forks_count":6,"subscribers_count":2,"default_branch":"master","last_synced_at":"2025-01-21T15:27:35.747Z","etag":null,"topics":["computer-vision","object-tracking"],"latest_commit_sha":null,"homepage":"","language":"HTML","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/mabdh.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"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":"2016-07-25T20:19:02.000Z","updated_at":"2022-10-26T19:12:58.000Z","dependencies_parsed_at":"2023-03-03T22:30:48.090Z","dependency_job_id":null,"html_url":"https://github.com/mabdh/mot-pf","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/mabdh%2Fmot-pf","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mabdh%2Fmot-pf/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mabdh%2Fmot-pf/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mabdh%2Fmot-pf/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/mabdh","download_url":"https://codeload.github.com/mabdh/mot-pf/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":243658270,"owners_count":20326467,"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":["computer-vision","object-tracking"],"created_at":"2024-11-20T20:43:46.096Z","updated_at":"2026-01-03T04:04:14.332Z","avatar_url":"https://github.com/mabdh.png","language":"HTML","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Multiple-Object Tracking Using Particle Filter\nThis is the project for Computer Graphics Lab in University of Bonn\n## Implementing a multiple object tracking with Particle Filter based on this reference.\n```\nM. D. Breitenstein, F. Reichlin, B. Leibe, E. Koller-Meier and L. V. Gool\n”Online multi-person tracking-by-detection from a single, uncalibrated\ncamera”, IEEE Trans. Pattern Anal. Mach. Intell., vol. 33, no. 9, pp.1820\n-1833 2011.\n```\n\nThis is an Eclipse Project.\n\n## Structure of Directory\nThis directory contains :\n\n- Debug and Evaluate - Store evaluation data for every experiment. ex : *Eval1_* is the second experiment. Create folder of EvalN_ manually if you want to do N+1 experiments. With data format `x-axis-FalseNegative-FalsePositive-TruePositive-IDSwitch-MOTA-MOTP` (could be anything, example: number of particles, sigma propagation, etc)\n\n- PETS_frame - Contain sequence of video. With filename **format frame_0000.jpg**\n\n- PETS_gt - Contain ground truth data with filename format frame_0000.txt. With data format `number_of_frame-x(top-left)-y(top-left)-width-height-index`\n- PETS_GT_map - Contain detection maps from ground truth\n- PETS_map - Contain detection maps from detectors\n- src\n- TrackerData - Contain ground truth data with filename format frame_0000.txt. With data format `number_of_frame-x(top-left)-y(top-left)-width-height-index`\n- View1_result - Result of tracked objects on the image\n\n## Note \nThere is also \n- a documentation inside src/html/index.html\n- A python file to plot the evaluation\n\t- EvaluateNumParticles (To evaluate tracker with x-axis is number of particles)\n\t- EvaluatePETS (To evaluate tracker with x-axis is sigma_of_propagation (could be changed..))\n\n## Dependencies\nIn Eclipse project. Go to\n```\nProject-\u003eProperties-\u003eC/C++ Build-\u003eSettings\n```\n\nIn GCC C++\n```\nCompiler-\u003eMiscelanneous-\u003eadd other flags \"-std=c++11 -std=c++0x\"\n```\n\nIn C++ \n```\nLinker-\u003eLibraries-\u003eadd Libraries (-l) \"config++\"\n```\n\n\n## Configuration File Structure\n\n```\nparticlefilter :\n{\n    main :\n    {\n        num_experiment = 1;\t\t\t\t\t\t\t\t\t// number experiment that will be executed with various parameters\n        detmapfiles = \"PETS_map/\";\t\t\t\t\t\t\t// directory of detection maps\n        trackerdatafiles = \"TrackerData/\";\t\t\t\t\t// directory of tracker data *.txt\n        groundtruthfiles = \"PETS_gt/\";\t\t\t\t\t\t// directory of ground truth data *.txt\n        evalresultfiles = \"Evaluate/\";\t\t\t\t\t\t// directory to store evaluation result\n        sequenceframefiles = \"PETS_frame/\";\t\t\t\t\t// directory of sequence frames\n        resulttrackerfiles = \"View1_result/\";\t\t\t\t// directory to store image of tracked objects\n        main0 :\t\t\t\t\t\t\t\t\t\t\t\t// first experiment\n        {\n            min_area_detection_threshold = 30;\t\t\t\t// threshold value to find contour of objects\n            number_of_particles = 50;\t\t\t\t\t\t// number of particles\n            threshold_detection = 160;\t\t\t\t\t\t// threshold value to treshold binary images\n            use_histogram = 3;\t\t\t\t\t\t\t\t// tipe of histograms (single, divide into 3, overlap)\n            vis_type = 2;\t\t\t\t\t\t\t\t\t// visualization type (particles, circle, bounding box)\n            with_gt = 1;\t\t\t\t\t\t\t\t\t// flag status to use ground truth or not\n            sigma_propagate = [10.0, 10.0, 1.0, 1.0];\t\t// value of sigma propagation (sigma_p and sigma_v)\n            sigma_measurement = 1.0;\t\t\t\t\t\t// value of sigma measurement\n            c_detection = 0.6;\t\t\t\t\t\t\t\t// constant to weight detection model (1-alpha)\n            c_color = 0.4;\t\t\t\t\t\t\t\t\t// constant to weight color (alpha)\n            mul_factor_c_color = 0.6;\t\t\t\t\t\t// constant to weight detection model (1-alpha),  when there is an occlusion\n            mul_factor_c_detection = 0.4;\t\t\t\t\t// constant to weight color (alpha), when there is an occlusion\n            width_default = 40;\t\t\t\t\t\t\t\t// width default of bounding box\n            height_default = 80;\t\t\t\t\t\t\t// height default of bounding box\n            using_occlusion_handling = 1;\t\t\t\t\t// flag status to run using occlusion handling or not\n        };\n        main1 :\t\t\t\t\t\t\t\t\t\t\t\t// here comes another variation of parameter\n        {\n        ...\n        };\n        main2 :\t\t\t\t\t\t\t\t\t\t\t\t// here again..\n        ...\n        ...\n        ...\n    };\n}\n```\n\nThe documentation of ParticleFilter class can be found here [Particle Filter Class](https://mabdh.github.io/multiple-object-tracking-particle-filter)\n\nThe report can be found here [Project Report](https://github.com/mabdh/multiple-object-tracking-particle-filter/blob/master/pdf/LabReportv2.pdf)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmabdh%2Fmot-pf","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fmabdh%2Fmot-pf","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmabdh%2Fmot-pf/lists"}