{"id":20972054,"url":"https://github.com/hpennington/mono-visual-odometry","last_synced_at":"2026-04-28T16:04:58.734Z","repository":{"id":63113692,"uuid":"565321103","full_name":"hpennington/mono-visual-odometry","owner":"hpennington","description":"Monocular Visual Odometry in NumPy","archived":false,"fork":false,"pushed_at":"2023-12-25T19:39:46.000Z","size":91387,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":2,"default_branch":"main","last_synced_at":"2025-03-13T08:27:12.267Z","etag":null,"topics":["computer-vision","numpy","opencv","python"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/hpennington.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE.txt","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":"2022-11-13T02:28:11.000Z","updated_at":"2024-05-26T18:29:01.000Z","dependencies_parsed_at":"2024-11-19T04:06:28.116Z","dependency_job_id":"b1482c4c-46ab-49c4-9fb0-4c247ade9072","html_url":"https://github.com/hpennington/mono-visual-odometry","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/hpennington/mono-visual-odometry","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hpennington%2Fmono-visual-odometry","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hpennington%2Fmono-visual-odometry/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hpennington%2Fmono-visual-odometry/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hpennington%2Fmono-visual-odometry/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/hpennington","download_url":"https://codeload.github.com/hpennington/mono-visual-odometry/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hpennington%2Fmono-visual-odometry/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":261533951,"owners_count":23173315,"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","numpy","opencv","python"],"created_at":"2024-11-19T04:06:22.496Z","updated_at":"2026-04-28T16:04:53.699Z","avatar_url":"https://github.com/hpennington.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"\n![](https://github.com/hpennington/mono-visual-odometry/raw/main/point_cloud.gif)\n\n# Monocular visual odometry\nA Work in Progress implementation of visual odometry in numpy. Currently aided by some opencv functions. The plan is to remove these and implement with purely numpy.\n\n\n#### Functions to implement in native numpy\n  - [ ] goodFeaturesToTrack\n  - [x] ransac\n  - [x] FundamentalMatrixTransform\n  - [ ] Brute-Force Matcher (BFMatcher)\n  - [ ] Compute ORB feature descriptors\n  - [x] triangulate\n  - [x] extract_pose (Needs refactoring for deciding ambiguities)\n  - [x] fundamentalToEssential\n  - [x] make_homogeneous\n\n\n## Setup\n\n```bash\nconda env create -f environment.yml\nconda activate pyvo\n```\n\nMy suggestion is to open src/visual_odometry.ipynb in VS Code.\nAny web browser and jupyter notebook will work, but I find that VS Code make the nicest notebook environment.\n\n## Demo\nPress 'q' to end the demo sooner than the full duration.\n\n### Feature matches\nThe red and green points represent the detected feature in the current and previous frame. A blue line is draw between these points.\n![](https://github.com/hpennington/mono-visual-odometry/raw/main/features.jpeg)\n\n\n### Integrated pose plot\nRed is the ground truth and green is the predicted pose\n![](https://github.com/hpennington/mono-visual-odometry/raw/main/vo.png)\n\n### Point cloud\nOpen the point cloud in the open3d app. http://www.open3d.org/download/\n![](https://github.com/hpennington/mono-visual-odometry/raw/triangulation/point_cloud.png)\n\n\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fhpennington%2Fmono-visual-odometry","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fhpennington%2Fmono-visual-odometry","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fhpennington%2Fmono-visual-odometry/lists"}