{"id":21915165,"url":"https://github.com/ethanlee928/jetson-vision","last_synced_at":"2026-05-19T03:40:26.246Z","repository":{"id":243905395,"uuid":"813643237","full_name":"ethanlee928/jetson-vision","owner":"ethanlee928","description":"Real time video analytics with Nvidia's Jetson devices.","archived":false,"fork":false,"pushed_at":"2024-06-18T10:00:27.000Z","size":41,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-01-27T09:23:45.684Z","etag":null,"topics":["computer-vision","edge-computing","nvidia","object-detection","python","video-analytics"],"latest_commit_sha":null,"homepage":"","language":"Python","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/ethanlee928.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":"2024-06-11T13:18:57.000Z","updated_at":"2024-07-25T02:43:48.000Z","dependencies_parsed_at":"2024-06-16T08:40:18.426Z","dependency_job_id":null,"html_url":"https://github.com/ethanlee928/jetson-vision","commit_stats":null,"previous_names":["ethanlee928/jetson-vision"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ethanlee928%2Fjetson-vision","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ethanlee928%2Fjetson-vision/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ethanlee928%2Fjetson-vision/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ethanlee928%2Fjetson-vision/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ethanlee928","download_url":"https://codeload.github.com/ethanlee928/jetson-vision/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":244933368,"owners_count":20534351,"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","edge-computing","nvidia","object-detection","python","video-analytics"],"created_at":"2024-11-28T19:09:18.386Z","updated_at":"2026-05-19T03:40:21.216Z","avatar_url":"https://github.com/ethanlee928.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Jetson Vision\n\nReal time video analytics with Nvidia's Jetson devices.\n\n## Prerequisites\n\n### Hardware\n\n- Tested with NVIDIA Jetson Nano (Jetpack 4.6 [L4T 32.6.1])\n\n### Docker Nvidia Runtime\n\n```bash\nsudo vim /etc/docker/daemon.json\n\n{\n    \"runtimes\": {\n        \"nvidia\": {\n            \"path\": \"nvidia-container-runtime\",\n            \"runtimeArgs\": []\n        }\n    },\n    \"default-runtime\": \"nvidia\"\n}\n```\n\n```bash\nsudo service docker restart\n\n# Check\nsudo docker info | grep Default\n\n# Expected output\nDefault Runtime: nvidia\nWARNING: No blkio weight support\nWARNING: No blkio weight_device support\n```\n\n## How to Start\n\n### Docker Enviornment\n\n```bash\n./scripts/build.sh\n\n# Start docker container\n./scripts/start.sh\n```\n\n### Download Pre-trained Models\n\n- Pretrained models will be downloaded @ `/jetson-inference/data/networks`\n- In `scripts/start.sh`, the models directory is mounted to local volume (`/media/data/models/`). Thus, no need to re-download the models multiple times in docker environment.\n\n```bash\ncd /jetson-inference/tools\n./download-models.sh\n```\n\n## Basics\n\nHello world codes for using Jetson-inference.\n\n```bash\ncd basics\n```\n\n### Object Detection\n\n```bash\npython3 detect.py /dev/vidoe0\n```\n\n### Semantic Segmentation\n\n```bash\npython3 segment.py /dev/video0\n```\n\n## Analytics\n\nUsing Jetson-inference toghether with Supervision to do vidoe analytics.\n\n```bash\ncd analytics/\n```\n\n### People Counting in a Zone\n\nCounting number of people in a defined polygon zone.\n\n```bash\npython3 counting.py /dev/video0\n```\n\n### Flow analysis\n\nCounting objects going in and going out of a line zone.\n\n```bash\npython3 flow.py /dev/video0\n```\n\n### People Redaction\n\nDetects person and redact the whole body, could be used to process video with privacy concerns.\n\n```bash\npython3 redaction.py /dev/video0\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fethanlee928%2Fjetson-vision","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fethanlee928%2Fjetson-vision","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fethanlee928%2Fjetson-vision/lists"}