{"id":19517363,"url":"https://github.com/saornek/ic4us-zed-camera-template","last_synced_at":"2026-06-18T07:31:53.324Z","repository":{"id":187865864,"uuid":"668643383","full_name":"saornek/IC4Us-Zed-Camera-Template","owner":"saornek","description":"IC4U is a robot guide dog that assists blind people by mimicking a real guide dog with the help of AI and ML. In this repository you can find the code template used in all IC4U's object detection applications.","archived":false,"fork":false,"pushed_at":"2023-08-07T15:07:58.000Z","size":5939,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-02-26T00:12:07.543Z","etag":null,"topics":["ic4u","jetson-nano","nvidia","object-detection","python","zed-camera","zed2"],"latest_commit_sha":null,"homepage":"https://selinoid.com/","language":"Python","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/saornek.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}},"created_at":"2023-07-20T09:28:29.000Z","updated_at":"2023-10-09T16:36:29.000Z","dependencies_parsed_at":"2023-08-12T13:28:31.125Z","dependency_job_id":"5faaa3c5-c15b-4da7-8bb6-65cf97ddb629","html_url":"https://github.com/saornek/IC4Us-Zed-Camera-Template","commit_stats":null,"previous_names":["saornek/ic4us-zed-camera-template"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/saornek/IC4Us-Zed-Camera-Template","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/saornek%2FIC4Us-Zed-Camera-Template","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/saornek%2FIC4Us-Zed-Camera-Template/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/saornek%2FIC4Us-Zed-Camera-Template/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/saornek%2FIC4Us-Zed-Camera-Template/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/saornek","download_url":"https://codeload.github.com/saornek/IC4Us-Zed-Camera-Template/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/saornek%2FIC4Us-Zed-Camera-Template/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":34481299,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-26T15:22:16.424Z","status":"online","status_checked_at":"2026-06-18T02:00:06.871Z","response_time":128,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"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":["ic4u","jetson-nano","nvidia","object-detection","python","zed-camera","zed2"],"created_at":"2024-11-11T00:02:46.670Z","updated_at":"2026-06-18T07:31:53.307Z","avatar_url":"https://github.com/saornek.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# IC4U's ZED Camera Template\n\nThis repository contains IC4U's object detection related projects code template. This code template can be used for building a custom object detector using the ZED 2i stereo camera, the ZED SDK, and a custom Pytorch weight.\n\n[![Link to my YouTube video!](https://github.com/saornek/IC4Us-Zed-Camera-Template/blob/main/example.png?raw=true)](https://www.youtube.com/watch?v=0KgxXRvYVTQ)\n\nTo see more of IC4U, visit my [YouTube channel](https://www.youtube.com/@Selinoid).\n\n## Getting Started\n - Get the latest [ZED SDK](https://www.stereolabs.com/developers/release/) and [pyZED Package](https://www.stereolabs.com/docs/app-development/python/install/)\n - Check the [Documentation](https://www.stereolabs.com/docs/object-detection/custom-od/)\n\n ## Setting Up \n\n - Clone this repository into your ZED folder\n```bash\ngit clone https://github.com/saornek/IC4Us-Zed-Camera-Template.git\n```\n\n - Then clone Yolov5 into the current folder\n```bash\ngit clone https://github.com/ultralytics/yolov5\n\n# Install the dependencies if needed\ncd yolov5\npip install -r requirements.txt\n```\n\n- Download a model file (or prepare your own) https://github.com/ultralytics/yolov5/releases\n\n```bash\n# Downloading by commmand line\nwget https://github.com/ultralytics/yolov5/releases/download/v6.0/yolov5m.pt\n```\n- Prepare your Labels CSV file.\n\nI chose to use a CSV file so, I could match the label ID of each detected object with its corresponding label name.\nIn this code, I researched what dataset yolov5 model uses. I saw that it used the MSCOCO dataset, so I created a CSV file with the object's IC4U required for its intelligent disobedience feature. \n\nYou can adjust or create a CSV file according to your projects requirements.\n\nA CSV file example format:\n```csv\nlabel_id, label\n0, person\n1, bicycle\n2, car\n```\n\n\n## Run the code\n\n*NOTE: The ZED 1 is not compatible with this module*\n\n```\npython detector.py --weights yolov5m.pt # [--img_size 512 --conf_thres 0.1 --svo path/to/file.svo]\n```\n\n## Training your own model\n\nThis sample can use any model trained with YOLOv5, including custom trained one. For a getting started on how to trained a model on a custom dataset with YOLOv5, see here https://docs.ultralytics.com/tutorials/train-custom-datasets/\n\nI have prepared my datasets for IC4U's weights using [Roboflow](https://roboflow.com/). I highly recommend Roboflow for its simplicity and speed in managing and annotating datasets.\n\n## Contributing\nContributions to this repository are welcome.  If you find any bugs or have suggestions for improvements, please feel-free to submit a pull request.\n\n## Acknowledgments\nThank you to Stereolabs for providing the ZED SDK, the custom object detector tutorial and their endless support.\n\n## Support\nFor any questions or support related to this library, you can contact me via the repository issues page.","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsaornek%2Fic4us-zed-camera-template","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fsaornek%2Fic4us-zed-camera-template","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsaornek%2Fic4us-zed-camera-template/lists"}