{"id":28211974,"url":"https://github.com/sverrenystad/computer-vision","last_synced_at":"2026-02-27T03:01:31.097Z","repository":{"id":291494076,"uuid":"945936231","full_name":"SverreNystad/computer-vision","owner":"SverreNystad","description":"Winter Pole Detection for Autonomous Driving.","archived":false,"fork":false,"pushed_at":"2025-08-27T10:41:43.000Z","size":36352,"stargazers_count":2,"open_issues_count":1,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-10-27T14:43:56.795Z","etag":null,"topics":["computer-vision"],"latest_commit_sha":null,"homepage":"https://www.youtube.com/watch?v=txX2eZbohZM","language":"Jupyter Notebook","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/SverreNystad.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,"zenodo":null}},"created_at":"2025-03-10T11:05:18.000Z","updated_at":"2025-08-27T10:44:32.000Z","dependencies_parsed_at":"2025-05-05T02:09:27.776Z","dependency_job_id":"e228b0c2-d9e2-4839-9ccf-1e0445bb43bd","html_url":"https://github.com/SverreNystad/computer-vision","commit_stats":null,"previous_names":["sverrenystad/computer-vision"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/SverreNystad/computer-vision","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/SverreNystad%2Fcomputer-vision","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/SverreNystad%2Fcomputer-vision/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/SverreNystad%2Fcomputer-vision/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/SverreNystad%2Fcomputer-vision/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/SverreNystad","download_url":"https://codeload.github.com/SverreNystad/computer-vision/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/SverreNystad%2Fcomputer-vision/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":29883111,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-02-26T23:51:21.483Z","status":"online","status_checked_at":"2026-02-27T02:00:06.759Z","response_time":57,"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":["computer-vision"],"created_at":"2025-05-17T18:10:20.525Z","updated_at":"2026-02-27T03:01:31.085Z","avatar_url":"https://github.com/SverreNystad.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# SnowPole Object Detection with LiDAR data and RGB\nThere has been major advancements in Autonomous driving in recent years, attributed to computer\nvision (DL). However, such models are mostly focused on driving in ideal conditions, and thus struggles\nwith challenging conditions like snowy roads. One way to localize the road in winter time is by relying\non the location of snow poles, which are typically erected on either side of the road in areas prone to\nsnow in the winter. Our task here is to perform real time object detection of snow poles, in order to\nfurther develop AD capabilities in winter conditions.\n\nOur goal was the following:\n\n_We wanted to develop a lightweight model that can reliably spot snow poles before the car needs them, while fitting the power/compute budget of an edge device. Meeting this challenge pushes the winter capability of autonomous driving a crucial step closer to production in the Nordics._\n\n## Dataset\nThe dataset was collected by the [NAPLab](https://www.ntnu.edu/idi/naplab) at NTNU.\n\nWe had access to two separate datasets for this task. The first dataset is a selection of natural images\n(RGB), and the second dataset consists of LiDAR images. The LiDAR images are combined as\nRGB images by combining Near-IR, Signal, and Reflectivity channels. Near-IR maps to blue,\nSignal to green, and Reflectivity to red. \nAs redistribution of the dataset is prohibited the images and labels are not in the repository. To reproduce the findings or use the data contact [NAPLab](https://www.ntnu.edu/idi/naplab) at NTNU.\n\n## Our results\n\u003cimg width=\"1920\" height=\"1080\" alt=\"image\" src=\"https://github.com/user-attachments/assets/f30d3d53-7b4e-4ef5-bd1a-94baa69ae34b\" /\u003e\n\u003cimg width=\"1920\" height=\"1080\" alt=\"image\" src=\"https://github.com/user-attachments/assets/9205e7e7-a23f-4aff-88ee-eb928fdefab9\" /\u003e\n\n\n\n## Usage\n\nTrain model on rgb dataset run the following command:\n```bash\npython train-rgb.py\n```\n\nTrain model on lidar dataset run the following command:\n```bash\npython train-lidar.py\n```\n\nTrain model on combined dataset run the following command:\n```bash\npython train-combined.py\n```\n\n### Submission\n\nTo create a submission run the following command:\n```bash\npython submission.py\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsverrenystad%2Fcomputer-vision","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fsverrenystad%2Fcomputer-vision","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsverrenystad%2Fcomputer-vision/lists"}