{"id":20461887,"url":"https://github.com/vinay0410/pedestrian_detection","last_synced_at":"2026-03-11T22:02:05.999Z","repository":{"id":166633583,"uuid":"101651814","full_name":"vinay0410/Pedestrian_Detection","owner":"vinay0410","description":"Detects Pedestrians in images using HOG as a feature extractor and SVM for classification","archived":false,"fork":false,"pushed_at":"2022-10-18T13:59:28.000Z","size":2740,"stargazers_count":74,"open_issues_count":5,"forks_count":25,"subscribers_count":5,"default_branch":"master","last_synced_at":"2025-04-13T06:29:44.521Z","etag":null,"topics":["computer-vision","detects-pedestrians","hog-features","human-detection","human-detection-algorithm","pedestrian-detection","person-detection","svm"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"gpl-3.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/vinay0410.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":"2017-08-28T14:30:34.000Z","updated_at":"2024-12-12T06:51:45.000Z","dependencies_parsed_at":"2023-07-26T21:31:31.990Z","dependency_job_id":null,"html_url":"https://github.com/vinay0410/Pedestrian_Detection","commit_stats":null,"previous_names":["vinay0410/pedestrian_detection"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/vinay0410/Pedestrian_Detection","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/vinay0410%2FPedestrian_Detection","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/vinay0410%2FPedestrian_Detection/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/vinay0410%2FPedestrian_Detection/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/vinay0410%2FPedestrian_Detection/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/vinay0410","download_url":"https://codeload.github.com/vinay0410/Pedestrian_Detection/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/vinay0410%2FPedestrian_Detection/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":30404094,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-03-11T21:51:19.558Z","status":"ssl_error","status_checked_at":"2026-03-11T21:50:57.892Z","response_time":84,"last_error":"SSL_read: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"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","detects-pedestrians","hog-features","human-detection","human-detection-algorithm","pedestrian-detection","person-detection","svm"],"created_at":"2024-11-15T12:28:51.724Z","updated_at":"2026-03-11T22:02:05.982Z","avatar_url":"https://github.com/vinay0410.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Pedestrian Detection\n\n**Note:** The code provided may not be compatible with python3. A migration to python3 is in the pipeline.\n\n## Dependencies\n\n* OpenCV\n* scikit-image ```pip install scikit-image==0.14.1```\n* scikkit-learn ```pip install scikit-learn==0.20.2```\n\n## Running Detection\n\nTo test on images, simply run, `python detectmulti.py -i \u003cpath to image\u003e`\n\nFor example, `python detectmulti.py -i sample_images/pedestrian.jpg`\n\n\nFor more options run, `python detectmulti.py -h`\n\nFollowing are some examples,\n\n\n![Pedestrian](.readme_images/before_nms1.png?raw=true \"Sample Results\")\n![Pedestrian](.readme_images/after_nms1.png?raw=true \"Sample Results\")\n\n![Pedestrian](.readme_images/before_nms2.png?raw=true \"Sample Results\")\n![Pedestrian](.readme_images/after_nms2.png?raw=true \"Sample Results\")\n\n\n## Training\nThis code is meant for Training a Pedestrian Detector using [INRIA Person Dataset](http://pascal.inrialpes.fr/data/human/).  \n**Note:** If the above link doesn't work, then the above dataset can be downloaded from [here](https://drive.google.com/file/d/14GD_pBpBsprPiZlkmtXN_y5K72To16if/view?usp=sharing).\n\nDownload, Uncompress and place it in the root of this repository.\n\nThen just run:\n```\nsudo sh fixpng.sh # To fix the broken png files in this dataset.\n```\n**Note:** *The above step is necessary to fix the broken pngs in the dataset, without running this the classifer won't be correctly trained.*\n\nTo train just run:\n```\npython train.py --pos \u003cpath to positive images\u003e --neg \u003cpath to negative images\u003e\n```\nFor INRIA dataset, this would be probably,\n```\npython train.py --pos INRIAPerson/train_64x128_H96/pos --neg INRIAPerson/train_64x128_H96/neg\n```\n\nAfter training, two new files would be created, namely, `person.pkl` and `person_final.pkl`. The former is the pre eliminary detector and the latter is the improved (hard negatively mined) detector.\n\n### Note on Training:\nTraining can use high amounts of memory, so be sure to have a swap space in case of RAM overflows. Also, memory consumption can be reduced by decreasing the maximum number of hard negative windows to be mined. This is defined by the `MAX_HARD_NEGATIVES` global variable in `train.py`.\n\n\n## Testing\nAfter successful training just run:\n```\npython test.py --pos \u003cpath to positive images\u003e --neg \u003cpath to negative images\u003e\n```\nFor INRIA dataset, this would be probably,\n```\npython test.py --pos INRIAPerson/test_64x128_H96/pos --neg INRIAPerson/test_64x128_H96/neg\n```\n\nThis would print `True Positives`, `True Negatives`, `False Positives`, `False Negatives`, `Precision`, `Recall` and `F1 Score`.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fvinay0410%2Fpedestrian_detection","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fvinay0410%2Fpedestrian_detection","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fvinay0410%2Fpedestrian_detection/lists"}