{"id":22085369,"url":"https://github.com/seieric/gst-dsobjectsmask","last_synced_at":"2026-05-06T22:11:43.789Z","repository":{"id":185519094,"uuid":"585092092","full_name":"seieric/gst-dsobjectsmask","owner":"seieric","description":"📀NVIDIA DeepStream integrated GStreamer Plugin. Mask objects with cuda cores on Jetson boards. Fast and smooth since everything is done on NVMM.🏎","archived":false,"fork":false,"pushed_at":"2023-01-05T02:16:48.000Z","size":5061,"stargazers_count":1,"open_issues_count":0,"forks_count":1,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-03-23T21:47:08.964Z","etag":null,"topics":["cuda","cuda-programming","deepstream","gpu","gstreamer","gstreamer-plugins","instance-segmentation","jetson-agx-orin","jetson-agx-xavier","jetson-tx1","jetson-tx2","jetson-xavier","maskrcnn","nvidia-jetson","nvidia-jetson-nano","opencv","opencv4","resnet","resnet50"],"latest_commit_sha":null,"homepage":"","language":"C++","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/seieric.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":"2023-01-04T09:49:59.000Z","updated_at":"2025-03-20T12:13:17.000Z","dependencies_parsed_at":null,"dependency_job_id":"fa427aaa-73d4-4129-bbd9-062f494f66fa","html_url":"https://github.com/seieric/gst-dsobjectsmask","commit_stats":null,"previous_names":["seieric/gst-dsobjectsmask"],"tags_count":1,"template":false,"template_full_name":null,"purl":"pkg:github/seieric/gst-dsobjectsmask","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/seieric%2Fgst-dsobjectsmask","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/seieric%2Fgst-dsobjectsmask/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/seieric%2Fgst-dsobjectsmask/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/seieric%2Fgst-dsobjectsmask/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/seieric","download_url":"https://codeload.github.com/seieric/gst-dsobjectsmask/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/seieric%2Fgst-dsobjectsmask/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":32713959,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-06T19:35:05.142Z","status":"ssl_error","status_checked_at":"2026-05-06T19:35:03.996Z","response_time":117,"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":["cuda","cuda-programming","deepstream","gpu","gstreamer","gstreamer-plugins","instance-segmentation","jetson-agx-orin","jetson-agx-xavier","jetson-tx1","jetson-tx2","jetson-xavier","maskrcnn","nvidia-jetson","nvidia-jetson-nano","opencv","opencv4","resnet","resnet50"],"created_at":"2024-12-01T01:13:44.107Z","updated_at":"2026-05-06T22:11:43.773Z","avatar_url":"https://github.com/seieric.png","language":"C++","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Gst-dsobjectsmask\n\nThis plugin masks objects detected by NVIDIA nvinfer plugin. Fast and smooth since all the masking processes are done with GPU. Originally forked from [seieric/gst-dsobjectsmosaic](https://github.com/seieric/gst-dsobjectsmosaic).\n\nMust be a better masking solution than masking with nvdsosd.\n![](https://raw.githubusercontent.com/seieric/gst-dsobjectsmask/main/gst-dsobjectsmask.png \"\")\n\n**Note: This plugin is tested with [PeopleSegNet](https://catalog.ngc.nvidia.com/orgs/nvidia/teams/tao/models/peoplesegnet), which is an instance segmentation model. Masking process refers to a object's mask_params of NvDsObjectMeta. Other models (e.g. semantic segmentation models) may not attach mask_params and this wouldn't work as expected.**\n\n**Note: For Jetson only, not works with dGPU.**\n\n## Features\n- Mask objects with cuda\n- Specify class ids for which blur should be applied\n- Fast and smooth processing\n\n### Sample\n![](https://raw.githubusercontent.com/seieric/gst-dsobjectsmask/main/samples/sample.png \"\")\n\n## Gst Properties\n| Property | Meaning | Type and Range |\n| -------- | ------- | -------------- |\n| min-confidence | Minimum confidence of objects to be masked | Double, 0 to 1\n| class-ids | Class ids of objects for which masking should be applied | Semicolon delimited integer array |\n\n## Depedencies\n- DeepStream 6.1\n- OpenCV4 with CUDA support\n## Download and Installation\nIf your environment satisfies the requirements, just run following commands.\n```bash\ngit clone https://github.com/seieric/gst-dsobjectsmask.git\ncd gst-dsobjectsmask\nsudo make -j$(nproc) install\n```\n\n## Example usage\nThis is a brief instruction to test this plugin after installtion.\n1. Download [NVIDIA-AI-IOT/deepstream_tao_apps](https://github.com/NVIDIA-AI-IOT/deepstream_tao_apps) to ```/opt/nvidia/deepstream/deepstream-6.1/sources/apps```.\n2. Download required models for deepstream_tao_apps. Refer to [the documentation](https://github.com/NVIDIA-AI-IOT/deepstream_tao_apps#2-download-models).\n3. Build custom parser in ```/opt/nvidia/deepstream/deepstream-6.1/sources/apps/deepstream_tao_apps/post_processor```.\n4. Run the sample script ```samples/peoplesegnet_test.sh```.\n5. You will get the ```peoplesegnet_test.mp4``` in your curennt directory.","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fseieric%2Fgst-dsobjectsmask","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fseieric%2Fgst-dsobjectsmask","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fseieric%2Fgst-dsobjectsmask/lists"}