{"id":13617205,"url":"https://github.com/intel-iot-devkit/concurrent-video-analytic-pipeline-optimization-sample-w","last_synced_at":"2025-04-14T03:33:23.810Z","repository":{"id":72159199,"uuid":"234423082","full_name":"intel-iot-devkit/concurrent-video-analytic-pipeline-optimization-sample-w","owner":"intel-iot-devkit","description":"Create a concurrent video analysis pipeline featuring multistream face and human pose detection, vehicle attribute detection, and the ability to encode multiple videos to local storage in a single stream.","archived":true,"fork":false,"pushed_at":"2023-01-03T22:56:17.000Z","size":3702,"stargazers_count":6,"open_issues_count":5,"forks_count":4,"subscribers_count":12,"default_branch":"master","last_synced_at":"2024-11-08T01:38:55.848Z","etag":null,"topics":["computer-vision","deep-learning","edge","edge-ai","edge-computing","image-recognition","inference","intel","live-demo","machine-learning","object-detection","openvino","pretrained-models","real-time","reference-implementation","video"],"latest_commit_sha":null,"homepage":"https://software.intel.com/content/www/us/en/develop/topics/iot/reference-implementations/concurrent-video-analytic-pipeline-optimization.html","language":"C++","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"bsd-3-clause","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/intel-iot-devkit.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}},"created_at":"2020-01-16T22:20:19.000Z","updated_at":"2024-04-22T08:24:31.000Z","dependencies_parsed_at":"2023-05-22T12:00:26.274Z","dependency_job_id":null,"html_url":"https://github.com/intel-iot-devkit/concurrent-video-analytic-pipeline-optimization-sample-w","commit_stats":null,"previous_names":[],"tags_count":4,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/intel-iot-devkit%2Fconcurrent-video-analytic-pipeline-optimization-sample-w","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/intel-iot-devkit%2Fconcurrent-video-analytic-pipeline-optimization-sample-w/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/intel-iot-devkit%2Fconcurrent-video-analytic-pipeline-optimization-sample-w/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/intel-iot-devkit%2Fconcurrent-video-analytic-pipeline-optimization-sample-w/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/intel-iot-devkit","download_url":"https://codeload.github.com/intel-iot-devkit/concurrent-video-analytic-pipeline-optimization-sample-w/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248815795,"owners_count":21165983,"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","deep-learning","edge","edge-ai","edge-computing","image-recognition","inference","intel","live-demo","machine-learning","object-detection","openvino","pretrained-models","real-time","reference-implementation","video"],"created_at":"2024-08-01T20:01:38.309Z","updated_at":"2025-04-14T03:33:18.800Z","avatar_url":"https://github.com/intel-iot-devkit.png","language":"C++","funding_links":[],"categories":["HarmonyOS"],"sub_categories":["Windows Manager"],"readme":"# DISCONTINUATION OF PROJECT #\nThis project will no longer be maintained by Intel.\nIntel has ceased development and contributions including, but not limited to, maintenance, bug fixes, new releases, or updates, to this project.\nIntel no longer accepts patches to this project.\n# Concurrent Video Analytic Pipeline Optimzation Sample \nSupport users to quickly setup and adjust the core concurrent video analysis workload through configuration file to obtain the best performance of video codec, post-processing and inference based on Intel® integrated GPU according to their product requirements.\nUsers can use the sample application video_e2e_sample to complete runtime performance evaluation or as a reference for debugging core video workload issues.\n\n## Typical workloads\nSample par files can be found in par_files directory. Verfied on i7-8559U. Performance differs on other platforms.\n* 16 1080p H264 decoding, scaling, face detection inference, rendering inference results, composition, saving composition results to local H264 file, and display\n* 4 1080p H264 decoding, scaling, human pose estimation inference, rendering inference results, composition and display\n* 4 1080p H264 decoding, scaling, vehicle and vehicle attributes detection inference, rendering inference results, composition and display\n* 16 1080p RTSP H264 stream decoding, scaling, face detection inference, rendering inference results, composition and display.\n* 16 1080p H264 decoding, scaling, face detection inference, rendering inference results, composition and display. Plus 16 1080p H264 decoding, composition and showing on second display. \n* Multi-display support with multi par file, eg : video_e2e_sample -par ..\\par_file\\n4_1080p_fd.par ..\\par_file\\n4_1080p_vd.par\n\n# Dependencies\nThe sample application depends on [Intel® Media SDK](https://software.intel.com/en-us/media-sdk/), [Intel® OpenVINO™](https://software.intel.com/en-us/openvino-toolkit) and [FFmpeg](https://www.gyan.dev/ffmpeg/builds/ffmpeg-release-full-shared.7z)\n\n# FAQ\nSee doc/FAQ.md\n\n# Table of contents\n\n  * [License](#license)\n  * [Documentation](#documentation)\n  * [System requirements](#system-requirements)\n  * [How to build](#how-to-build)\n  * [How to run demo](#how-to-run-demo)\n  * [Known limitations](#know-limitations)\n\n# License\nThe sample application is licensed under MIT license. See [LICENSE](./video_e2e_sample/LICENSE) for details.\n\n# Documentation\nSee [user guide](./doc/concurrent_video_analytic_sample_application_user_guide.pdf)\n\n# System requirements\n\n**Operating System:**\nWindows 10 Enterprise\n\n**Software:**\n* [MediaSDK 2020 R1](https://software.intel.com/en-us/media-sdk/)\n* [OpenVINO™ 2021.3](https://software.intel.com/en-us/openvino-toolkit)\n\n**Hardware:** \n* Intel® platforms including Core™ or Atom™ processors which supported by the MediaSDK 2020 R1 and OpenVINO 2021.3. \n* For Media SDK, the major platform dependency comes from the Intel GPU driver.\n* For OpenVINO™, see details from here: https://software.intel.com/en-us/openvino-toolkit/documentation/system-requirements\n\n# How to build\n\nRun .\\script\\compile.bat to build sample application video_e2e_sample. \n\nPlease refer to ”Installation Guide“ in [user guide](./doc/concurrent_video_analytic_sample_application_user_guide.pdf) for details.\n\n# How to run demo\n\nBefore this, you should download the IR file by the .\\script\\download_IR_file.py to .\\video_e2e_sample\\model\\ folder\nReplace the video clips in par file. Such as download face detection demo video from https://github.com/elainewangprc/testvideo/ with 1080p.h264, \nand use above video clips to replace the file location in .\\par_file\\*.par, (-i::h264 content\\1080p.h264)\nThe run: cd .\\script\\ ;  Run_FD_test.bat\n\n# Known limitations\n\nThe sample application has been validated on Intel® platforms Skylake(i7-6770HQ), Coffee Lake(i7-8559U i7-8700) and Whiskey Lake(i7-8665UE).\n\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fintel-iot-devkit%2Fconcurrent-video-analytic-pipeline-optimization-sample-w","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fintel-iot-devkit%2Fconcurrent-video-analytic-pipeline-optimization-sample-w","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fintel-iot-devkit%2Fconcurrent-video-analytic-pipeline-optimization-sample-w/lists"}