Skip to content
/ DLstream Public

yolov3, yolo12, segmenations, face, pose, keypoints on dlstream

8 stars 0 forks Branches Tags Activity
Star
Notifications You must be signed in to change notification settings

bharath5673/DLstream

BranchesTags

Repository files navigation


Intel DLStreamer – Ultra-Optimized AI Video Analytics Stack (OpenVINO Powered)

🔖 EXCLUSIVE Release – Low-Code • Hardware-Accelerated • Docker-Ready

orchestrator-ready code for seamless integration
YOLO Detection • YOLO Pose • Tracking • ROI Analytics • Multi-Stream Pipelines • Python First
Fully Accelerated · Low Code · Docker Ready · Production Tested

🖥 Recommended System Setup

Component Recommended / Supported
OS Ubuntu 24.04 LTS
OpenVINO Version 2025.4+
DLStreamer Version 2025.0.1.3
Acceleration Intel CPU • iGPU • Intel ARC
Docker Support Yes – OpenVINO Runtime Containers
Bare Metal Support Full

✔️ Supports full XPU execution (CPU + GPU + VPU) ✔️ OAK-D / OAK-Lite / OAK-Pro support (DepthAI + OpenVINO backend) ✔️ Movidius MyriadX / NCS2 optimized ✔️ Multi-stream, multi-model, ROI pipelines ✔️ Python & C++

🤖 Supported OpenVINO Hardware

Intel CPUs

  • 11th/12th/13th/14th Gen Intel Core
  • Intel Xeon scalable
  • Intel Atom (Edge)

Intel Integrated GPUs

  • Intel UHD / Iris / Iris Xe
  • Intel Xe-LP / Xe-HPG
  • Tiger Lake, Alder Lake, Raptor Lake, Meteor Lake iGPU

Intel ARC Discrete GPUs

  • ARC A380 / A750 / A770
  • ARC Pro Series

Intel® Data Center GPUs

⚡ Quick Start (1 Step)

Install OpenVINO runtime → Clone repo → Run QuickTest.sh

Install OpenVINO + DLStreamer

Intel official quick install:

🔗 https://docs.openvino.ai

DLStreamer:

🔗 https://dlstreamer.github.io/get_started)

Clone this Repo and Run Quick Demo

git clone https://github.com/bharath5673/DLstream.git
cd DLstream
bash QuickDemo.sh

Runs instantly with DLStreamer-ready pipelines:

  • YOLO Detection
  • YOLO Pose
  • Multi-model, multi-stream pipelines
  • Region-based analytics
  • Full OpenVINO acceleration
  • YOLO Models Converter

🎯 What This Repo Provides

✔️ Docker-Ready

Run the entire AI video analytics stack inside Intel's official:

  • OpenVINO Runtime Containers
  • DLStreamer Media Analytics Containers

All pipelines run identical in Docker and Bare-Metal.

✔️ DLStreamer Templates (Production Ready)

  • Multi-model pipelines
  • YOLO detection (OpenVINO IR / ONNX)
  • YOLO-pose via OpenVINO
  • Multi-stream tiled GStreamer pipelines
  • Region-based analytics
  • Python GStreamer bindings
  • ❗C++ full application templates
  • Triton-compatible (OpenVINO backend)

✔️ Fully-Optimized & Low-Code

Minimal coding — edit configs and run.

You get:

  • HIGH throughput using XPU execution
  • ZERO CUDA / NVIDIA dependencies
  • End-to-end pipelines optimized for CPU+iGPU

🌟 Showcase Gallery

🔥 Multi-Model Pipeline

🔗 DLStreamer-Configs/MultiModel

🟦 ROI Based Counting (Python)

🔗 DLStreamer-Python/ROI-counting

🟧 YOLO POSE (OpenVINO)

🔗 DLStreamer-Python/Pose/

🟧 YOLO PERSON TRACKING (OpenVINO)

🔗 DLStreamer-Python/tracking/

🟧 SEGMENTATION

🔗 DLStreamer-Python/Pose/

🟧 Face ANALYSIS

🔗 DLStreamer-Python/face/

🟧 CLASSIFICATION

🔗 DLStreamer-Python/classification/

⚡ Quick Demo

cd DLstream
bash QuickDemo.sh

📂 Repo Structure

DLstreamer/
├── demo
│   ├── pedestrian_tracker.gif
│   ├── segmentation.gif
├── demo.gif
├── DLStream-Configs
│   ├── dlstreamer_omz
│   │   ├── models
│   │   │   ├── intel
│   │   │   │   ├── age-gender-recognition-retail-0013
│   │   │   │   │   ├── FP16
│   │   │   │   │   │   ├── age-gender-recognition-retail-0013.bin
│   │   │   │   │   │   └── age-gender-recognition-retail-0013.xml
│   │   │   │   │   ├── FP16-INT8
│   │   │   │   │   │   ├── age-gender-recognition-retail-0013.bin
│   │   │   │   │   │   └── age-gender-recognition-retail-0013.xml
│   │   │   │   │   └── FP32
│   │   │   │   │       ├── age-gender-recognition-retail-0013.bin
│   │   │   │   │       └── age-gender-recognition-retail-0013.xml
│   │   │   │   ├── emotions-recognition-retail-0003
│   │   │   │   │   ├── FP16
│   │   │   │   │   │   ├── emotions-recognition-retail-0003.bin
│   │   │   │   │   │   └── emotions-recognition-retail-0003.xml
│   │   │   │   │   ├── FP16-INT8
│   │   │   │   │   │   ├── emotions-recognition-retail-0003.bin
│   │   │   │   │   │   └── emotions-recognition-retail-0003.xml
│   │   │   │   │   └── FP32
│   │   │   │   │       ├── emotions-recognition-retail-0003.bin
│   │   │   │   │       └── emotions-recognition-retail-0003.xml

│   │   │   ├── yolo11n_openvino_model
│   │   │   │   ├── n
│   │   │   │   │   ├── metadata.yaml
│   │   │   │   │   ├── yolo11n.bin
│   │   │   │   │   ├── yolo11n.json
│   │   │   │   │   └── yolo11n.xml
│   │   │   │   ├── yolo11s.bin
│   │   │   │   └── yolo11s.xml
│   │   │   ├── yolo11n.pt
│   │   │   ├── yolo11s
│   │   │   │   ├── FP16
│   │   │   │   │   ├── yolo11s.bin
│   │   │   │   │   └── yolo11s.xml
│   │   │   │   └── FP32
│   │   │   │       ├── yolo11s.bin
│   │   │   │       └── yolo11s.xml

│   │   ├── openvino_ga_cid
│   │   └── stats
│   └── download_YOLO_models.py
├── DLStream-Python
│   ├── dlstreamer_test_yolo.py
│   ├── dlstreamer_test_yolo_save_vid.py
│   ├── draw_face_attributes.py
│   └── hello_dlstreamer.py
├── inputs
│   ├── 1192116-sd_640_360_30fps.mp4
│   ├── head-pose-face-detection-female-and-male.mp4
│   └── youtube_stream_20250321_151616.mp4
├── Intel_logo.jpg
├── OpenVino.png
├── outputs
│   └── dlstream_output_20251209_072421.mp4
├── QuickDemo.sh                                                   ### main sh file
├── README.md
└── test_dl.py                                                     ### orchestartor running all python demos

🙏 Acknowledgements

               

Massive respect to the Intel Edge AI + OpenVINO community.
Pipelines, models, tracking logic, and deployment flows are inspired by best practices from DLStreamer and open-source AI/ML communities.

🔰 Credits & Sources

🟩 YOLO Ecosystem
🟦 Core AI / CV Architectures
  • OpenVINO Model Zoo
  • OpenCV DNN
  • RepVGG, OREPA, FasterRCNN/SSD papers
  • ONNX Runtime → OpenVINO conversion tools
🟧 Intel DLStreamer & Media Analytics
  • DLStreamer (gst-gva)
  • OpenVINO Execution Provider
  • GStreamer plugins for inference (gvadetect, gvaclassify, gvatrack, etc.)

Documentation: https://dlstreamer.github.io https://docs.openvino.ai

🔵 Tracking, ROI, Multi-Model Inspirations
  • KLT + ByteTrack/DeepSORT concepts
  • GVA ROI analytics
  • Open-source MOT community

⭐ Special Thanks

Thank you to every engineer and researcher contributing to
OpenVINO, DLStreamer, YOLO, tracking algorithms, and computer vision innovation.

This project stands on the shoulders of giants.

About

yolov3, yolo12, segmenations, face, pose, keypoints on dlstream

Topics

opencv tensorflow intel pytorch yolo segmentation face-recognition license-plate-recognition openvino npu detectron2 oak-d dlstreamer yolov8

Resources

Readme
Activity

Stars

8 stars

Watchers

0 watching

Forks

0 forks
Report repository

Releases

No releases published

Packages

No packages published

Languages