I will build custom computer vision and yolo object detection models

R
rahul_adidravid
R
rahul_adidravid
Rahul Adidravid

About this gig

Need to detect, count, track, or read objects in your images or video? I build custom computer vision models that actually run in production - on cameras, edge devices, and the cloud.


 What I build:

 - Object detection and tracking (surveillance, traffic, retail)

 - ANPR / license plate recognition

 - People counting and crowd analytics

 - OCR and text extraction

 - PPE and safety detection


 Why work with me:  

 - Computer Vision Engineer with 5+ years of industry experience

 - Real deployed projects, not just notebooks

 - Edge deployment specialist (Jetson, TensorRT, ONNX, Triton)

 - Source code, documentation, and a demo video with every order

 - Fast replies and clear communication


 My stack: YOLOv5 to v8, OpenCV, DeepSORT, ByteTrack, OCR, PyTorch, TensorFlow, ONNX, TensorRT, NVIDIA Jetson, Triton, Docker, FastAPI.


I also build AI chatbots, RAG systems, and LLM/agent apps.


 What you get:

 1. Quick chat to understand your use case and accuracy goals

 2. Data labeling support if needed

 3. Trained and optimized model

 4. Evaluation report

 5. Deployment as cloud API or on edge

  

 Send me your sample images and what you need to detect, and I will help you get it working.

Get to know Rahul Adidravid

Rahul Adidravid

Computer Vision AI Engineer Object Detection YOLO Edge AI

  • FromIndia
  • Member sinceMay 2024
  • Avg. response time1 hour
  • Languages

    Hindi, English, Gujarati, Tamil
I'm a Computer Vision and AI Engineer with 5+ years of experience building and deploying real-time AI vision systems on edge devices. I work on object detection and tracking (YOLO, DeepSORT, ByteTrack), ANPR, people counting, crowd analytics, and OCR. I specialize in edge AI, deploying optimized models on NVIDIA Jetson with TensorRT, ONNX, Triton, and DeepStream for low-latency live video. I also build AI chatbots and LLM/RAG apps. Tools: Python, OpenCV, YOLO, PyTorch, TensorFlow, Docker, FastAPI. Message me to build your CV solution.