Browse categories
Explore
Fiverr Pro
English
$
USD
I will build object detection and tracking system using yolo
Sarab Dar
About this gig
I will build a custom AI object detection and tracking system tailored to your specific requirements using YOLO and OpenCV.
This system is designed to detect, track, and analyze objects in real-time from images, videos, or live IP camera streams (RTSP), making it ideal for surveillance, automation, and intelligent video analytics applications.
I specialize in building practical computer vision solutions that work reliably in real-world environments such as CCTV systems, live camera feeds, and recorded video analysis.
Get to know Sarab Dar
Sarab Dar
ML Engineer
- FromPakistan
- Avg. response time1 hour
Languages
Urdu, English
I’m a Machine Learning Engineer with over a year of hands-on experience building, optimizing, and deploying intelligent systems using Python and modern ML frameworks. My focus is always on creating efficient, scalable, and maintainable solutions that generate measurable business value.
My Portfolio
FAQ
Can you work with live IP cameras or CCTV NVRs?
Yes. I can process live video streams from IP cameras and NVRs using RTSP if the stream URL and access credentials are provided and the camera supports external streaming. If RTSP access is restricted by the device or network, I can work with recorded video instead.
Can you train the model on my custom dataset?
Yes. I can train a custom YOLO model using your dataset to detect specific objects based on your requirements. The dataset you provide me, it's quality and labeling will affect final performance.
Can this system run in real-time?
Yes, I optimize models for real-time performance depending on your hardware (CPU/GPU). If you want a GPU optimized project i would recommend Nvidia so we can move the project to Nvidia's Deepstream.
What do I need to provide to start the project?
You should provide: - Clear project requirements - Dataset (if custom training is needed) - Sample videos or expected input type - RTSP URL (if using live stream)
