Browse categories
Explore
Fiverr Pro
English
$
USD
I will build object detection and computer vision with yolo
Product Engineer using Nextjs, FastAPI and No Code Tools
I help startups and founders build modern web apps and MVPs using both no-code and custom code. From Figma to live products, I create fast, scalable, and visually polished websites using Webflow, Fram...
Vetted by Fiverr Pro
A. Moiz Khatri was selected by the Fiverr Pro team for their expertise.
Vetted for
Website Development
About this Gig
Are you looking for a computer vision expert to build smart AI-powered image and video systems? You're in the right place.
I specialize in real-time object detection, image recognition, image segmentation, face recognition, and video analytics using the latest deep learning frameworks from idea to full deployment.
What I deliver:
- Object detection & tracking using YOLOv8 / YOLOv5
- Face recognition & landmark detection
- Image segmentation (UNet, Mask R-CNN)
- Pose estimation using MediaPipe
- OCR extract text from images
- Custom YOLO model training on your dataset
- People & vehicle counting, anomaly detection
- OpenCV image processing pipelines
Tools: PyTorch, TensorFlow, OpenCV, MediaPipe, FastAPI
Industries: retail, security, healthcare, manufacturing, sports
All projects include clean Python code, a README, and a demo video.
Message me before ordering to confirm scope and timeline.
My Portfolio
Other Data Science & ML Services I Offer
FAQ
Do you train custom YOLO models on my own dataset?
Yes , I handle labeling, training, evaluation, and delivery.
What do you deliver?
Python source code, requirements file, README, and a demo video.
Can you deploy the model as an API?
Yes, FastAPI or Flask API with AWS/GCloud deployment is available in Premium.
I don't have a labeled dataset — can you help?
Yes, dataset labeling is available as an add-on using Roboflow or LabelImg.
Do you support live camera or RTSP streams?
Yes, real-time webcam and RTSP stream integration is supported.
