I will detect, count and track objects and build custom ai model

India

I speak Hindi, English, Japanese

2 orders completed

Simulation and computer vision engineer

I build simulators and computer vision pipelines. I have delivered a licensed simulator to a paying client, shipped as a packaged installer rather than a demo. My own work includes a lattice-Boltzman...
About this Gig

Send me a short clip and tell me what you need to find. I will check what is possible before you order.


WHAT YOU GET


- Detection: vehicles, people, equipment, livestock, stockpiles, solar panels, roof or facade damage

- Counting and tracking: each object gets an ID, so you get real counts, not duplicates

- Inspection: flagged frames with timestamps, so you only review what matters

- Clear outputs: annotated video, a CSV of every detection, and a short PDF report


HOW I WORK


I use YOLOv8 and YOLO-World for detection and ByteTrack or BoT-SORT for tracking. If a standard model misses your object, I train a custom one on your footage. Everything runs on my own GPU workstation, so your footage never goes to a third-party AI service.


WHY ME


I am a simulation and computer vision engineer from IIT Mandi. I built a detection and tracking framework validated on a 148-clip benchmark, so I care about accuracy you can measure, not just good-looking boxes.


NOT INCLUDED


Flying the drone, live real-time streaming setups, and orthomosaic or 3D mapping (see my mapping gig).

APIs:

Microsoft Computer Vision AI

•

Amazon Rekognition

Expertise:

Image processing

•

Feature learning

Programming language:

Python

•

MATLAB

•

SQL

•

Colab

•

MLflow

Tools:

Jupyter Notebook

•

OpenCV

•

TensorFlow

•

MLflow

•

SimpleCV

•

Colab

Frameworks:

Scikit-learn

•

DeepPy

•

Google ML Kit

•

PyTorch

•

Panda

My Portfolio