Husan

Computer Vision for Crops

December 2025LiveGitHub

Next.js · React · TypeScript · FastAPI · ONNX Runtime · Computer Vision · ResNet-18 · Three.js

An AI-powered crop stress detection platform that classifies plant conditions from smartphone or drone imagery with a web-first, mobile-friendly workflow.

  1. 1. Context
  2. 2. Problem and Objective
  3. 3. System Architecture
  4. 4. AI Model
  5. 5. Product Experience
  6. 6. Telegram Bot Integration
  7. 7. What This Project Demonstrates

1. Context

Apollo AI is an AI500 Hackathon 2025 Stage 2 submission focused on democratizing precision agriculture by making crop diagnostics accessible from standard phone and drone images.

The project is built as a deployed prototype, combining an interactive product experience with a production-style inference backend.

2. Problem and Objective

Farmers and field operators often lack quick, low-cost diagnostic tools that can be used directly in real-world conditions.

Apollo AI addresses this by providing:

  • Fast image-based crop stress classification
  • A low-friction user experience that works on mobile devices
  • Multiple access paths (web interface and Telegram bot)

3. System Architecture

The platform is split into a modern frontend and a Python inference backend.

  • Frontend: Next.js 15 (App Router), React 19, Tailwind CSS
  • Backend: FastAPI deployed as serverless functions on Vercel
  • Inference runtime: ONNX Runtime for efficient model execution
  • Visualization: Three.js-based interactive 3D Drone Scanner

This architecture supports responsive UX, clear API boundaries, and deployment-ready scalability for prototype usage.

photoappFastAPImodel1capturephoto2POST /predictwebbotweb | bot3preprocess224x224x34resnet1838 classes
A farmer photographs a crop leaf using their phone camera or captures it via drone. The image lands in the Next.js frontend, which provides a responsive, mobile-first upload experience.
How an image moves through the system, from capture to crop diagnosis.

4. AI Model

The classification engine is based on a ResNet-18 model trained on PlantVillage data.

  • Dataset scale: 70k+ images
  • Target: crop stress and disease class detection
  • Reported demo-class performance: up to 99% accuracy

The model pipeline is integrated into a user-facing flow so inference is not isolated from product behavior.

TomatoHealthyTomatoEarly BlightPotatoLate BlightCornCommon RustAppleBlack Rotclassifying... 1/5
Tomato leaf classified as Healthy with 98.7% confidence in 11 ms.confidence98.7%
Five samples classified by the ResNet-18 model. Confidence scores reflect demo-class performance on the PlantVillage dataset.

5. Product Experience

The frontend emphasizes usability for non-technical users and field-friendly workflows.

  • Mobile-first responsive layouts
  • Glass-morphism visual language for clear, modern UI
  • Dedicated demo route (/demo) for testing classification flow
  • Visual storytelling via 3D scanner interaction

6. Telegram Bot Integration

A Telegram assistant extends access for users who prefer messaging-first interactions.

  • Provides instant analysis support and app access flow
  • Uses a polling architecture
  • Runs locally or on a VPS even when web deployment is on Vercel

This makes the platform more reachable across different user behavior patterns.

7. What This Project Demonstrates

Apollo AI demonstrates end-to-end product engineering across ML inference, backend API design, interactive frontend experience, and multi-channel delivery.

It also shows practical deployment thinking: model serving on serverless infrastructure, modern React architecture, and user-facing tooling designed for fast iteration in a hackathon-to-product trajectory.