Case 06 · Wonder Cement · Spatial Computing & Civil Engineering AR

Augmented Reality Civil Estimator with LiDAR Spatial Mesh

Instant construction site volumetric calculation and automated material estimation.

±2%

Measurement Accuracy

Calibrated vs laser rangefinders

100%

On-Device Mesh

LiDAR spatial polygon calculation

100k+

Contractors

Active masons & builders onboarded

< 3s

Instant BOM

Complete concrete volume calculation

01

The Engineering Challenge

Site contractors, builders, and masons in developing construction sectors frequently miscalculate structural concrete requirements, resulting in either costly material over-ordering or project delays from mid-pour shortages. Manual tape-measure estimates on uneven ground were slow, imprecise, and prone to calculation error.

Lead Spatial AR Engineering & Backend Partner

Cross-Platform Mobile & Native Spatial Computer Vision

WebDior engineered the AR spatial scanning subsystem, native C++ computer vision plane triangulation, and the backend cloud sync connecting site estimates to Wonder Cement's SAP ERP order dispatch system.

Key Engineering Deliverables

  • Flutter cross-platform application with native MethodChannels for ARCore & ARKit
  • Custom C++ OpenCV polygon triangulation calculating non-rectangular room areas
  • On-device TensorFlow Lite civil estimator computing cement bags, sand, and aggregate
  • FastAPI integration layer syncing site material estimates directly to SAP ERP dealers
02

Production Architecture Blueprint

Spatial AR SubsystemVerified Spec

Native ARKit LiDAR & ARCore depth mesh stream accessed via MethodChannels

Standard: Real-time plane detection and vertex tracking on iOS & Android

Provides accurate geometric boundaries regardless of site floor irregularities.

C++ Geometry PipelineVerified Spec

Custom OpenCV 3D polygon triangulation and polygon extrusion algorithms

Standard: Sub-50ms execution on standard mobile processors

Calculates precise cubic volume for complex non-rectangular foundations.

Civil Material EngineVerified Spec

IS 456 concrete mix ratio formulas (M20, M25, M30 grades) with dry volume factor

Standard: ±2% volume variance compared to physical laser surveying

Provides trustworthy bag counts that site contractors rely upon for ordering.

SAP Procurement GatewayVerified Spec

FastAPI middleware connecting approved contractor BOMs to SAP ERP

Standard: Automated dealer routing and inventory reservation within 5 seconds

Closes the loop from mobile site scan to delivered cement bags at the jobsite.

03

Technologies & Frameworks

Flutter

Mobile App

ARKit

Spatial AI

ARCore

Spatial AI

C++

OpenCV Mesh

TensorFlow

Estimation ML

FastAPI

Cloud API

SQLite

Offline Sync
04

Technical Implementation Deep-Dive

01

Spatial Computer Vision

LiDAR Point Cloud Mesh and Plane Segmentation

Active construction environments present challenging visual conditions: dusty surfaces, harsh daylight, and uneven debris. We engineered a native AR subsystem that fuses visual odometry with LiDAR depth point clouds.

The system automatically detects floor planes, structural columns, and wall boundaries, projecting a responsive holographic wireframe that guides the contractor through the scan.

Real-time spatial plane detection calibrated to ±2% accuracy against laser meters.
02

Civil Engineering Logic

From 3D Mesh to Exact Cement Bag Count

A raw area measurement is not enough to order concrete. Structural slabs require converting wet geometric volume to dry material ratios, accounting for cement grades (M20, M25), rebar displacement, and standard shrinkage coefficients.

Our civil engine processes the scanned 3D polygon, applies verified engineering standards, and produces a complete bill of materials—specifying exact cement bags, gravel volume, and water requirements.

03

ERP Integration

Offline-First Sync to SAP Dealer Supply Chains

Construction sites often suffer from weak cellular connectivity. The app stores all spatial meshes, project estimates, and contractor profiles in an encrypted local SQLite database.

Once the device detects connectivity, estimates sync to Wonder Cement's SAP ERP backend, alerting the nearest regional dealer to dispatch the required bags directly to the jobsite.

05

Measurable Business Impact

±2% Accuracy

Spatial measurement accuracy verified against laser rangefinders

100k+ Users

Contractors, builders, and masons onboarded onto e-Sampark

< 3s

Instant bill of materials calculation for complex foundation shapes

Explore Applied AI & NLP
06
Case 01 · ASTRA

Autonomous Options Trading & DARWIN∞ Research Engine

A production algorithmic trading platform featuring the DARWIN∞ evolutionary research engine, sub-second strike selection, and walk-forward validation across 5-year tick archives.

Architecture: DARWIN∞ + Async Bridge · P95 execution: 1.4s / order loop

Case 02 · NIKE Retail Innovation

Autonomous In-Store Kiosk with Geo-Inventory Mesh & Spatial AR

A tamper-proof in-store kiosk operating system integrating RealityKit 3D apparel inspection, conversational styling assistants, and sub-second geo-tagged cross-store inventory lookup.

Display engine: SwiftUI + RealityKit 60fps · Inventory lookup: Sub-second geo mesh

Case 03 · Kronos

Systematic Perpetual Futures Platform with 3-Tier Risk Gates

A high-performance crypto perpetuals trading system on Hyperliquid L1, featuring an asynchronous Rust execution loop, 3-tier risk gates, and a 2.51 Calmar ratio.

Execution loop: Rust async tokio · Performance: 77.7% CAGR / 2.51 Calmar

Case 04 · AI Outreach

Multi-Tenant B2B Outreach Engine with Model Gateway

A multi-tenant B2B outreach SaaS platform built with Next.js and NestJS, featuring row-level security, resilient multi-LLM failover, and zero-reputation-loss email deliverability.

Backend architecture: NestJS + Postgres RLS · AI Gateway: Claude, GPT-4o, Gemini auto-failover

Case 05 · Kempinski Hotels

Next-Gen In-Room iPad Operating System for Luxury Hospitality

A custom native iPadOS operating system for Kempinski Hotel Mall of the Emirates, integrating interactive 3D mall exploration, Opera Cloud PMS, and in-room service booking.

Client architecture: SwiftUI + Jamf Pro ASAM · PMS integration: Oracle Opera Cloud

07Start your project

Let's build your
next product.

Have a project in mind or need senior engineers to scale? Tell us what you're building. We'll get back to you within 24 hours with timeline estimates and a clear plan.

01

Discovery call

A 30-minute working session to understand your product goals, technical needs, and timeline.

02

Actionable roadmap

Within 48 hours, you receive a clear scope, architecture plan, and milestone budget.

03

Weekly delivery

Senior engineers begin shipping working, production-ready software in transparent weekly sprints.

hello@webdior.comDelhi, IN — working worldwideBooking Q3 2026