SUMIRA ENGINEERING

Digital AI, IoT & Smart Tech

MLNG

-- --- ---- // --:--:-- HRS

MLNG COMPLEX, BINTULU

DIGITAL AI-POWERED
SURVEILLANCE ANALYTICS
IN OSH MANAGEMENT

PROOF OF CONCEPT (POC) OUTCOME REPORT UPDATE

PRESENTATION TO: Management Team

ORGANIZATION: Malaysia LNG Sdn. Bhd. (MLNG)

“Verifying Practical Capability of Digital AI Surveillance Analytics”

Presented by

Ir. Ts. Michael Anggie

Director, Sumira Engineering

AI

MLNG.POC

Company Overview

About Sumira Engineering

Established in 2021, Sumira is a Bumiputera-owned Sarawakian engineering and technology company founded and led by a team of siblings with complementary engineering and industry expertise.

Our multidisciplinary foundation brings together engineering knowledge, industry experience and practical project capabilities, enabling us to support end users, contractors and strategic industry partners through engineering design, project execution, technology integration and operational support.

Core Multidisciplinary Capabilities

01Oil & Gas Engineering
02Water Tech & Process Eng.
03ACMV & Building Services
04Fire Fighting & Protection
05Building Auto & Smart Sys.
06Surveillance, Secu. & Infra.
07Lift & Escalator
08Network & Telecomm
09Digital Auto. Warehouse
10Engineering Fabrication
11Green Energy & Low Carbon
12Robotic & AI

Our Core Focus

DIGITAL AI, IoT & SMART TECHNOLOGY

Engineering Expertise // Intelligent Solutions

Executive Summary

Digital AI Proof of Concept

The Digital AI-Powered Surveillance Analytics Proof of Concept (POC) was conducted at the Malaysia LNG Sdn. Bhd. (MLNG) Complex, Bintulu, specifically within the Contractor Yard (CY)_1 area, including the designated smoking area, to demonstrate the application of Digital AI technology in supporting Occupational Safety and Health (OSH), safety compliance, and security surveillance.

POC Execution Details

  • Location:MLNG Complex, Bintulu (Contractor Yard CY_1 Area & Smoking Area)
  • Client:Malaysia LNG Sdn. Bhd. (MLNG)
  • Execution Date:13th August 2026
  • Technology:MEGVII AI Solution

Site Execution Photo Records

CY_1 FIELD CAPTURES (poc1.jpeg - poc4.jpeg)
POC Photo 1
ENLARGE
01 // PHOTO poc1.jpeg
POC Photo 2
ENLARGE
02 // PHOTO poc2.jpeg
POC Photo 3
ENLARGE
03 // PHOTO poc3.jpeg
POC Photo 4
ENLARGE
04 // PHOTO poc4.jpeg
Primary Goals

POC Objectives

To demonstrate and verify the practical applicability of the currently available Digital AI capabilities for supporting OSH, safety compliance, and security surveillance.

✓

Demonstrate AI capability to analyze surveillance camera feeds and identify predefined events in real time.

✓

Verify face detection and face recognition capabilities within the designated surveillance area.

✓

Verify basic PPE compliance detection.

✓

Verify mobile phone usage detection.

✓

Verify intrusion and access-related detection.

✓

Verify perimeter monitoring via AI-based detection across defined perimeter boundaries.

✓

Verify smoking detection capability outside the designated smoking areas.

✓

Demonstrate generation of AI events and alerts following successful detections.

Parameters

POC Scope & Testing Boundaries

8 Functional Areas Assessed

1 Personnel ID
5 Unauthorized Person
2 Basic PPE Compliance
6 Perimeter Monitoring
3 Mobile Phone Usage
7 Smoking Compliance
4 Intrusion/Access
8 Event/Alert Generation

Capability Demonstration

This POC was conducted to demonstrate AI detection capabilities available within the system configuration at the time of testing. It serves as a practical capability demonstration and does not constitute a full-scale operational deployment or final performance acceptance.

AI Parameter Evaluation Matrix

POC VALIDATION & DETECTION RESULTS

Demonstrated Parameters

0

/ 8 100% VERIFIED

Face Detection

Evaluation of detection & recognition capability.

ACHIEVED

Safety Helmet

Detection of personnel missing safety helmets.

ACHIEVED

Face Mask

Detection of personnel missing face masks.

ACHIEVED

Mobile Phone

Detection of personnel operating a mobile phone.

ACHIEVED

Intrusion

Movement into defined restricted areas.

ACHIEVED

Unauthorized Person

Persons without required authorization.

ACHIEVED

Perimeter

Movement across defined boundaries.

ACHIEVED

Smoking Detection

Detection within non-designated areas.

ACHIEVED
Attachment 1

Visual Evidence & Captures

Real-time AI detection snapshots from the MEGVII AIoT Engine during the POC at MLNG Complex.

Face Detection
ENLARGE
01 // DETECTION

Face Detection & FR

No Helmet
ENLARGE
02 // PPE VIOLATION

PPE Detection (Safety Helmet)

Mobile Phone
ENLARGE
03 // BEHAVIORAL

Mobile Phone Usage

No Mask
ENLARGE
04 // HEALTH OSH

PPE Detection (Face Mask)

Intrusion Personal
ENLARGE
05 // SECURITY

Intrusion - Personal

Intrusion Vehicle
ENLARGE
06 // VEHICLE

Intrusion - Vehicle

Perimeter Detection
ENLARGE
07 // BOUNDARY

Perimeter Boundary

Smoking Detection
ENLARGE
08 // COMPLIANCE

Smoking Detection

Observations & Conclusion

POC Strategic Summary & Way Forward

Key Observations

6 CORE FINDINGS

01 AI Feasibility Demonstrated

AI & computer vision are applicable to the MLNG environment.

02 Wider Application Potential

Opportunity to expand beyond CY1 and current use cases.

03 Existing Infrastructure Opportunity

Existing CCTV and network infrastructure can potentially be leveraged.

04 Platform Development Opportunity

Integrated dashboard, analytics, alerts and reporting can enhance the solution.

05 Progressive Deployment

Phased implementation allows validation before wider deployment.

06 Business Value Opportunity

Safety, operational and financial benefits can be further quantified.

Conclusion & Way Forward

FROM POC TO SCALABLE DIGITAL AI

01 — DEMONSTRATE

AI capability validated in MLNG environment

✓
↓
02 — EXPAND

Broader coverage & additional AI use cases

→
↓
03 — INTEGRATE

Digital AI dashboard, alerts, analytics & reporting

→
↓
04 — QUANTIFY

Safety, operational, productivity & financial value

→
↓
05 — SCALE

Investment-ready implementation across MLNG

★

“From Proof of Concept → Proof of Value → Full-Scale Implementation.”

Value Proposition

ADDED VALUE TO MLNG

Transforming existing surveillance infrastructure into a proactive, intelligent, and highly efficient OSH management asset.

01

Cost Optimisation

Reduce repetitive monitoring effort and optimise utilisation of existing manpower and infrastructure.

02

Enhanced Safety & Risk Reduction

Provide an additional layer of continuous monitoring to support earlier identification of potential safety risks.

03

Improved Operational Efficiency

Automate selected monitoring activities and allow personnel to focus on higher-value tasks.

04

Faster Response & Awareness

Deliver timely digital alerts and information to support faster operational and safety response.

05

Data-Driven Decision Making

Transform visual and operational information into structured data, trends and actionable insights.

06

Scalable & Future-Ready

Start with targeted applications and progressively expand AI capabilities across MLNG based on proven value.

Bottom-Line Statement

“Transforming existing infrastructure and operational data into measurable safety, operational and financial value for MLNG.”

Network System Design Architecture

Edge-to-Admin Topology

Site Location (Field Capture)

MEGVII CCTV 1-6 (Bullet-Type)
CCTV 1
CCTV 2
CCTV 3
CCTV 4
CCTV 5
CCTV 6
HIKVISION CCTV 7-12 (Dome-Type)
CCTV 7
CCTV 8
CCTV 9
CCTV 10
CCTV 11
CCTV 12
POE SWITCH

Site Location Aggregator

── FO cable ──
POE SWITCH

Site Admin Central Switch

Analytics Engine
MEGVII (HEMETV)
AIoT
Edge Processor
MEGVII
AI BOX
Storage Archive
Video Recorder
NVR
Router
LAN Gate

LAPTOP 1

MEGVII Mon.

LAPTOP 2

Hikvision Mon.

Boundaries & Realities

POC LIMITATIONS – MLNG DIGITAL AI POC

Operating parameters and scope boundaries identified during the proof-of-concept phase at MLNG Complex.

01

Limited AI Algorithm Coverage

The POC utilised selected AI algorithms based on the defined use cases, with opportunities to develop additional algorithms for broader operational and OSH applications.

02

Limited Coverage – CY1 Only

The POC was conducted within the selected CY1 area, limiting validation across other MLNG facilities and operating environments.

03

Limited Use Cases

The POC focused on selected AI/OSH applications, while additional use cases remain available for future development.

04

No Integrated Digital AI Dashboard

A fully integrated dashboard was not included in the POC due to budgetary considerations. Therefore, centralised monitoring, analytics, alerts and management reporting were not demonstrated.

05

Limited Scenario Exposure

The POC had limited exposure to the wider range of operating conditions, safety scenarios and abnormal situations that may occur across MLNG facilities.

06

Budgetary / Resource Constraint

The POC was implemented within the allocated budget and resources, limiting the extent of AI development, dashboard implementation and wider deployment.

Strategic Roadmap

FUTURE RECOMMENDATIONS – MLNG DIGITAL AI

Strategic way forward addressing POC boundaries to transition from proof of concept to full-scale enterprise capability.

01

Algorithm Expansion

Develop and deploy site-specific AI algorithms tailored to broader operational and OSH applications (e.g. chemical hazard proximity, heavy machinery interaction, ergonomics).

02

Facility-Wide Rollout

Progressively expand AI surveillance coverage from CY1 to include operational process units, LNG storage tanks, offloading jetties, and perimeter boundaries.

03

Broadened Use Cases

Extend AI applications to turnaround (TAR) operations, routine plant maintenance, contractor permit compliance, and hazardous zone access verification.

04

Integrated AI Dashboard

Implement a centralised safety dashboard featuring real-time multi-channel monitoring, predictive analytics, automated alert routing, and management reporting.

05

Scenario Exposure Testing

Subject AI models to a wider spectrum of operating conditions, adverse weather, night-time lighting, and simulated abnormal emergency events.

06

Phased Investment Model

Adopt a milestone-based deployment roadmap starting with high-priority use cases and progressively expanding investment based on demonstrated operational value.

Strategic Advantage

WHY SUMIRA?

Combining local Sarawak engineering leadership with advanced AI technology for direct, agile, and sustainable execution.

01

Local Implementation Lead

Sarawak-based team providing direct project coordination, implementation and client engagement throughout the project lifecycle.

02

Fast Response & Mobilisation

Local presence enables rapid response, mobilisation and coordination to address technical and operational requirements.

03

No Immigration & Deployment Constraints

Local technical personnel can be deployed directly, avoiding immigration, work-permit and associated deployment requirements for foreign personnel.

04

Strong Understanding of Industrial Requirements

Strong understanding of the local industrial environment, engineering practices, operational requirements and project expectations in Sarawak.

05

Dedicated Local Technical Support

Local technical team available for ongoing service support, troubleshooting, maintenance and coordination throughout implementation and subsequent operations.

06

Supported by Advanced AI Technology

Sumira is supported by MEGVII, an established AI technology company with advanced computer vision and AI capabilities, enabling the application of proven AI technology within industrial environments.

07

Scalable & Investment-Ready Capability

Sumira can lead the progressive development of the Digital AI solution from POC to wider implementation, supported by a clear business case, measurable value and a phased investment roadmap.

Bottom Line

“Sumira leads the local implementation, supported by MEGVII’s advanced AI technology — combining local industrial expertise with proven AI capabilities to deliver a practical, scalable and investment-ready Digital AI solution for MLNG.”

Actionable Info

INTEGRATED DASHBOARD

FROM DATA to SAFETY INTELLIGENCE

The Integrated Dashboard serves as your centralized safety intelligence platform, transforming raw data from multiple sources into actionable insights. This unified system visualizes all data—providing real-time monitoring, automated alerts, comprehensive analytics, and reporting across personnel, contractors, and vendors.

LIVE MONITORING

  • - Camera status
  • - Selected live feeds
  • - Operational locations

AI EVENTS

  • - PPE violation
  • - Restricted area
  • - Vehicle proximity
  • - Intrusion & Smoke

EVENT INFO

Location | Date | Time | Camera | Event Type | Image Capture Evidence

PREVENTIVE ANALYTICS

Statistical summary of performance (daily, weekly, monthly) & anomaly trends.

ONE DASHBOARD. ONE VIEW. ACTIONABLE INFORMATION.

Management does not need to continuously monitor every camera. The system highlights events that require attention.

THE END

DIGITAL AI, IoT & SMART TECHNOLOGY

Engineering Expertise. Intelligent Solutions.

Successfully demonstrating practical AI capabilities for enhanced safety visibility, compliance verification, and operational intelligence.

Sumira Engineering Sdn. Bhd.

POC Verification - MLNG Complex Bintulu

GLOBAL SURVEILLANCE MATRIX

MLNG Bintulu Complex - Video Ingest Wall

MEGVII AIoT CORE // 10G FO LINK DISPLAYING 26 CHANNELS

EVIDENCE CAPTURE

Evidence Snapshot
MLNG BINTULU // CY_1
MEGVII AIoT LOG