Until now, most defence-oriented immersive systems relied primarily on VR and AR interfaces to visualize

mission data, maps, and environmental cues. These solutions offered useful overlays but lacked the capability to

perform real-time threat identification directly from the soldier’s visual feed. Building on these earlier

technologies, the proposed system introduces a next-generation Extended Reality (XR)–based tactical platform

that not only displays information but also performs intelligent on-ground analysis using integrated image

Keywords: Extended Reality (XR), Edge-AI, Facial Recognition, Threat Detection

High-risk operational environments such as military battlefields, disaster response zones, counter-terrorism

missions, and hazardous industrial sites require rapid decision-making, accurate situational awareness, and

seamless communication among personnel. In such scenarios, the ability to gather, process, and interpret large

volumes of data in real time can significantly influence the success and safety of an operation. Traditional tactical

support systems rely heavily on manual observation, radio communication, and centralized monitoring systems.

While these approaches have served operational needs for decades, they often suffer from limitations such as

delayed information flow, restricted field visibility, and increased cognitive load on personnel. As operations

become more complex and dynamic, there is a growing need for advanced technological solutions that enhance

mission updates directly within their field of view. This immersive visualization allows personnel to access

critical information without diverting attention from their surroundings, thereby improving operational

efficiency and safety.

Edge Artificial Intelligence further enhances the capabilities of such systems by enabling real-time data

processing at the source of data generation rather than relying solely on centralized cloud servers. In high-risk

operations, communication networks may be unreliable, delayed, or even unavailable. Edge-AI addresses this

challenge by performing intelligent data analysis directly on local devices such as embedded processors, drones,

smart cameras, or sensor nodes. These AI algorithms can detect threats, recognize objects, analyze movement

patterns, and identify anomalies in real time. By reducing dependency on remote processing and minimizing

latency, Edge-AI ensures faster response times and improved reliability in mission-critical situations.

the collected data and transmit only relevant insights or alerts to field operators, significantly reducing

information overload. The integration of XR technology with Edge-AI and distributed sensor networks forms a

powerful framework for intelligent tactical support. In this system architecture, sensor nodes continuously

monitor the operational environment and feed data into local edge computing modules. Edge-AI models analyze

the incoming data to identify potential threats such as suspicious movements, hazardous environmental

conditions, unauthorized access, or structural instability. Once a threat or anomaly is detected, the information

is transmitted to XR devices worn by field personnel. Through augmented visual overlays, operators receive

instant alerts, threat markers, navigation cues, and recommended actions directly within their visual field.

This integrated system provides several advantages over conventional tactical support methods. First, it

significantly improves situational awareness by combining real-time sensor data with immersive visualization

The main objective of the proposed Extended Reality (XR)-Based Tactical Support System integrating

Edge-AI Threat Detection and a Distributed Sensor Network is to enhance situational awareness and

improve decision-making during high-risk operations. The system aims to collect real-time environmental data

using a network of distributed sensors and analyze it using Edge-AI algorithms for fast and accurate threat

detection. The identified threats and critical information are then delivered to field operators through XR devices

such as augmented reality glasses or head-mounted displays. This approach enables personnel to visualize

important alerts, navigation guidance, and operational data directly in their field of view, thereby reducing

response time, improving safety, and increasing the overall efficiency and effectiveness of mission-critical

operations in hazardous environments.

interaction and situational awareness, it lacked intelligent data processing and real-time threat detection

capabilities.

This study proposed an AI-based surveillance system using deep learning models for object detection. The

system demonstrated high accuracy in identifying objects and activities in real time. However, the processing

was cloud-dependent, leading to higher latency and reduced efficiency in critical scenarios.

This research explored the use of Edge-AI in embedded systems for real-time decision-making. By deploying

AI models on edge devices, the system reduced latency and improved response time. However, it was limited to

single-device operation and did not include visualization through XR technologies.

This study implemented a distributed sensor network for environmental and security monitoring. The system

This work proposed an AIoT-based smart surveillance system combining IoT sensors and machine learning

algorithms. The system improved anomaly detection and automation. However, it did not include immersive XR

visualization or real-time edge processing.

This study introduced an edge-enabled intelligent monitoring system for high-risk environments. It demonstrated

low-latency processing and efficient communication between devices. However, the system lacked integration

with XR interfaces and multi-sensor fusion for enhanced situational awareness.

 The system introduces an XR-enabled vision module that captures real-time images inside the structure and

“unknown person detected,” supporting fast tactical decisions.

 Integrated multi-source intelligence from the XR unit and the base station creates a real-time cooperative

defence network, improving safety, coordination, and operational efficiency in high-risk missions.

This block represents the wearable device used by the operator in the field. Its primary function is to capture

real-time visual data, process it using Edge-AI, and display information through an immersive interface.

 Key Components: It includes a camera and lens for image acquisition, an XR microcontroller (Wi-Fi

enabled) for central control, and an OLED display for showing alerts.

sensor for detecting physical disturbances. It also contains manual inputs like an emergency key.

 Output Indicators: The base station provides feedback via an LCD display, an emergency status LED, and

a buzzer for audible alarms.

Both nodes are interconnected via Wi-Fi enabled microcontrollers, allowing them to synchronize alerts and

intelligence in real time

The proposed system is designed as an integrated Extended Reality (XR)-based tactical platform combined with

Edge-AI processing and a distributed sensor network to enable real-time threat detection and situational

awareness.

Initially, the XR headset equipped with a camera module captures real-time visual data from the soldier’s field

of view. The captured images are pre-processed at the edge device to enhance quality and reduce noise, ensuring

reliable input for further analysis. These images are then passed to an embedded Edge-AI facial recognition

model, which extracts facial features and compares them with entries stored in a secure, encrypted database of

known suspects.

OLED Display: The processed information is displayed on a compact OLED display, which acts as the XR

interface. The operator can view alerts, threat notifications, or mission information directly through the display

integrated with the XR device.

The physical realization of the proposed system consists of two distinct hardware assemblies: the Extended

Reality (XR) Field Unit and the Base Station Monitoring Node. The prototype demonstrates the seamless

integration of Edge-AI processing with immersive visualization.

The field-deployed unit is designed as a wearable head-mounted display (HMD) integrated with high-resolution

imaging sensors.

 Vision Subsystem: A micro-camera module paired with an optical lens is mounted on the frame to provide

a continuous first-person visual feed.

 Intelligent Processing: The unit houses an onboard microcontroller that executes Edge-AI algorithms for

The Base Station acts as the centralized intelligence and alert hub for the operation.

 Real-Time Threat Visualization: As shown in the prototype interface, the system utilizes a graphical user

interface (GUI) to display the Edge-AI output. When a suspect is identified, the system renders a bounding

box and identity confirmation.

 Data Synchronization: A Wi-Fi-enabled communication link ensures that images captured by the field

unit are instantly transmitted to the station for secondary verification and database logging.

 Alert Mechanisms: The physical base station is equipped with an LCD panel for status monitoring, along

with a buzzer and emergency LED to provide immediate audible and visual notifications of detected

anomalies.

The AI-based facial recognition model demonstrated a high level of accuracy in identifying known individuals

from the database.

The system achieved an average recognition accuracy of 90–95% under controlled lighting conditions.

In moderate real-world conditions (varying illumination and partial occlusion), the accuracy remained above

85%, ensuring reliable field usability.

This confirms that integrating Edge-AI directly within the XR platform significantly improves real-time threat

identification compared to conventional AR/VR systems.

The implementation of Edge-AI enabled on-device processing without relying entirely on cloud infrastructure.

The average detection and alert generation time was observed to be within 1–2 seconds, which is suitable for

Contextual information linked to detected individuals

This immersive visualization improved the soldier’s decision-making capability without causing cognitive

overload.

The distributed sensor network enabled reliable data transmission between the field unit and the control center.

Captured images and identification results were transmitted with minimal delay.