NV300-E

NV300-E

4CH 3G-SDI Military IP65 AGX Orin Computer NV300-E (S32E)

NVIDIA Jetson AGX Orin 32G LPDDR5 DRAM
1 x HDMI + 1 x USB 3.0 + 4 x 3G-SDI
IP65 Sealed with DTL-38999 Connectors
Vehicle Grade DC Input 18-36V
Operating Temperature: -20°C to +50°C
MIL-STD-810 Vibration Method 514.6: ◎Acceleration: 5.0 Grms
MIL-STD-810 Vibration Method 514.6: ◎PSD: 0.01257 g2/Hz
MIL-STD-810 Shock Method 516.6: ◎Wave Form: Half Shine Wave
MIL-STD-810 Shock Method 516.6: ◎Acceleration: 75G

Download

Datasheet

Manual

Get A Quote

Product Content
Technical Profile
Specifications
Order Information

The NV300-E (S32E) AGX Orin Computer is an ultra-small-form-factor rugged edge computing solution designed for autonomous, uncrewed and counter-UAV missions. Built using a Modular Open Systems Approach (MOSA), it features a modular chassis and architecture integrated with the NVIDIA Jetson AGX Orin System-on-Module (SOM), delivering the performance, flexibility, and scalability required for next-generation defense applications. Engineered for austere environments and optimized for size, weight, and power (SWaP), the NV300-E enables seamless integration into highly space-constrained platforms.

Military-Grade Performance

Built with a heavy-duty aluminum enclosure featuring conduction cooling and advanced EMI shielding, the NV300-E (S32E) ensures superior durability and protection against electromagnetic interference (EMI). The system meets the stringent requirements of MIL-STD-461 and MIL-STD-1275E for ground vehicles, making it ideal for high-performance military applications. Equipped with an isolated MIL-STD-461 and MIL-STD-1275E compliant power module, it effectively safeguards against aircraft and ground vehicle voltage surges, spikes, and transients. The combination of EMI shielding and filtering enhances signal integrity, minimizes conducted and radiated emissions, and ensures stable operation in harsh and high-interference environments.

Unparalleled Sensor Fusion and Multi-Video Data Input

Equipped with a multi-sensor fusion engine, the NV300-E integrates radar, RF detection, electro-optical (EO), and infrared (IR) sensors to provide a comprehensive airspace security solution. The system supports multi-video data input, including:

4 Channel 3G-SDI and 10G SFF+ for seamless video transmission
High-resolution real-time 3D visualization of airspace threats
AI-driven target classification to distinguish hostile drones from false alarms

IP65-Rated Protection for Harsh Environments

Designed to withstand extreme conditions, the NV300-E (S32E) features an IP65-rated, rugged aluminum enclosure that offers exceptional resistance to shock, vibration, and environmental hazards. Its conduction-cooled design enhances thermal efficiency, ensuring reliable performance in demanding military and industrial applications. With complete protection against dust ingress and low-pressure water jets, the system delivers optimal functionality even in the most challenging operational settings.

NVIDIA^® Jetson AGX Orin

Equipped with the NVIDIA Jetson AGX Orin module, the NV300-E (S32E) features the NVIDIA Ampere architecture with 1,792 CUDA cores and 56 Tensor Cores, delivering up to 241 TOPS of AI performance within a configurable 15W–60W power envelope. Offering up to 8× the AI performance of Jetson AGX Xavier, it supports multiple concurrent AI inference pipelines and high-speed interfaces for multi-sensor integration, making it ideal for energy-efficient autonomous systems, robotics, and defense edge applications.


Edge AI Platform	SFF & SWaP	Open Modular Architecture	MIL-STD-810 Rugged
Integrated with the NVIDIA Jetson AGX Orin (up to 64GB), it delivers up to 275 TOPS of AI performance for next-gen autonomous and uncrewed mission-critical applications.	Ultra-compact and lightweight, SWaP-optimized for integration and deployment in highly space-constrained vehicles.	Supports NVIDIA Jetson AGX Orin and SMARC x86 processor options, with flexible I/O and configuration capabilities including multiple USB 3.0, GbE, serial, display, video capture, GP, and GPIO interfaces.	Built for austere environments, featuring a fully sealed, passively cooled design. Supports operation from -20°C to +50°C and meets the strict DoD standards MIL-STD-810H, MIL-STD-461G, and MIL-STD-1275E/704F.

SDI (Serial Digital Interface)

AI targeting systems leverage data from computer sensors and various sources to statistically assess potential targets, aggregating information from drone footage, surveillance data, open-source intelligence, and monitored movements and behaviors. This comprehensive approach enables efficient target detection and tracking. Supporting these capabilities, a state-of-the-art embedded hardware system empowers small flying robots to perform real-time onboard computation necessary for object tracking.

In computer vision applications, video processing and display are essential tasks, requiring seamless transmission of video or images from cameras to the host vision system. To achieve this, system designers must select the appropriate video interface standard based on factors like data rates, cable lengths, and power delivery options. 3G-SDI is widely adopted in professional video production and broadcasting environments, supporting resolutions up to 1080p at 30/60Hz and offering data rates up to 3 Gbps. These signals are transmitted via a single 75Ω coaxial cable, making them suitable for applications requiring high fidelity and real-time video transmission, with cable lengths of up to 200m (using RG59/RG6 cables).

Furthermore, the system allows connection to 4 Channel 3G-SDI Video Input while maintaining low latency between input and output channels. The generated output channel provides a Bird's-Eye-View created from four SDI input channels, with each output channel selectable into one main channel for enhanced flexibility and functionality.

CUDA-Based GPU Acceleration for Video Stream Object Detection

The NV300-E (S32E) excels in object detection, a critical technology for applications such as autonomous driving and intelligent video analytics. Achieving high accuracy in object detection requires extensive training on large datasets, a task well suited to the parallel computing capabilities of NVIDIA GPUs. These GPUs are specifically designed to efficiently train large neural networks, enabling the rapid and effective generation of models for object detection inference.

Object detection plays a pivotal role in computer vision and image/ video processing. Achieving top accuracy and fast detection under varying conditions—such as changes in position, scale, illumination, and noise—poses a significant challenge that cannot be effectively addressed by sequential processing on a single-core General Purpose Central Processing Unit (GPCPU). This post outlines the essentials for leveraging NVIDIA GPUs to implement high-performance object detection pipelines quickly and efficiently, addressing the inherent complexities of real-time object detection in dynamic environments.

(Sourced from NVIDIA)

Block Diagram

Appearance

System
High Performance Processor	Ampere GPU + Arm Cortex-A78AE CPU + 32GB LPDDR5 + 64GB eMMC 5.1
GPU	Jetson AGX Orin 32GB: two graphics processing cluster (GPC) \| seven TPC \| 1,792 CUDA cores \| 56 Tensor cores Ray-Tracing cores \| 108 Sparse TOPS \| Maximum Operating Frequency: 939 MHz
AI Performance	32GB: Up to 241 TOPS (INT8)
Memory Type	Jetson AGX Orin 32GB 256-bit LPDDR5 DRAM
Expansion Slot
Expansion Slot	1 x M.2 M-Key, 1 x M.2 Key-B, 1 x SIM, 1 x 5V Fan 1 x I2C, 2 x UART, 1 x I2S, 2x SPI, 1 x CAN 1 x Camera Connector (6 CSI camera support) 2 x GLAN, 1 x 10G (SFP+ Based)
Display
Graphics Interfaces	1 x HDMI 2.0 (max resolution 3840 x 2160)
Storage
Storage	64GB eMMC 5.1 Flash
Front I/O
X1	18-36 V DC-IN
X2	1 x HDMI with D38999
X3	1 x USB3.0 with D38999
X4~7	4 x 3G-SDI with BNC Connector
Rear I/O
Ground Screw	1 x
Debug Access Panel	1 x Reset Button
	1 x Recover Button
	1 x USB Type-C for Debug
	1 x USB Type-C for Recovery
Power Requirement
Power Input	18V~36V DC-IN
Operating System
Operating System	Ubuntu 22.04 with JetPack 6.2
Physical
Dimensions	250 x 325 x 100 mm (W x D x H)
Weight	8.65 kg
Chassis	Aluminum AL6061
Heatsink	Aluminum Alloy, Corrosion Resistant.
Finish	Anodic aluminum oxide, Color: PANTONE 7743C (Nato Green), Black (optional)
Cooling	Natural Passive Convection/Conduction. No Moving Parts
Ingress Protection	IP65
Environmental (Designed to Meet)
MIL-STD-461 (Optional)
EMC	CE102 basic curve, 10kHz - 30 MHz RE102-4, (1.5 MHz) -30 MHz - 5 GHz RS103, 1.5 MHz - 5 GHz, 50 V/m equal for all frequencies
Reliability	No Moving Parts; Passive Cooling. Designed & Manufactured using ISO 9001/2000 Certified Quality Program
Operating Temp.	-20°C to 50°C (ambient with air flow)
Storage Temp.	-40°C to 85°C
Relative Humidity	5% to 95%, non-condensing

NV300-E (S32E)

IP65 NVIDIA AGX Orin Military Computer, Jetson AGX Orin 64GB, 12-30V DC-IN, Extended Temp. -20°C to +50°C, 64GB eMMC, 4 x 3G-SDI, 1 x HDMI, 1 x USB 3.0