Item
RuggedMilitary Jetson Computer
NV300-CU
Military Jetson Computer
[7STARLAKE]
Equipped with a multi-sensor fusion engine, the AV600-CU-A20 integrates radar, RF detection, electro-optical (EO), and infrared (IR) sensors to provide a comprehensive airspace security solution.
Edge AI Platform
Integrated with the NVIDIA® Jetson AGX Orin (64GB), delivering up to 275 TOPS of AI performance for next-gen autonomous and uncrewed mission-critical applications.
SFF & SWaP
Ultra-compact and lightweight, SWaP-optimized for integration and deployment in highly space-constrained vehicles.
Open Modular Architecture
Jetson AGX Orin and SMARC x86-based architecture/processor options. Robust IO and configuration options, including multiple USB 3.0, GbE, serial, display, video capture, GPS, GPIO.
MIL-STD 810 Rugged
Engineered for austere environments. -20°C to +50 °C operating temp, passive cooled. Fully sealed. MIL-STD-810H, MIL-STD-461G, MIL-STD-1275E/704F.
Model
NV300-CU
Vendor
7STARLAKE
Category
Rugged Defense Products
Product Group
Military Jetson Computer
Consulting
Requirements analysis and custom system design
Implementation
Integration guidance and lifecycle technical support
Verification
Testing against specifications and industry standards
Features
- Counter UAV Visulation Platform with Multi-Sensors Data Fusion
- NVIDIA® Jetson AGX Orin 32G/64G LPDDR5 DRAM
- Data Fusion : 2 CH 3G-SDI NVENC H.264 Low Latency (options)
- Data Input : 1x10G SFP+ 2xLAN , 8xCH GMSL 2.0 (options)
- Connectivity : CAN Bus+1x RS232/422/485 Support
- IP65 Classified with DTL38999 Connector (options)
- DC-DC 12V~30V, Options 18V~36V with MIL-461 EMI Filter
- 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 Sine Wave
- MIL-STD-810 Shock Method 516.6: ◎Acceleration: 40G
- Extended Temperature -20°C to +55°C
Technical Profile
Unparalleled Sensor Fusion and Multi-Video Data Input
Equipped with a multi-sensor fusion engine, the AV600-CU-A20 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:
● 3G-SDI, HD-SDI, and 10G Fiber for seamless video transmission ● High-resolution real-time 3D visualization of airspace threats ● AI-driven target classification to distinguish hostile drones from false alarms
Rugged Military-Grade Computer for Extreme Shock and Vibration Resistance
Built to withstand the most extreme battlefield conditions, the NV300 Series is a high-performance rugged computer engineered to meet and exceed MIL-STD-810 for shock, vibration, and environmental resilience. Designed for mission-critical applications, it delivers exceptional durability in combat vehicles, aerospace, and defense operations.
Unmatched Shock & Vibration Resistance
20mm Cannon Shock Resistance: Rigorously tested to endure the intense shock impact of a 20mm cannon firing, ensuring stable operation even under extreme firepower conditions. High-Level Vibration Durability: Certified to withstand continuous high-frequency vibration in armored vehicles, aircraft, and naval environments without performance degradation.
Built for the Battlefield
Ruggedized Aluminum Alloy Enclosure: Heavy-duty conduction-cooled chassis for enhanced thermal management and structural integrity. Secure Mounting & Anti-Vibration Isolation: Engineered with shock-absorbing dampers to protect internal components from mechanical stress. Extreme Temperature & Environmental Protection: Operates reliably in -40°C to 55°C and resists dust, moisture, and battlefield contaminants. MIL-STD-810H & MIL-STD-901D Compliance: Ensures resilience against mechanical shock, sudden impact, and repeated exposure to harsh environments.
NVIDIA® Jetson AGX Orin
Bring your next-gen products to life with the world's most powerful AI computers for energy-efficient autonomous machines. Equipped with an NVIDIA® Ampere® architecture GPU featuring 2048 CUDA® and 64 Tensor Cores, the NV300-1LS64, integrated with the NVIDIA® Jetson AGX Orin module, delivers up to 275 TOPS of AI performance with power configurable between 15W and 60W. Besides, NVIDIA® Jetson AGX Orin™ modules have 8X the performance than Jetson AGX Xavier for multiple concurrent AI inference pipelines, plus high-speed interface support for multiple sensors, making them the ideal solution for a new age of robotics.
NVIDIA® JetPack™ Support
Compatible with NVIDIA® JetPack™ 6.0 and higher, the NV300-1LS64 enables users to harness a comprehensive library of tools for building top-tier inference models. This enhances application performance by accelerating graphics, data processing, and image classification functions which can be tailored to your specific needs.
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. HD-SDI and 3G-SDI are widely adopted standards 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 video input channels, including 4 Channel HD-SDI video channels or 4 Channel 3G-SDI Video Input plus 2 channel SDI sources video output. It generates from 2 up to 4 video output channels while maintaining low latency between input and output channels. The generated output channel provides a Bird's-Eye-View created from 4 SDI input channels, with each output channel selectable into one main channel for enhanced flexibility and functionality.
Detecting Objects in Point Clouds with NVIDIA CUDA-PointPillars
NV300-1LS64 can generate a point cloud, a data set consisting of points within a coordinate system. Each point in a point cloud holds valuable information, such as three-dimensional coordinates (X, Y, Z), color, classification value, intensity value, and time. Point clouds are primarily produced by 3D Lidar systems, which are extensively used in various NVIDIA® Jetson applications, including autonomous driving, perception modules, and 3D modeling. A key application of point clouds is utilizing long-range and high-precision data sets to achieve 3D object detection, which is essential for perception, mapping, and localization algorithms.
GPU acceleration of object detection on video stream using CUDA
NV300 excels in object detection, a crucial technology for applications such as autonomous driving and intelligent video analytics. Achieving high accuracy in object detection necessitates extensive training with large datasets, a task ideally suited for 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 datasets for object detection inference.
Object detection plays a pivotal role in computer vision, as well as in image and 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.
Specifications
System
Content
High performance Processor
Ampere GPU + Arm Cortex-
GPU
64GB: Two graphics processing cluster (GPC) | eight texture processing clusters (TPC) | 2048 NVIDIA® CUDA® cores | 64 Tensor cores Ray-
AI Performance
64GB: Up to 275 Sparse TOPS (INT8)
Memory Type
Jetson AGX Orin 64GB: 64GB 256-bit LPDDR5 DRAM
Expansion Slot
Item
Content
Expansion Slot
1x M.2 Key-
1x I2C, 2x UART, 1x I2S, 2x SPI, 1x CAN
1x Camera Connector (6 CSI camera support)
Display
Item
Content
Graphics Interfaces
1x HDMI 2.0 (max resolution 3840x2160)
Storage
Item
Content
M.2
1x M.2 Key-
64 GB eMMC 5.1 Flash
Ethernet
Item
Content
Controller
2x GLAN
1x 10G (SFP+ Based)
Front I/O
Item
Content
X1
DC12-30 VDC
X2
1x HDMI with D38999
X3
1x USB2.0 with D38999
X4
1x GbE LAN with D38999
X5
1x USB2.0 + 1x RS422 with D38999
Item
Content
Ground Screw
1
X6
2x 3G-
Debug Access Panel
1x Reset Button
1x Recover Button
1x USB type-
1x USB Type-
1x Reboot LED
X7
5x SMA for WiFi/
Power Requirement
Item
Content
Power Input
12V~32VDC
Operating System
Item
Content
Operating System
Ubuntu 20.04 with JetPack 6.0
Physical
Item
Content
Dimensions
250 x 325 x 100 mm (W x D x H)
Chassis
Aluminum AL6061
Heatsink
Aluminum Alloy, Corrosion Resistant.
Finish
Anodic aluminum oxide (Color)
Cooling
Natural Passive Convection/
Ingress Protection
IP65
Environmental
Item
Content
MIL-
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 to 50°C (ambient with air flow)
Storage Temp
-40 to 85°C
Relative Humidity
5% to 95%, non-
Resources