Scenario Overview
Edge AI for every camera — object detection, OCR, anomaly discovery. Local inference, real-time, privacy-safe. 1–20+ streams, offline-capable. Deployable across industrial, retail, security & healthcare.
Local Real-Time Inference
Local Real-Time Inference
  • NPU/GPU acceleration, ms response
  • Video stays on-device, privacy compliant
  • Runs offline without network
Multi-Stream Scalability
Multi-Stream Scalability
  • 1–20+ channels at 1080p per device
  • Tiered compute from 26 TOPS to 275 TOPS
  • Horizontal scaling, no bottleneck
Bandwidth-Efficient & Privacy-Safe
Bandwidth-Efficient & Privacy-Safe
  • Only event metadata transmitted, ~tens of KB each
  • On-device auto-redaction, no sensitive data to cloud
  • Dual RTSP / WebRTC output, flexible integration
Application Scenarios
Object Detection

Real-time detection, counting & tracking

YOLO-series models detect people, vehicles & objects, with tracking for entry/exit counts, dwell time & heatmaps. The foundational capability behind most vision applications.


Core Advantages

  • 80+ common classes out of the box, fine-tune for custom categories
  • 1–20+ channels at 1080p real-time per device
  • Tracking, counting, and heatmap post-processing with one click
DemoReference Design
Scene Feature
Person / Vehicle / Object Detection
80+ COCO classes, fine-tunable
Scene Feature
Entry/Exit Counting & Tracking
Bi-dir count, ID tracking, BI-ready
Scene Feature
Zone Heatmap / Line Crossing
Zone heatmaps & line-cross alerts
OCR Text Recognition

On-device OCR & QR — image to data

Edge OCR for chars, digits, serials & QR codes + rules engine. Ideal for industrial batch traceability, license plate recognition & production line serial validation.


Core Advantages

  • Chinese, English, digits, and QR codes — all-in-one recognition
  • Edge inference keeps sensitive text on-device
  • Layer rules engine for format validation and database entry
DemoReference Design
Scene Feature
Industrial Batch Codes
Line code OCR, auto-verified
Scene Feature
License Plate / Container ID
Gate & container ID, fast trigger
Scene Feature
QR / Barcode
QR auto-register, barcode verify
Anomaly Detection

Defects, violations & intrusion detection

Anomaly detection, classification & segmentation models find 'missing' or 'should-not-be-there' targets — surface defects, missing PPE, intrusions, falls. Deploy with few-shot fine-tuning.


Core Advantages

  • Supervised classification + unsupervised anomaly detection — dual approach
  • Fine-tune custom models with just 50 images on SenseCraft
  • Event-triggered local alerts, only tens of KB metadata transmitted
Reference DesignCode
Scene Feature
Surface Defect Inspection
Scratch, missing part & misassembly
Scene Feature
Safety Violation Alerts
Missing PPE & danger zone alerts
Scene Feature
Posture Anomaly
Fall & loiter via 17/33 keypoints
Deployment & Selection
Architecture

Where to place compute: 3 deployment topologies

A video analytics solution combines four types of components — cameras, AI compute nodes, network, and cloud. Depending on where compute resides, deployments fall into three topologies.


Core Advantages

  • All-in-One AI Camera (reCamera / R2130): 1 stream, simplest, plug-and-play
  • Detached Edge Box (J3011 / J4012): 2–6 channels, cost-effective workhorse
  • Multi-Stream Video Hub (J5012 / AGX Orin): 9+ channels, centralized RTSP processing
wikiSelection Guide
Product ImageProductCore PositioningAI Performance (INT8)Cost
Vision V2OEM Custom Board0.04 TOPS~$30
reCameraAll-in-One AI Camera1 TOPS~$80
R2130RPi 5 + Hailo-826 TOPS~$200
J3011Jetson Orin Nano 8G40 TOPS$599
J4012Jetson Orin NX 16G100 TOPS$949
J5012AGX Orin 64G275 TOPS$3149

Right-sizing: choose hardware by channel count

To determine how many 1080p30 streams you can run, look at TOPS and model size. The table below summarizes AI performance and cost across six products.


Core Advantages

  • Channel benchmark: 1080p @ 15 FPS (std real-time); 30+ FPS halves estimate
  • Bottleneck: video decode, not inference — larger models amplify
  • How to choose: 1 ch — reCamera; 2–6 ch — J3011/J4012; 9+ ch or GMSL — J5012
Product ImageProductEthernetUSBMIPI CSIGMSLRTSP Decode (1080p30, H.265)
reCamera×1 (100M)×1——1 stream (on-device)
R2130×1 (GbE)×2×2—~4 streams (RPi 5 VPU)
J3011×1 (GbE)×4×2—11 streams
J4012×1 (GbE)×4×2—18 streams
J5012×4 GbE + ×1 10GbE×4—×844 streams

Which device works with my camera?

The table below summarizes video input interfaces and hardware decoding limits for each device.


Core Advantages

  • IP Cameras: RTSP via Ethernet, channels limited by HW decode ceiling (NVIDIA data)
  • Local Cameras: MIPI CSI (J3011 / J4012) or GMSL (J5012 only, ×8 daughter)
  • Output + Industrial Bus: RTSP / WebRTC output; J4012 / J5012 include CAN + RS-485
Product ImageProductCooling MethodSuitable EnvironmentOperating TemperaturePower Supply
reComputer AI Industrial R2135Active (Fan)Standard Indoor-20~65°CDC 12-19V
reComputer Industrial R2235Passive (Fanless)Dusty/Workshop-20~50°CDC 9-36V Wide
reComputer Super J3011Active (Fan) SuperStandard Indoor-20~60°CDC 12-19V
reComputer Industrial J3011Passive (Fanless) IndustrialDusty/Workshop-20~60°CDC 12V~24V
reComputer Super J4012Active (Fan) SuperStandard Indoor-20~60°CDC 12-19V
reComputer Industrial J4012Passive (Fanless) IndustrialDusty/Workshop-20~60°CDC 12V~24V
reComputer Robotics J5012Active (Fan)Standard Indoor / GMSL-10~60°CDC 19~48V
reServer Industrial J501Passive (Fanless) IndustrialDusty/Workshop-20~60°CDC 12V~36V

Passive vs Active: choose by dust level

Dust level determines cooling: fan (active) for lower cost & sustained full-load; fanless sealed enclosure (passive) for dust, wide temp & voltage — built for harsh environments.


Core Advantages

  • High dust (mining, mills, outdoor) → passive Industrial/Fanless, sealed fanless
  • Indoor (office, retail, lab) → active cooling (Super/AI), fan-cooled better value
  • Naming: J-series 'Industrial' = passive; R2000 'AI' = fan, else fanless
Success Cases
Contact Us
We Are Glad to Be Your Hardware Partner !
Next
Intelligent Video Analytics