Precise details:
Product Overview
The AI VisionCube Kit is a revolutionary AI visual tracking system designed specifically for drones, integrating high-performance target recognition, dynamic tracking, and anti-jammingcontrol. Through the fusion of deep learning algorithms and high-performance intelligent chips, drones equipped with this kit can achieve automatic target acquisition, stable tracking, and precise trackings in complex electromagnetic environments. This significantly reduces the operational threshold for pilots and greatly improves mission execution efficiency.
Features
-1.2km-Long-Range Recognition
Equipped with single/dual-camera collaborative algorithms and precision optical modules, automatically identifies human/vehicle targets at 1.2km range. Achieves 85% higher recognitionaccuracy than conventional AI systems, enabling beyond-visual-range operations in complexenvironments.
- Multi-Target Recognition
YOLOv7-optimized architecture simultaneously tracks 50+ dynamic targets within FOV. Supports self-training algorithm deployment for customized classification models in defensee andsurveillance scenarios.
- PiPArchitecture
Dual-stream PiP technology combines global situational awareness (main view) with 8x digital zoom tracking (sub-view), allowing real-time environmental analysis and precision strikee decision-making.
- Adaptive Lock-On Tracking
After identifying multiple targets, the drone can correct its heading. The intelligent crosshairr adsorption algorithm will adsorb the tracked target to the central area of the screen, reducing the locking time to 0.5 seconds. This significantly reduces the micro-operation load on the pilot andincreases the locking success rate to 92% in high-speed moving scenarios.
-Dynamic Memory Locking
Integrates temporal prediction models and Kalman filter algorithms to reacquire targets within 3s after occlusion/visual loss. Enhances tracking stability by 40% in dense foliage environments.
- Multi-sensor Compatibility
Switchable visible/thermal sensors with 9650 mV/lux·s D/T-high sensitivity and uncooled thermal imaging. Ensures 24/7 target ID capability from -20℃ to 60℃, defeating camouflage/thermal masking.
- Lightweight Integration
Modular design (<200g) supports BetaFlight open-source flight controllers. Achieves AI capability deployment within 5 minutes via plug-and-play installation, compatible with industrial drones to FPV racers.
-Target Re-locking Support
After locking a target, if you wish to change the target, you can toggle the corresponding channel's remote-control lever. An additional aiming reticle will appear in the VTX image. Use the RCdirection stick to move the aiming reticle to the new target, and then lock it again.
-Expand Search Range
When the crosshairr is not yet aligned with typical targets (e.g., people or vehicles) but you want tolock onto them quickly, simply toggle the corresponding channel on the remote control. Once activated, the drone's flight path will auto-adjust, and the crosshairr will swiftly and precisely snapto the detected targets in the frame.
| Technical Specifications | Details |
|---|
| AI Vision Module Name | AI VisionCube S |
| Target Recognition Type | Default: Human, Vehicle |
| Target Detection Range | Vehicle: 450mHuman: 170m |
| Min Target Tracking Pixel | 16x16 pixels |
| Max Tracking Speed of Dynamic Target | 60km/h |
| Intelligent Adhesive Tracking | Supports crosshairr fuzzy locking for close-range adhesive tracking |
| Trajectory Prediction & Memory Tracking | Supports trajectory prediction and feature memory tracking |
| Max Target Recognition Number | 50 |
| Picture-in-Picture (PiP) | Supported |
| Input Voltage | DC 9-16V |
| Power Consumption | 10W |
| Operating Temperature | -20°C~60°C |
| AI Image Processing Computing Power | 1 TOPS |
| Technical Parameters | Details |
|---|
| Communication Protocol | CRSF |
| Communication Method | UART |
| Video Output Format | CVBS |
| Supported Firmware | BetaFlight |
| Input Voltage | 9-16V |
| Mounting Holes | 25.5×25.5mm |
| Size (Main Module) | 38×38×29mm |
| Weight (Main Module) | 43.8g |
| Visible Light Camera Module | |
| - Size | 19×19×30mm |
| - Weight | 13.6g |
| - Video Input Format | 1920×1080@30Hz |
| Short-focal Camera | |
| - Low Light Performance | 7341 mV/lux·s |
| - CMOS Sensor | 1/2.8 Inch |
| - FOV | 69°(H)×42°(V) |
| - Focal Length | 4mm |
AI VisionCube Kit Brochures(EN)-20250310
AI VisionCube Kit User Manual (EN) V1.3.0-20250513
Model: AI VisionCube S