HS Airforce AI VisionCube Kit FPV AI Camera Module, 1.2 km object recognition, PiP, CRSF, Betaflight/APM/PX4 S
Original price was: $273.57.$136.79Current price is: $136.79.
Description
Overview
HS Airforce AI VisionCube Kit is an FPV AI Camera Module designed for long-range object recognition and subject tracking on FPV drones. The modular system offers multi-sensor options (visible and thermal), PiP dual-stream viewing, and onboard AI that detects and tracks multiple subjects while integrating with common FPV flight stacks.
For pre-sales or technical questions, contact [email protected] or visit https://rcdrone.top/.
Key Features
- Up to 1.2 km ultra-long-range object recognition with powerful onboard AI.
- Multi-object recognition: identifies and tracks up to 50 subjects in view.
- Continuous tracking of moving subjects using trajectory prediction and feature memory.
- Adaptive subject adhesion around the center area to improve hold rate by over 80% and simplify pilot control.
- PiP architecture: dual-stream view combines a wide main view with up to 8x digital zoom sub-view for real-time scene analysis.
- Multi-sensor compatibility: switchable visible/thermal imaging; low-light sensitivity up to 9650 mV/luxs; operating range -20 to 60.
- AI VisionCube Kit performance uplift: recognition distance +80%+, accuracy +60%+, dynamic tracking success +45%+ (per vendor data).
- Lightweight integration design (<200g) with plug-and-play installation in about 5 minutes; supports Betaflight/APM/PX4 open-source flight controllers.
- CRSF protocol, 9-16 V input, compact 38*38 mm board with 25.5*25.5 mm mounting holes.
Specifications
| Product Type | FPV AI Camera Module |
| Model Number | AI VisionCube Kit |
| High-concerned chemical | None |
| Origin | Mainland China |
| Package | Yes |
| Weight | 250g |
Variants and AI Board
| Parameter | AI VisionCube S | AI VisionCube D | AI VisionCube ST | AI VisionCube DT |
|---|---|---|---|---|
| Default recognition types | People, Vehicle | People, Vehicle | People, Vehicle | People, Vehicle |
| Detection range (vehicle) | 450m | 1200m | 450m | 1200m |
| Detection range (person) | 170m | 500m | 170m | 500m |
| Minimum tracking pixels | 16*16 Pixels | 16*16 Pixels | 16*16 Pixels | 16*16 Pixels |
| Maximum tracking speed | 60km/h | 60km/h | 60km/h | 60km/h |
| Adaptive subject adhesion | Support | Support | Support | Support |
| Trajectory prediction & feature memory | Support | Support | Support | Support |
| Maximum subjects supported | 50 | 50 | 50 | 50 |
| Picture-in-Picture (PiP) | Support | Support | Support | Support |
| Computing power (TOPS) | 1 | 6 | 1 | 6 |
| Protocol | CRSF | CRSF | CRSF | CRSF |
| Supported firmware | Betaflight / APM / PX4 | Betaflight / APM / PX4 | Betaflight / APM / PX4 | Betaflight / APM / PX4 |
| Input voltage (V) | 9-16 | 9-16 | 9-16 | 9-16 |
| AI board dimensions (LxWxH, mm) | 38*38*27.7 | 38*38*26.7 | 38*38*27.7 | 38*38*26.7 |
| Mounting holes (mm) | 25.5*25.5 | 25.5*25.5 | 25.5*25.5 | 25.5*25.5 |
Visible Camera 1
| Parameter | S | D | ST | DT |
|---|---|---|---|---|
| Sensor (Inches) | 1 / 2.8 | 1 / 2.6 | 1 / 2.8 | 1 / 2.6 |
| Focal length (mm) | 4 | 3.9 | 4 | 3.9 |
| FOV | 69(H)*42(V) | 72(H)*45(V) | 69(H)*42(V) | 72(H)*45(V) |
| Low light performance | 7341 mV/luxs | 9650 mV/luxs | 7341 mV/luxs | 9650 mV/luxs |
| Video input format | 1920*1080@30hz | 1920*1080@60hz | 1920*1080@30hz | 1920*1080@60hz |
| Camera dimension (LxWxH, mm) | 19*19*30 | 40.8*25*26 | 19*19*30 | 40.8*25*26 |
Visible Camera 2
| Parameter | S | D | ST | DT |
|---|---|---|---|---|
| Sensor (Inches) | N/A | 1 / 2.6 | N/A | 1 / 2.6 |
| Focal length (mm) | N/A | 12 | N/A | 12 |
| FOV | N/A | 26(H)*15(V) | N/A | 26(H)*15(V) |
| Low light performance | N/A | 9650 mV/luxs | N/A | 9650 mV/luxs |
| Video input format | N/A | 1920*1080@50h | N/A | 1920*1080@50h |
| Camera dimension (LxWxH, mm) | N/A | 40.8*25*26 | N/A | 40.8*25*26 |
Thermal Camera
| Parameter | S | D | ST | DT |
|---|---|---|---|---|
| Pixel pitch | N/A | N/A | 12um | 12um |
| Focal length | N/A | N/A | 9.1mm | 9.1mm |
| FOV | N/A | N/A | 20.3(H)*15.2(V) | 20.3(H)*15.2(V) |
| Response band | N/A | N/A | 8~14um (LWIR) | 8~14um (LWIR) |
| Video input format | N/A | N/A | 384*288@25hz | 384*288@25hz |
| Camera dimension (LxWxH, mm) | N/A | N/A | 26*26*42.63 | 26*26*42.63 |
| Interface | N/A | N/A | USB | USB |
Details
AI VisionCube S, ST, D, DT models with varying camera configurations for FPV AI applications.
AI VisionCube Kit enhances target recognition; supports 170m human and 450m vehicle detection, upgrading from 1.0 AI Module’s 100m limit.
AI VisionCube series includes S, D, ST, DT models with human and vehicle detection. Ranges vary from 170m to 1200m. All support tracking up to 60km/h, 50 targets, PIP, trajectory prediction, and adhesive tracking.
HS Airforce AI VisionCube Kit offers 1 or 6 TOPS computing power, CRSF protocol, BetaFlight/APM/PX4 support, 916V input, compact design with 383826.7/27.7 mm dimensions, 25.525.5 mm mounting holes, and integrated visible camera.
Compares two camera models with 1/2.8 and 1/2.6 sensors, differing in focal length, FOV, low light performance, video format (30Hz/60Hz), and compact vs. larger dimensions.
HS Airforce AI VisionCube Kit includes a 1/2.6″ sensor, 12mm focal length, 2615 FOV, 9650 mV/luxs sensitivity, 19201080@50Hz video, and compact 40.82526mm size. Thermal unit offers 12m pixel pitch, 9.1mm lens, 20.315.2 FOV, 814m LWIR, 384288@25Hz output, 262642.63mm, and USB interface.
2025 Global Debut Next-Gen Hyper-Sensing AI Module with dual and single lens cameras
2025 Global Debut Next-Gen Hyper-Sensing AI Module with camera and accessories
2025 Global Debut Next-Gen Hyper-Sensing AI Module with dual lenses and circuit board.
2025 Global Debut Next-Gen Hyper-Sensing AI Module with QR codes and modular design




Reviews
There are no reviews yet.