| Model Type | Object Detection |
|---|---|
| Framework | LiteRT (TensorFlow Lite) |
| Algorithm | YOLOX-Nano |
| Technical Details | This unit performs object detection using a quantized YOLOX-Nano model, engineered for ultra–low-power edge devices. It processes static RGB images or video frames and outputs bounding boxes with class labels using an anchor-free detection head and depthwise-separable convolutions, drastically reducing the computational load. The pipeline includes input normalization, INT8 quantization, and optimized execution paths for embedded CPUs and NPUs. Ideal for portable, fanless, or autonomous systems requiring efficient visual AI capabilities with minimal power usage. |
Object Detection – Low Power on Edge
Energy-efficient object detection optimized for edge platforms with power and thermal constraints.
Leave your message here
Fill the form with the required information
$0.00
Object Detection – Low Power on Edge
app details
Resources
Use Cases
Quality Control
Industrial Safety
Surveillance
Security
supported chipsets
Intel® Core™ i3
People Counter
Lightweight real-time people counting model based on quantized YOLOX, optimized for edge devices using LiteRT (TensorFlow Lite) .
View Model|
|