| Model Type | Object Detection |
|---|---|
| Framework | LiteRT (TensorFlow Lite) |
| Algorithm | YOLOX |
| Technical Details | This unit performs object detection using a quantized YOLOX model. It processes static RGB images or video frames to return bounding boxes with class labels. Designed for real-time inference on edge CPUs and NPUs. Class mapping is provided via metadata.json. Ideal for security, safety, and visual AI tasks in constrained environments. |
Object Detection
Fast object detection using YOLOX optimized for embedded edge devices.
Leave your message here
Fill the form with the required information
$0.00
Object Detection
app details
Resources
Use Cases
Quality Control
Supported SECO Devices
AI optimized hardware
Fanless embedded PCs
Modules
supported chipsets
Intel® Core™ i3
Qualcomm® Dragonwing QCS6490
Qualcomm® Dragonwing QCS5430
NXP i.MX 8M Plus
NXP i.MX 95
Performance Benchmark
Hardware
Latency (ms)
Memory Usage
Processing unit
SECO SOM-SMARC-QCS6490
123.16 ms
14.06 MB
CPU
SECO SOM-SMARC-QCS6490
15.77 ms
14.06 MB
NPU
SECO SOM SMARC iMX8Plus
1469 ms
10.55 MB
CPU
SECO SOM SMARC iMX8Plus
121.43 ms
10.55 MB
NPU
SECO SOM-SMARC-MX95
363.87 ms
14.06 MB
CPU
SECO Titan 300 TGL-UP3
45.9 ms
14.06 MB
CPU
SECO Titan 300 TGL-UP3
31.32 ms
14.06 MB
CPU
People Counter
Lightweight real-time people counting model based on quantized YOLOX, optimized for edge devices using LiteRT (TensorFlow Lite) .
View Model
Automated Quality Inspection with Vision AI
Real-time AI-powered vision system for detecting defects in manufacturing environments
View Model
Image Classification
Efficient CNN model for image classification on mobile and embedded edge devices.
View Model
FFNet for Real-Time Semantic Segmentation
Lightweight semantic segmentation model optimized for real-time street scene analysis on edge devices.
View Model|
|