| Model Type | Semantic Segmentation |
|---|---|
| Framework | LiteRT (TensorFlow Lite) |
| Algorithm | FFNet |
| Technical Details | FFNet-40S is a compact convolutional neural network designed for pixel-wise semantic segmentation of high-resolution images. It combines a ResNet-style encoder with a multi-branch decoder, enabling efficient processing on devices with limited compute resources. Ideal for smart city and autonomous driving scenarios. |
FFNet for Real-Time Semantic Segmentation
Lightweight semantic segmentation model optimized for real-time street scene analysis on edge devices.
Leave your message here
Fill the form with the required information
$0.00
FFNet for Real-Time Semantic Segmentation
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
1318 ms
12.38 MB
CPU
SECO SOM-SMARC-QCS6490
58 ms
12.38 MB
NPU
SECO SOM SMARC iMX8Plus
767 ms
12.38 MB
CPU
SECO SOM SMARC iMX8Plus
85.85 ms
12.38 MB
NPU
SECO SOM-SMARC-MX95
3564 ms
12.38 MB
CPU
SECO Titan 300 TGL-UP3
365.21 ms
12.38 MB
CPU
SECO Titan 300 TGL-UP3
164.76 ms
12.38 MB
CPU
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
MiDaS for Monocular Depth Estimation
Efficient single-camera depth estimation using quantized MiDaS v2 model optimized for edge AI deployment.
View Model|
|