Menu
Account
Search
Advanced Search
Back to the App List
main product photo

People Counter

by SECO

Lightweight real-time people counting model based on quantized YOLOv8n, optimized for edge devices using TensorFlow Lite.

Contact us
$0.00
More Information
People Counter
app details
Model Type

Object Detection & People Counting
Framework

TensorFlow Lite
Algorithm

YOLOv8 (Quantized for TFLite)
Technical Details

This unit detects people from single RGB frames and provides a live count along with average detection confidence. Designed to run on TFLite-compatible edge processors.

Available on request through SECO or integrated in Clea AI Studio
Use Cases
Industrial Safety and Surveillance
Supported IoT 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
105.11 ms
21.9 MB
CPU
SECO SOM-SMARC-iMX8Plus
1538 ms
21.9 MB
CPU
SECO SOM-SMARC-iMX95
411.48 ms
21.9 MB
CPU
SECO Titan 300 TGL-UP3 AI LiteRT
49.91 ms
21.9 MB
CPU
SECO Titan 300 TGL-UP3 AI OpenVino
37.44 ms
21.9 MB
CPU
SECO SOM-SMARC-iMX8Plus
207.12 ms
21.9 MB
NPU

Related models

Object Detection
Object Detection

Fast and accurate object detection using quantized YOLOv8n optimized for embedded edge devices.

 View Model
Face Recognition for Industrial HMI
Face Recognition for Industrial HMI

Secure face recognition HMI system for personalized user access in industrial environments.

 View Model
PoseNet for Multi-Person Pose Detection
PoseNet for Multi-Person Pose Detection

Lightweight and quantized PoseNet model for real-time multi-person pose estimation on edge hardware.

 View Model
HRNet for Human Pose Estimation
HRNet for Human Pose Estimation

High-resolution neural network for accurate keypoint detection in human pose estimation tasks.

 View Model