| Model Type | Pose Estimation |
|---|---|
| Framework | AI Edge LiteRT, OpenVINO |
| Algorithm | HRNetPose |
| Technical Details | HRNet maintains high-resolution representations through the entire network and integrates features from multiple resolutions. It achieves state-of-the-art accuracy in human keypoint localization, and is suitable for edge applications with sufficient processing capabilities. |
HRNet for Human Pose Estimation
High-resolution neural network for accurate keypoint detection in human pose estimation tasks.
Leave your message here
Fill the form with the required information
$0.00
HRNet for Human Pose Estimation
app details
Resources
Use Cases
Industrial Safety
Surveillance
supported chipsets
Intel® Core™ i7
Performance Benchmark
Hardware · Backend
Processing unit
Latency (ms)
Avg. Peak RAM
Intel Tiger Lake · OpenVINO
GPU
15.4 ms
664.8 MB
Intel Tiger Lake · OpenVINO
CPU
14.1 ms
627.1 MB
Intel Tiger Lake · AiEdgeLiteRT
CPU
39.4 ms
172.5 MB
MediaTek Genio 510 · AiEdgeLiteRT
CPU
145.8 ms
76 MB
NXP i.MX 8M Plus · AiEdgeLiteRT
NPU
45.9 ms
76.1 MB
NXP i.MX 8M Plus · AiEdgeLiteRT
GPU
45.7 ms
76.1 MB
NXP i.MX 8M Plus · AiEdgeLiteRT
CPU
1714.4 ms
76.1 MB
Qualcomm QCS6490 · AiEdgeLiteRT
NPU
3.3 ms
82.5 MB
Qualcomm QCS6490 · AiEdgeLiteRT
CPU
159.7 ms
80.2 MB
PoseNet for Multi-Person Pose Detection
Lightweight and quantized PoseNet model for real-time multi-person pose estimation on edge hardware.
View Model
Face Detection for Industrial HMI
Real-time face detection for industrial HMI applications.
View Model
People Counter
Real-time people detection and counting for industrial and monitoring applications.
View Model
MiDaS for Monocular Depth Estimation
Efficient single-camera depth estimation using quantized MiDaS v2 model optimized for edge AI deployment.
View Model|
|