Gesture Recognition
Gesture recognition is an AI algorithm that detects 21 keypoints on the hand from images or video and recognizes 26 predefined gesture types (hand shapes and movements). It enables new forms of human-computer interaction (HCI) such as contactless operation, sign language recognition, AR/VR interaction, and device control.
Algorithm Overview
It consists of the following two stages:
- Hand Pose Estimation (Gestures Pose): Detects 21 hand keypoints (fingertips, joints, etc.)
- Gesture Classification (Gestures Classify): Identifies 26 gesture types from keypoint configurations
Recognizable Gestures (26 types)
| Index | Gesture | Meaning / Use |
|---|---|---|
| 0 | call | Phone / Calling |
| 1 | dislike | Dislike / Reject |
| 2 | fist | Fist / Confirm |
| 3 | four | Number 4 |
| 4 | grabbing | Grabbing |
| 5 | grip | Gripping |
| 6 | like | Like / OK |
| 7 | little_finger | Little finger |
| 8 | middle_finger | Middle finger |
| 9 | no_gesture | Neutral |
| 10 | ok | OK sign |
| 11 | one | Number 1 |
| 12 | palm | Open palm |
| 13 | peace | Peace sign |
| 14 | peace_inverted | Inverted peace |
| 15 | point | Pointing |
| 16 | rock | Rock sign |
| 17 | stop | Stop |
| 18 | stop_inverted | Inverted stop |
| 19 | three | Number 3 |
| 20 | three_gun | Three-gun |
Edge AI Board (RV1126B) Execution Efficiency
| Processing Stage | Model Size | Processing Time |
|---|---|---|
| Hand Pose Estimation (Gestures Pose) | 11.6MB | 58ms |
| Gesture Classification (Gestures Classify) | 2.81MB | 5ms |
| Total | 14.41MB | Approx. 63ms |
Key Features
- 21 keypoints + 26-type classification: High-precision hand movement recognition
- High-speed processing: Pose estimation 58ms + classification 5ms, approximately 63ms total
- Lightweight model: Compact total size of 14.41MB
- Real-time capable: Low-latency recognition on edge AI boards
Use Cases
- Contactless operation interfaces (medical settings, cleanrooms)
- Alternative input for AR/VR controllers
- Sign language recognition systems
- Smart home gesture control (lighting, appliances)
- Interactive digital signage operation
- Contactless communication in nursing care facilities
- Hands-free device operation in factories
Edge AI Board Implementation
Using the RV1126B NPU, hand pose estimation (58ms) and gesture classification (5ms) are processed in a combined total of approximately 63ms. Combined with USB cameras or MIPI cameras, a fully edge-based gesture recognition system can be built.