Daisy-Chain Detection & Pose Estimation

gst-ai-daisychain-detection-pose performs cascaded inference: first Object Detection locates human bodies, then Pose Detection draws skeleton connections for each detected person.

Prerequisites

• Completed QIM SDK Installation and Model Download

Steps

1. Verify Models

ls -l /etc/models/yolox_quantized.tflite /etc/models/hrnet_pose_quantized.tflite

2. View Configuration

cat /etc/configs/config-daisychain-detection-pose.json

3. Run

radxa@airbox$

gst-ai-daisychain-detection-pose --config-file=/etc/configs/config-daisychain-detection-pose.json

Press Ctrl + C to stop.

Expected Output

Using DSP delegate with TFLITE for Pose
Using DSP delegate with TFLITE for Detection
VERBOSE: Replacing 329 out of 329 node(s) with delegate (TfLiteQnnDelegate) node
VERBOSE: Replacing 518 out of 518 node(s) with delegate (TfLiteQnnDelegate) node
Pipeline state changed from PAUSED to PLAYING

The display shows the test video with bounding boxes and skeleton overlays for detected people.

Validation

• Detection (YOLOX, 329 ops) and pose (HRNet, 518 ops) running simultaneously on DSP
• Pipeline reaches PLAYING state
• Display shows both bounding boxes and human skeletons