> ## Documentation Index
> Fetch the complete documentation index at: https://dragonwingdocs.qualcomm.com/llms.txt
> Use this file to discover all available pages before exploring further.

# AI sample applications

> The QIR SDK provides AI sample applications for hand detection, depth estimation, face detection, pose estimation, image classification, object detection, and segmentation.

The QIR SDK provides the following AI sample applications.

<CardGroup cols={2}>
  <Card title="Detect hands with sample_hand_detection" href="./detect-hands-with-sample_hand_detection">
    `sample_hand_detection` uses the Python-based hand recognition ROS node to detect hand and hand movement.
  </Card>

  <Card title="Estimate image depth values with sample_depth_estimation" href="./estimate-image-depth-values-with-sample_depth_estimation">
    Input an RGB image named `input_image.jpg` or subscribe to the ROS topic `/cam0_stream1`, then publish per-pixel depth values as the `/depth_map` ROS topic.
  </Card>

  <Card title="Detect faces with sample_face_detection" href="./detect-faces-with-sample_face_detection">
    The `sample_face_detection` sample application is a Python-based face detection ROS node that uses Qualcomm Neural Network (QNN) for model inference.
  </Card>

  <Card title="Estimate human poses with sample_hrnet_pose_estimation" href="./estimate-human-poses-with-sample_hrnet_pose_estimation">
    The `sample_hrnet_pose_estimation` sample application provides high-precision human pose estimation capabilities.
  </Card>

  <Card title="Classify images with sample_resnet101" href="./classify-images-with-sample_resnet101">
    The `sample_resnet101` is a Python-based ROS node that performs image classification using QNN-based inference.
  </Card>

  <Card title="Detect objects with sample_object_detection" href="./detect-objects-with-sample_object_detection">
    The `sample_object_detection` is a Python launch file utilizing QNN for model inference, demonstrating camera data streaming, AI-based inference, and real-time visualization of object detection results.
  </Card>

  <Card title="Segment objects with sample_object_segmentation" href="./segment-objects-with-sample_object_segmentation">
    The `sample_object_segmentation` is a Python launch file utilizing QNN for model inference, demonstrating camera data streaming, AI-based inference, and real-time visualization of object segmentation results.
  </Card>
</CardGroup>