用于深度分析的 Z 坐标：此值有助于确定用户身体的各个部位是在用户臀部前方还是后方。如需了解详情，请参阅下面的 Z 坐标部分。
Pose Detection API 与 Facial Recognition API 类似，因为它会返回一组地标及其位置。不过，虽然人脸检测还会尝试识别微笑的嘴巴或睁开的眼睛等特征，但姿势检测不会给某个姿势或姿势本身的地标附加任何含义。您可以创建自己的算法来解释姿势。有关某些示例，请参阅姿势分类提示。
姿势检测功能只能检测图片中的一人。如果图片中有两个人，模型将为检测到最高置信度的人分配地标。
Z 坐标
Z 坐标是为每个地标计算的实验性值。它以“图像像素”为单位（如 X 和 Y 坐标），但它不是真正的 3D 值。Z 轴垂直于镜头，穿过对象的臀部。Z 轴的原点大约是两个臀部之间的中心点（相对于镜头的左/右和前/后）。Z 负值表示镜头朝向；正值表示远离镜头。Z 坐标没有上限或下限。
示例结果
下表显示了右侧姿势中几个地标的坐标和 InFrameLikelihood。请注意，用户左手的 Z 坐标为负值，因为它们位于拍摄对象的臀部中心前方并朝向镜头。
[null,null,["最后更新时间 (UTC)：2025-07-25。"],[[["\u003cp\u003eML Kit's Pose Detection API enables real-time body pose tracking in apps, using skeletal landmark points to identify body positions.\u003c/p\u003e\n"],["\u003cp\u003eIt offers cross-platform support, full-body tracking with 33 landmarks including hands and feet, and InFrameLikelihood scores for landmark accuracy.\u003c/p\u003e\n"],["\u003cp\u003eTwo SDK options are available: a base SDK for real-time performance and an accurate SDK for higher precision landmark coordinates.\u003c/p\u003e\n"],["\u003cp\u003eThe API is currently in beta and subject to change.\u003c/p\u003e\n"]]],[],null,["# Pose detection\n\nThis API is offered in beta, and is not subject to any SLA or deprecation policy. Changes may be made to this API that break backward compatibility. \n\nThe ML Kit Pose Detection API is a lightweight versatile solution for app\ndevelopers to detect the pose of a subject's body in real time from a\ncontinuous video or static image. A pose describes the body's position at one\nmoment in time with a set of skeletal landmark points. The landmarks\ncorrespond to different body parts such as the shoulders and hips. The relative\npositions of landmarks can be used to distinguish one pose from another.\n\n[iOS](/ml-kit/vision/pose-detection/ios)\n[Android](/ml-kit/vision/pose-detection/android)\n\nML Kit Pose Detection produces a full-body 33 point skeletal match that includes\nfacial landmarks (ears, eyes, mouth, and nose) and points on the hands and feet.\nFigure 1 below shows the landmarks looking through the camera at the user, so\nit's a mirror image. The user's right side appears on the left of the image: \n**Figure 1.**Landmarks\n\nML Kit Pose Detection doesn't require specialized equipment or ML expertise in\norder to achieve great results. With this technology developers can create one\nof a kind experiences for their users with only a few lines of code.\n\nThe user's face must be present in order to detect a pose. Pose detection works\nbest when the subject's entire body is visible in the frame, but it also\ndetects a partial body pose. In that case the landmarks that are not\nrecognized are assigned coordinates outside of the image.\n\nKey capabilities\n----------------\n\n- **Cross-platform support** Enjoy the same experience on both Android and iOS.\n- **Full body tracking** The model returns 33 key skeletal landmark points, including the positions of the hands and feet.\n- **InFrameLikelihood score** For each landmark, a measure that indicates the probability that the landmark is within the image frame. The score has a range of 0.0 to 1.0, where 1.0 indicates high confidence.\n- **Two optimized SDKs** The base SDK runs in real time on modern phones like the Pixel 4 and iPhone X. It returns results at the rate of \\~30 and \\~45 fps respectively. However, the precision of the landmark coordinates may vary. The accurate SDK returns results at a slower framerate, but produces more accurate coordinate values.\n- **Z Coordinate for depth analysis** This value can help determine whether parts of the users body are in front or behind the users' hips. For more information, see the [Z Coordinate](#z_coordinate) section below.\n\nThe Pose Detection API is similar to the [Facial Recognition API](/ml-%0Akit/vision/face-detection) in that it returns a set of landmarks and their\nlocation. However, while Face Detection also tries to recognize features such as\na smiling mouth or open eyes, Pose Detection does not attach any meaning to the\nlandmarks in a pose or the pose itself. You can create your own algorithms to\ninterpret a pose. See\n[Pose Classification Tips](/ml-kit/vision/pose-detection/classifying-poses) for\nsome examples.\n\nPose detection can only detect one person in an image. If two people are in the\nimage, the model will assign landmarks to the person detected with the highest\nconfidence.\n\nZ Coordinate\n------------\n\nThe Z Coordinate is an experimental value that is calculated for every landmark. It\nis measured in \"image pixels\" like the X and Y coordinates, but it is not a true\n3D value. The Z axis is perpendicular to the camera and passes between\na subject's hips. The origin of the Z axis is approximately the center point\nbetween the hips (left/right and front/back relative to the camera).\nNegative Z values are towards the camera; positive values are away from it.\nThe Z coordinate does not have an upper or lower bound.\n\nSample results\n--------------\n\nThe following table shows the coordinates and InFrameLikelihood for a few\nlandmarks in the pose to the right. Note that the Z coordinates for the user's\nleft hand are negative, since they are in front of the subject's hips' center\nand towards the camera. \n\n| Landmark | Type | Position | InFrameLikelihood |\n|----------|----------------|------------------------------------|-------------------|\n| 11 | LEFT_SHOULDER | (734.9671, 550.7924, -118.11934) | 0.9999038 |\n| 12 | RIGHT_SHOULDER | (391.27032, 583.2485, -321.15836) | 0.9999894 |\n| 13 | LEFT_ELBOW | (903.83704, 754.676, -219.67009) | 0.9836427 |\n| 14 | RIGHT_ELBOW | (322.18152, 842.5973, -179.28519) | 0.99970156 |\n| 15 | LEFT_WRIST | (1073.8956, 654.9725, -820.93463) | 0.9737737 |\n| 16 | RIGHT_WRIST | (218.27956, 1015.70435, -683.6567) | 0.995568 |\n| 17 | LEFT_PINKY | (1146.1635, 609.6432, -956.9976) | 0.95273364 |\n| 18 | RIGHT_PINKY | (176.17755, 1065.838, -776.5006) | 0.9785348 |\n\nUnder the hood\n--------------\n\nFor more implementation details on the underlying ML models for this API, check\nout our [Google AI blog post](https://ai.googleblog.com/2020/08/on-device-real-time-body-pose-tracking.html).\n\nTo learn more about our ML fairness practices and how the models were trained,\nsee our [Model Card](/static/ml-kit/images/vision/pose-detection/pose_model_card.pdf)"]]
