[[["易于理解","easyToUnderstand","thumb-up"],["解决了我的问题","solvedMyProblem","thumb-up"],["其他","otherUp","thumb-up"]],[["很难理解","hardToUnderstand","thumb-down"],["信息或示例代码不正确","incorrectInformationOrSampleCode","thumb-down"],["没有我需要的信息/示例","missingTheInformationSamplesINeed","thumb-down"],["翻译问题","translationIssue","thumb-down"],["其他","otherDown","thumb-down"]],["最后更新时间 (UTC):2025-09-03。"],[],[],null,["# Detecting people\n\nVideo Intelligence can detect the presence of humans in a video\nfile and track the bounding box of individual people across the video or video\nsegment.\n\nPerson detection\n----------------\n\nTo detect people in a video, send a video annotation request to\nVideo Intelligence, and include the `PERSON_DETECTION` flag. The\nannotation request returns details about each person detected in the\nvideo, including video segment locations where the person is detected.\nThe annotation request can also provide bounding boxes too.\n\nAdditionally, person detection can detect the location of specific body parts as\n\"landmarks,\" such as `nose`, `left_shoulder`, or `right_shoulder`.\nFurthermore, person detection can detect other characteristics\nincluding clothing color, and clothing type. Specific characteristics that\nperson detection can recognize are provided in the following table.\n\nCheck out the [Video Intelligence API visualizer](https://zackakil.github.io/video-intelligence-api-visualiser/#Person%20Detection) to see this feature in action.\n\nFor an example, see\n[Person detection](/video-intelligence/docs/people-detection)."]]