> For the complete documentation index, see [llms.txt](https://docs.convai.com/api-docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.convai.com/api-docs/zh/cha-jian-yu-ji-cheng/convai-unreal-engine-plugin/features/vision.md).

# 视觉

在 Unreal Engine 中为 Convai 角色提供场景视觉，使其能够在对话期间对关卡中可见的内容作出反应。

视觉功能可让 Convai 角色在对话期间查看虚幻引擎关卡。你可以为角色添加场景捕获组件，并将其对准角色需要观察的区域；Convai 会将捕获的画面帧与语音一并使用。

<table data-view="cards"><thead><tr><th></th><th data-hidden data-card-target data-type="content-ref"></th></tr></thead><tbody><tr><td><strong>视觉功能的工作原理</strong><br>了解会话期间如何捕获场景画面、发现画面来源并将其发送至 Convai。</td><td><a href="https://docs.convai.com/api-docs/zh/cha-jian-yu-ji-cheng/convai-unreal-engine-plugin/features/vision/how-vision-works.md">视觉的工作原理</a></td></tr><tr><td><strong>视觉功能快速入门</strong><br>为角色添加 Environment Webcam 组件，并在一次“在编辑器中运行”（Play In Editor）会话中确认场景视觉功能正常工作。</td><td><a href="https://docs.convai.com/api-docs/zh/cha-jian-yu-ji-cheng/convai-unreal-engine-plugin/features/vision/vision-quick-start.md">视觉快速开始</a></td></tr><tr><td><strong>视觉画面来源</strong><br>配置内置的 Environment Webcam 组件、其渲染目标、捕获速率和活动来源选择。</td><td><a href="https://docs.convai.com/api-docs/zh/cha-jian-yu-ji-cheng/convai-unreal-engine-plugin/features/vision/vision-frame-sources.md">视觉帧源</a></td></tr><tr><td><strong>自定义视觉组件</strong><br>当内置的 Environment Webcam 组件无法满足图像处理流程需求时，创建 C++ 画面来源。</td><td><a href="https://docs.convai.com/api-docs/zh/cha-jian-yu-ji-cheng/convai-unreal-engine-plugin/features/vision/custom-vision-components.md">自定义视觉组件</a></td></tr><tr><td><strong>视觉功能蓝图参考</strong><br>可通过蓝图访问的视觉枚举、组件属性、事件和 Chatbot 集成节点的参考。</td><td><a href="https://docs.convai.com/api-docs/zh/cha-jian-yu-ji-cheng/convai-unreal-engine-plugin/features/vision/vision-blueprint-reference.md">视觉 Blueprint 参考</a></td></tr><tr><td><strong>视觉功能用法示例</strong><br>应用常见的蓝图模式，实现自动开始捕获、手动开始和停止、调整 FPS 以及切换来源。</td><td><a href="https://docs.convai.com/api-docs/zh/cha-jian-yu-ji-cheng/convai-unreal-engine-plugin/features/vision/vision-usage-examples.md">视觉使用示例</a></td></tr><tr><td><strong>视觉功能故障排查</strong><br>诊断视觉上下文缺失、启动失败、渲染目标为空、来源无效和捕获速率问题。</td><td><a href="https://docs.convai.com/api-docs/zh/cha-jian-yu-ji-cheng/convai-unreal-engine-plugin/features/vision/troubleshoot-vision.md">排查视觉问题</a></td></tr></tbody></table>

### 后续步骤

从 [视觉功能的工作原理](https://docs.convai.com/api-docs/zh/cha-jian-yu-ji-cheng/convai-unreal-engine-plugin/features/vision/how-vision-works.md) 开始，了解捕获流程。然后参阅 [视觉功能快速入门](https://docs.convai.com/api-docs/zh/cha-jian-yu-ji-cheng/convai-unreal-engine-plugin/features/vision/vision-quick-start.md) ，再前往 [视觉画面来源](https://docs.convai.com/api-docs/zh/cha-jian-yu-ji-cheng/convai-unreal-engine-plugin/features/vision/vision-frame-sources.md) 调整捕获设置，或参阅 [视觉功能用法示例](https://docs.convai.com/api-docs/zh/cha-jian-yu-ji-cheng/convai-unreal-engine-plugin/features/vision/vision-usage-examples.md).


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.convai.com/api-docs/zh/cha-jian-yu-ji-cheng/convai-unreal-engine-plugin/features/vision.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.
