Milvus 如何在 TB 级自动驾驶视频里检索关键片段
自动驾驶视频素材多到看不过来？Milvus 这个 demo 演示输入一句话就能搜出雨中施工这类具体片段，还能用图片搜相似场景。
一辆自动驾驶测试车一天能录下 TB 级视频，工程师需要的往往只是行人夜间过马路、高速出口被别车那几秒钟。Milvus 把每帧画面转成向量，同时存储天气、道路类型、红绿灯颜色等结构化细节，供联合检索。工程师输入“雨中有交通锥的施工路段”，文本被转成向量、按天气过滤后直接跳转到对应片段和时间戳。同一套流程也支持用一张参考图找出最接近的道路场景。该方法同样适用于工厂质检图像、机器人摄像头和安防视频检索。
One self-driving car can record terabytes of video in a day. But engineers don’t need all that footage. They need a few seconds when something important happened. A pedestrian crossed the road at night. A car cut near a highway exit. Roadwork appeared during heavy rain. Finding those moments by watching video after video doesn’t scale. A vision model can turn each frame into a vector and extract details such as the weather, road type, traffic-light color, lane count, and unusual events. Milvus stores and indexes those vectors and details so teams can search them together. Then an engineer can: Type “rainy construction zone with traffic cones,” let the application convert that text into a vector, filter the results by weather, and jump to the matching clip and timestamp. The same setup also works with a reference image. The application converts the image into a vector, and Milvus finds the closest road scenes. This gives autonomous-driving teams a practical way to find rare cases, review model failures, and collect useful training data. The same approach can help teams search for factory inspection images, robot camera footage, security video, and other large visual datasets. Try the demo: demos.milvus.io/structarray-se… 💬 0 🔄 0 ❤️ 1 👀 68 ⚡