![]() ! nvvideoconvert ! nvv4l2h264enc insert-sps-pps=true iframeinterval=10 ! tee name=h264 \ĭeep. Nvstreammux name=nvstreammux0 batch-size=4 batched-push-timeout=40000 width=640 height=480 ! queue ! nvinfer batch-size=4 config-file-path=deepstream-models/config_infer_primary_4_cameras.txt ! queue ! nvtracker ll-lib-file=deepstream-models/libnvds_mot_klt.so enable-batch-process=true ! queue ! nvmultistreamtiler width=640 height=480 rows=2 columns=2 ! nvvideoconvert ! nvdsosd ! queue ! tee name=deep \ĭeep. ! video/x-raw,format=I420,width=640,height=480 ! nvvideoconvert ! video/x-raw(memory:NVMM),format=NV12,width=640,height=480 ! nvstreammux0.sink_3 \ ![]() Nvarguscamerasrc ! nvvidconv ! video/x-raw,format=I420,width=640,height=480 ! queue ! tee name=camera1 \Ĭamera0. V4l2src device=/dev/video1 ! video/x-raw,width=640,height=480 ! videoconvert ! video/x-raw,format=I420,width=640,height=480 ! queue ! tee name=camera0 \ The sample media server described later uses two cameras, however, the two video streams are replicated to demonstrate that several video streams can be added. Figure 1 shows a sample snapshot of a video stream with the resulting bounding boxes after some AI processing performed by the NVIDIA DeepStream software module. We demonstrate how you can develop a scalable and robust prototype to capture from several different video sources by using GStreamer Daemon ( GstD), GstInterpipe, and the NVIDIA DeepStream SDK.īesides achieving real-time deep learning inference, the server is completely dynamic from the point of view that it is possible to change the properties and states of the several video streams being processed during run time.Ī valuable add-on is the capability of triggering actions such as taking snapshots or recording a video as a response to a specific event. In this post, we show you how to build a simple real-time multi-camera media server for AI processing on the NVIDIA Jetson platform. One typical example is a GUI to control the media server through interprocess communication. A media server provides multimedia all-in-one features, such as video capture, processing, streaming, recording, and, in some cases, the ability to trigger actions under certain events, for example, automatically taking a snapshot.įor you to make the best out of a media server, it must be scalable, modular, and easy to integrate with other processes.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |