Elements

Links under GStreamer element name (first column of the table) contain description of element properties, in the format generated by gst-inspect-1.0 utility

Inference plugins

Element	Description
gvadetect	Performs object detection and [optionally] classification/segmentation/pose estimation. Inputs: ROIs (regions of interest) or full frame. Output: object bounding box detection along with prediction metadata. queue element must be put directly after gvadetect element in pipeline. [eg syntax] gst-launch-1.0 … ! decodebin3 ! gvadetect model=$mDetect device=GPU[CPU,NPU] ! queue ! … OUT
gvaclassify	Performs object classification/segmentation/pose estimation. Inputs: ROI or full frame. Output: prediction metadata. queue element must be put directly after gvaclassify element in pipeline. [eg syntax] gst-launch-1.0 … ! decodebin3 ! gvadetect model=$mDetect device=GPU ! queue ! gvaclassify model=$mClassify device=CPU ! queue ! … OUT
gvainference	Executes any inference model and outputs raw results (does not interpret data and does not generate metadata). queue element must be put directly after gvainference element in pipeline. [eg syntax] gst-launch-1.0 … ! decodebin3 ! gvadetect model=$mDetect device=GPU ! queue ! gvainference model=$mHeadPoseEst device=CPU ! queue ! … OUT
gvatrack	Tracks objects across video frames using zero-term or short-term tracking algorithms. Zero-term tracking assigns unique object IDs and requires object detection to run on every frame. Short-term tracking allows to track objects between frames, thereby reducing the need to run object detection on each frame. [eg syntax] gst-launch-1.0 … ! decodebin3 ! gvadetect model=$mDetect device=GPU ! gvatrack tracking-type=short-term-imageless ! … OUT
gvaaudiodetect	Legacy plugin. Performs audio event detection using AclNet model. [eg syntax] gst-launch-1.0 … ! decodebin3 ! audioresample ! audioconvert ! audio/x-raw … ! audiomixer … ! gvaaudiodetect model=$mAudioDetect ! … OUT

Auxiliary plugins

Element	Description
gvaattachroi	Adds user-defined regions of interest to perform inference on, instead of full frame. Example: monitoring traffic on a road in a city camera feed, or when split large image to smaller pieces and inference each piece (healthcare cell analytics). [eg syntax] gst-launch-1.0 … ! decodebin3 ! gvaattachroi roi=xtl,ytl,xbr,ybr gvadetect inference-region=1 ! … OUT
gvafpscounter	Measures frames per second across multiple video streams in a single GStreamer process. [eg syntax] gst-launch-1.0 … ! decodebin3 ! gvadetect … ! gvafpscounter ! … OUT
gvametaaggregate	Aggregates inference results from multiple pipeline branches.
gvametaconvert	Converts the metadata structure to JSON or raw text formats, can write output to a file.
gvametapublish	Publishes the JSON metadata to MQTT or Kafka message brokers or files. [eg syntax] gst-launch-1.0 … ! decodebin3 ! gvadetect model=$mDetect device=GPU … ! gvametaconvert format=json … ! gvametapublish … ! … OUT
gvapython	Provides a callback to execute user-defined Python functions on every frame, used to augment DLStreamer with user-defined algorithms (e.g. metadata conversion, inference post-processing). [eg syntax] gst-launch-1.0 … ! gvaclassify ! gvapython module={gvapython.callback_module.classAge_pp} ! … OUT
gvawatermark	Overlays the metadata on the video frame to visualize the inference results. [eg syntax] gst-launch-1.0 … ! decodebin3 ! gvadetect … ! gvawatermark ! … OUT