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 .. list-table:: :header-rows: 1 * - Element - Description * - :doc:`gvadetect ` - Performs object detection using SSD-like (including MobileNet-V1/V2 and ResNet), YoloV2/YoloV3/YoloV2-tiny/YoloV3-tiny and FasterRCNN-like object detection models. * - :doc:`gvaclassify ` - Performs object classification. Accepts the ROI or full frame as an input and outputs classification results with metadata. * - :doc:`gvainference ` - Runs deep learning inference using any model with an RGB or BGR input. * - :doc:`gvaaudiodetect ` - Performs audio event detection using AclNet model. * - :doc:`gvatrack ` - Performs object tracking 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. * - :doc:`gvametaaggregate ` - Aggregates inference results from multiple pipeline branches. * - :doc:`gvametaconvert ` - Converts the metadata structure to the JSON format. * - :doc:`gvametapublish ` - Publishes the JSON metadata to MQTT or Kafka message brokers or files. * - :doc:`gvapython ` - Provides a callback to execute user-defined Python functions on every frame. Can be used for metadata conversion, inference post-processing, and other tasks. * - :doc:`gvawatermark ` - Overlays the metadata on the video frame to visualize the inference results. * - :doc:`gvafpscounter ` - Measures frames per second across multiple streams in a single process. .. toctree:: :maxdepth: 1 :hidden: gvadetect gvaclassify gvainference gvaaudiodetect gvatrack gvametaconvert gvametapublish gvametaaggregate gvapython gvawatermark gvafpscounter