Configuration

caution

This page is out of date and currently being worked on. Proceed at your own risk.

Nimble is controlled by an initial configuration file or by using the REST API. The configuration files are in YAML format and needs to be named config.yaml in the root directory. The REST API accepts data in the JSON format. Upon starting the docker container, the config.yaml is mounted into the container and loaded by the Nimble application. The REST API is the only method for dynamically updating the configuration after Nimble has started. For an example of the REST deployment method, please refer to Deployer Example.

The configuration file follows this YAML schema:

- sources:
    - type: "video"                     # string: "video", "file", "youtube", "inf", "zmq", "zmqinternal"
      address: "rtsp://camera:554/path" # string: url or path, depending on 'type' property
      rate: 25                          # integer: desired input rate
      timeout: -1                       # integer: if `source` is disconnected try to reconnect for this many minutes, -1 is try indefinitely
      proxy: true                       # boolean: whether to enable MP4 proxying of video stream
  pipeline:
    - "pipeline element"
    - name: "pipeline element"          # string: name of the pipeline element
      hw: "cpu"                         # string: "cpu", "igpu", "gpu", or "fpga"
      mode: "a"                         # string: "a" for high-throughput or "s" for low-latency
      config: {}                        # object, or array of objects:
  sinks:
    - type: "file"                      # string: "file", "inf", "zmq", "zmqinternal"
      address: "video.mp4"              # string: url or path, depending on 'type' property
      filter: "*"                       # string, integer, or array of integers: source(s) to filter on (by zero-based index)
  configuration:
    - address: "tcp://*:22951"          # string: url (for zmq sink)
      message: {}                       # any auxiliary configuration

Each element in the config is explained in this section:

Instructions to add custom models is explained in this section: Add Custom Model

Instructions to add custom pipeline stages is explained in this section: Add Custom Pipeline Stage

Sample Configuration Files

Samples for the different supported use cases are provided in the samples directory. The following pipelines can be realized by overwriting the contents of config.yaml with each of these configurations:

CPU pipelines
- c1_person-detection.yaml : This is config for a single channel person detection pipeline.
- c1_ppe-compliance.yaml : This is config for a single channel ppe compliance detection pipeline.
- c3_person-detection.yaml : This is config for a 3 channel person detection pipeline.
- c1_camera_person-detection.yaml : This is config for a single channel person detection pipeline streaming from a live camera, that also applies the social distancing algorithm with multiple zmq sinks. Please configure the camera url in the yaml.
- c1_mask-detection.yaml : This is config for a single channel mask detection pipeline.
- c1_person-detection_privacy.yaml : This is config for a single channel person detection and face detection pipeline that applies blurring to faces for privacy.
- c1_intrusion-detection.yaml : This is config for a single channel intrusion detection pipeline.
- c1_people-tracking.yaml : This is config for a single channel people tracking pipeline.
- c1_line-crossing.yaml : This is config for a single channel line crossing pipeline.
- c1_person-detection_c1_mask-detection.yaml : This is config for a combination of c1_person-detection.yaml and c1_mask-detection.yaml.
- c1_person-detection_c1_intrusion-detection_c1_people-tracking.yaml : This is config for a combination of c1_person-detection.yaml and c1_intrusion-detection.yaml and c1_people-tracking.yaml.
- c1_intrusion-detection_c1_people-tracking.yaml : This is config for a combination of c1_intrusion-detection.yaml and c1_people-tracking.yaml.
- c1_fire-detection.yaml : This is config for a single channel fire detection pipeline.
iGPU pipelines
- c1_igpu_person-detection.yaml : This is config for a single channel person detection pipeline.
GPU pipelines
- c1_gpu_person-detection.yaml : This is config for a single channel person detection pipeline.
FPGA pipelines
- c1_fpga_physical-distancing.yaml : This is config for a single channel physical distancing pipeline.
- c1_fpga_intrusion-detection.yaml : This is config for a single channel intrusion detection pipeline.
- c1_fpga_people-tracking.yaml : This is config for a single channel people tracking pipeline.
- c1_fpga_line-crossing.yaml : This is config for a single channel line crossing pipeline.
- cn_fpga_physical-distancing.yaml : This is config for a 16 channel physical distancing pipeline.