Support for Jetpack 6.1+ (Jetsons),

New / Updated

  • Supports Jetpack 6.1+ based Jetson devices
  • Upgrade to Deepstream 7.x.
    • DGPU based installations require a minimum driver version 560.x for consumer (RTX) GPUs and 535 for Datacenter GPUs.
  • Improved Camera stream latency handling
  • Improved exception reporting to provide more details for "Internal deployment error" scenarios.
  • MQTT connections now use WSS port 443 to mqtt.lumeo.com for improved compatibility with corporate firewalls.

Fixed

  • Fixes S3 uploads to custom GCP buckets from Save Clip node

Workaround for installation on Gateway's with a RAID setup

Fixed

  • Ignore smartctl failure during gateway setup process, for gateway hardware with advanced RAID setup which cannot be handled with the basic smartctl command. The side effect is that storage information for the Gateway will not be visible in Lumeo console,

Improved HikCentral Professional camera import and setup process.

Enhancements

  • v4.4.0 Improved support for HikCentral Professional.
    • Import HikCentral Professional camera streams into Lumeo using the HikCentral OpenAPI. See HikCentral Import for details.
    • Support to configure HikCentral Professional Events and Alarms using the OpenAPI to make alarm setup process easier. See Trigger HikCentral Alarm for details.

Fixes

  • v4.4.1 Fixes ONVIF streaming for the Hanwha Vision PNM-C32084RQZ camera and AI Box.

UI refresh, local recordings search capabilities, Increased compatibility for ONVIF clients

Enhancements

  • v4.0.0 Refreshed UI for the Web gateway manager makes it easier to use.
    • Dedicated tabs for Gateway status, Live streams, Recordings
    • See Status checks and gateway utilization at a glance
  • v4.0.0 Local recordings search. Adds ability to view analytics metadata contained in locally saved recordings and search for objects and text.
  • v4.2.2Manage Discrete GPU drivers from Settings -> System page
  • v4.2.2Clean Gateway cache + allow installing specific versions for better support.

Fixes

  • v4.1.0 Added ONVIF workarounds to make Lumeo Gateway ONVIF streams work better with certain clients.

New UI

New UI


Local recordings search

Local recordings search

Route MQTT connections over port 443, performance and start time improvements.

New

  • Improved compatibility with network firewalls by routing MQTT connections over secure web sockets and port 443 instead of legacy MQTT port.

Fixed

  • Fixes deadlocks and memory leaks in some rare conditions.
  • Improved deployment start times.

Fixes ONVIF and RTSP streaming from Media server.

Enhanced

  • Media server settings -> Local streams tab now allows bulk select and toggle for enabling/disabling ONVIF access to individual streams.
  • With Media server enabled, accessing streams within the Web Gateway Manager previously required an additional authentication. This is no longer required, and local streaming experience has been improved.

Fixed

  • ONVIF and RTSP streaming from the Media server in the Web Gateway Manager was broken when a Media password was set. This is now resolved. Turn off the Media server and turn it back on to fix this issue.

Bug fixes: Faster startup for Hanwha Vision cameras, prevent stuck deployments, logs now associated with correct deployments.

Fixed

  • Fixed a bug where a stuck deployment (because of slow cameras/network issues) prevented other deployments from starting/stopping. This lead to a lot of "stall detected" events.
  • Fixed a bug where logs and events from certain nodes and Custom Function were associated with the wrong deployment.
  • Improved slow-starts on certain cameras such as Hanwha Vision camera RTSP streams.

Pre-built AI models now download from cloud cache for faster startup, pipeline branches without source are ignored, license plate recognition is improved, NVIDIA-related crashes and memory leaks are mitigated, high CPU usage bug is fixed (redeploy required)

New

  • Pre-built AI model engines are now downloaded for Marketplace models from a cloud cache when available. This allows to skip "Optimizing AI model" step when starting a deployment on a gateway for the first time, which saves 15-20 minutes. Note: Pre-built Model engines are only available for common hardware configurations, so some hardware might still see longer start times.
  • Pipeline Nodes that don't have a path to the source node are now ignored. This allows ignoring the whole branches of the pipeline. Previously, only Function nodes could be left unconnected.
  • Support for improved License plate recognition model which is faster and more robust for side angle views of license plates.

Fixes

  • Deployment runner process crashes that started happening in 1.39.12 due to NVIDIA driver issues are now mitigated with the side effect of adding some delay to starting/stopping the deployment. This is a workaround till we upgrade Deepstream to 7.1 and NVIDIA patches the DGPU drivers.
  • Runners are now limited to 500 deployment starts. For deployments with a file source, the runner process stops accepting new deployments, and a new runner is started. For deployments with a live stream, the runner process is terminated and deployments are restarted. This helps to mitigate the memory leak in NVIDIA object tracker.
  • Gateway version 1.39.12 introduced an issue with higher than normal CPU usage for existing deployments. That is now resolved with 1.41.33, but requires that you re-deploy (not just restart) those pipelines (Deployment detail view -> Configuration tab -> Edit configuration -> Deploy).

Known Issues

  • When multiple deployments are running, logs from one deployment (in the Deployment detail view -> Logs tab) may appear in another deployment's view. We are working on a fix which will be rolled out in a patch release shortly.

Significant GPU memory savings enabling ~2x increase in number of streams processable on certain devices

New

  • This update introduces a new deployment architecture that results in significant GPU memory savings per deployment. This enables you to run close to 2x the previous number of deployments for certain models on the devices that were previously memory constrained, with no change for devices/models that are GPU compute constrained:

    Device TypeLight ModelsMedium ModelsHeavy Models
    Jetson Orin Nano 8GBUpto 2x more deploymentsSimilar capacity as v1.38.26Similar capacity as v1.38.26
    Jetson Orin NX 8GBUpto 1.5x more deploymentsSimilar capacity as v1.38.26Similar capacity as v1.38.26
    Jetson Orin NX 16GBUpto 1.5x more deploymentsSimilar capacity as v1.38.26Similar capacity as v1.38.26
    Jetson Orin AGX 32/64GBSimilar capacity as v1.38.26Similar capacity as v1.38.26Similar capacity as v1.38.26
    Nvidia DGPU systemsUpto 2x more deploymentsUpto 2x more deploymentsUpto 2x more deployments

Updated

  • Fix typo in logrotate conf which lead to some logs growing infinitely
  • System metrics reporting (CPU usage and such) changed from 15 mins to 1 minute
  • Fix for inbound webhooks not being passed along to Receive HTTP Webhook node.

Network route management, local recordings view and upload files for local processing.

New

  • Adds Network route management, ping check and port connectivity check capabilities. See Settings -> Network.

  • Add Local Recordings view


  • Uploaded Static media files (Settings -> Media Server) can now be added to Lumeo container as a local file so you can process files without uploading them to Lumeo cloud.