Highlighted Changes

• #427 Fixes issue with MongoDB where the latest MongoDB release (v5) does no longer run on Jetson devices.
• #420 Fixes issue in k8s setup
• #415 Fixes Docker compose installation instructions
• #356 Automatic creation of Docker Images
• #444 Fix Opendatacam Darknet Base docker tag

See Milestone v3.0.2 for a full list of issues and pull requests that went into the release.

Contributors

OpenDataCam is being developed by a small group of volunteers. 🙌

In this release we'd especially like to thank for their contribution (in alphabetic order) 🙏

• @napking
• @risyou
• @tdurand
• @vsaw
• @yauh

Highlighted Changes

• #427 Fixes issue with MongoDB where the latest MongoDB release (v5) does no longer run on Jetson devices.
• #420 Fixes issue in k8s setup
• #415 Fixes Docker compose installation instructions
• #356 Automatic creation of Docker Images
• #444 Fix Opendatacam Darknet Base docker tag

See Milestone v3.0.2 for a full list of issues and pull requests that went into the release.

Contributors

OpenDataCam is being developed by a small group of volunteers. 🙌

In this release we'd especially like to thank for their contribution (in alphabetic order) 🙏

• @napking
• @risyou
• @tdurand
• @vsaw
• @yauh

Highlighted Changes

• #427 Fixes issue with MongoDB where the latest MongoDB release (v5) does no longer run on Jetson devices.
• #420 Fixes issue in k8s setup
• #415 Fixes Docker compose installation instructions
• #356 Automatic creation of Docker Images

See Milestone v3.0.2 for a full list of issues and pull requests that went into the release.

Contributors

OpenDataCam is being developed by a small group of volunteers. 🙌

In this release we'd especially like to thank for their contribution (in alphabetic order) 🙏

• @napking
• @risyou
• @tdurand
• @vsaw
• @yauh

• Support for yolov4-tiny and make it default for jetson nano

New feature from v2.x

• Support for YOLOv4 and Yolov3-tiny-prn
• Drag & drop support for file, just drop a file on the UI and it will restart to process it
• Directional counters, see: #122 (comment)
• Fixed Memory leak on jetsons, expected running time should be counted in days now instead of hours ( #182 )
• Save / Reload counters config: see #122 (comment)
• Complete rewrite of Docker setup / install process in order to use docker-compose

Full changelog

• Improved performance by 6 FPS for Linux CUDA desktop machine by using cuDNN for the docker build
• Several smaller bugs fixes, clean up logs etc etc...
• Made ports configurable from config.json
• Add a configurable confidence threshold in config.json to filtrer out detections that are below this threshold. (default keep > 20% confidence)
• Add favicon
• Add "confirmation" modal when deleting recordings
• Add version number in side menu
• Updated all javascript dependencies: Next.js , Redux, React etc etc...
• Revert back to using the main ./darknet API as memory leak has been also fixed
• Update darknet fork once again using the new -dontdraw_bbox flag AlexeyAB kindly added for us : AlexeyAB/darknet@da05036
• Expose tracker config IOU and UNMATCHED FRAME tolerance
• Check if config.json version matches Opendatacam version
• Clean up code for drag& drop feature.. maybe add some UI tweaks like a drop indicator and a specific progress message
• Clean up and improve counter logic code
• Update API docs with new counters attributes
• Add Threshold to filter out large detections
• Update OpenMojis
• @fabianmoronzirfas added support for env variables: https://github.com/opendatacam/opendatacam/pull/222
• Add counter settings "minAngleWithCountingLine" : https://github.com/opendatacam/opendatacam/blob/development/documentation/CONFIG.md#counter-settings. Thanks @rantgithub for funding this feature
• Update documentation CONFIG.md as many default changed now.. we run on the demo.mp4 file now.. and file support is via drag & drop to simplify install process
• Update documentation Jetson nano
• Document how to run from custom weights with docker (possible now)
• Update Documentation for yolov3-tiny-prn and yolov4 weights

• Complete rewrite of Docker setup / install process in order to use docker-compose
• Update darknet fork once again using the new -dontdraw_bbox flag AlexeyAB kindly added for us : https://github.com/AlexeyAB/darknet/commit/da050367a8b174f751a2c9720195d51a369c4a4a
• Expose tracker config IOU and UNMATCHED FRAME tolerance
• Check if config.json version matches Opendatacam version
• Clean up code for drag& drop feature.. maybe add some UI tweaks like a drop indicator and a specific progress message
• Clean up and improve counter logic code
• Update API docs with new counters attributes
• Add Threshold to filter out large detections
• Update OpenMojis

• Support for YOLOv4 (set "NEURAL_NETWORK": "yolov4" in config.json)
• Upgraded docker setup and build workflow, see https://github.com/opendatacam/opendatacam/issues/178 , now you can run the docker container from jetson without needing to hack the support for CUDA.. It also simplified the Dockerfile file and made the build of OpenCV happening
• Result of previous point is support for RaspberryPi cam v2 (or any CSI cam compatible with nvarguscamerasrc) when running from the docker container for Jetson nano. Just set "VIDEO_INPUT": "raspberrycam"
• Improved performance by 6 FPS for Linux CUDA desktop machine by using cuDNN for the docker build
• Made ports configurable from config.json
• Add a configurable confidence threshold in config.json to filtrer out detections that are below this threshold. (default keep > 20% confidence)
• Add favicon
• Add "confirmation" modal when deleting recordings
• Add version number in side menu
• Updated all javascript dependencies: Next.js , Redux, React etc etc...
• Revert back to using the main ./darknet API as memory leak has been also fixed

• Better run from file support: auto-restart, record from beginning, persist frame index #88
• Add confidence score data
• Improve reliability on desktop for long run on file
• Restore last defined counter areas on boot
• Support to input video webcam stream with "-c 0" flag without gstreamer (default darknet)

v2.0.0 final release