• Watsor TensorRT detector has been upgraded to support latest TensorRT 8. It is still backward compatible with TensoRT 7. TensorRT 8 supports a lot more object detection models including Single Shot Detector and Faster R-CNN. The list of supported model can be found here.
• Raspberry Pi 3&4 images updated from the latest bullseye base image.

Breaking change

Docker image for Nvidia Jetson devices seems incompatible with Jetson Nano, because L4T base image no longer brings CUDA, CuDNN and TensorRT from the host file system. These libraries are now baked into Docker image, where the most recent version of them inherits JetPack 5.0 and Ubuntu 20.04. Jetson Nano is still uses JetPack 4.4.1 and Ubuntu 18.04, so until Nvidia provides an upgrade, it can not run the new Docker image.

As as workaround, on top of smirnou/watsor.jetson:1.0.6 image one can create an image with the latest Watsor's code or upgrade Watsor's Python module right in the container. However, it will not be able to run ONNX models since CUDA and TensorRT are still outdated in the host Jeson Nano system.

What's Changed

• Bug fixes by @asmirnou in https://github.com/asmirnou/watsor/pull/30

Full Changelog: https://github.com/asmirnou/watsor/compare/1.0.6...1.0.7

• All TensorFlow models supported: version 1 & 2.
• TensorFlow in Docker image is configured with full assortment of drivers and libraries to use GPU.
• The Coral accelerator got a new model SSD MobileDet.
• New Docker image for Jetson devices (Xavier, TX2, and Nano).

BREAKING CHANGE: GPU's code got rid of the plugin as it is now included in TensorRT 7. UFF models previously associated with that plugin have been recompiled and need to be downloaded and replaced.

• Added Watsor add-ons for Home Assistant
• Camera input and output ca be relative to the config directory

This release adds:

• support for Raspberry Pi 3 and 4 with 32-bit OS
• Helm chart to deploy Watsor on Kubernetes

• This release introduced the support for Raspberry Pi 4 with 64-bit OS, where Watsor can be installed either as Python module or using Docker image. To get decent performance on a device such as Raspberry Pi one needs the Coral USB accelerator.
• Documentation updated to make some nuances clear when configuring the app.

Watsor

Watsor detects objects in video stream using deep learning-based approach. Intended primarily for surveillance it works in sheer real-time analysing the most recent frame to deliver fastest reaction against a detected threat.

What it does

• Performs smart detection based on artificial neural networks significantly reducing false positives in video surveillance.
• Capable to limit detection zones using mask image with alpha channel.
• Supports multiple hardware accelerators such as The Coral USB Accelerator and Nvidia CUDA GPUs to speed up detection algorithms.
• Reports the detected objects via MQTT protocol primarily for integration with HomeAssistant.
• Allows to control video decoder using the commands published over MQTT.
• Broadcasts video stream with rendered object detections in MPEG-TS and Motion JPEG formats over HTTP.
• Captures video from any source and encodes video with rendered object detections in any format supported by FFmpeg.

Being applicable in CCTV, Watsor also suits other areas, where object detection in video stream is required.