Self-hosted, local only NVR and AI Computer Vision software. With features such as object detection, motion detection, face recognition and more, it gives you the power to keep an eye on your home, office or any other place you want to monitor.

Object detection for video surveillance

YOLOv4 Implemented in Tensorflow 2.

MambaCoral-DiffDet code and Dataset

TensorFlow Lite, Coral Edge TPU samples (Python/C++, Raspberry Pi/Windows/Linux).

SCoralDet and SCoralDet Dataset

Google Coral on the Raspberry Pi 4

Cat with prey detection on Raspberry Pi. Lock cat pet flap if prey is detected. Object detection implemented in TFLite with ImageNet v1 SSD. Inference on EdgeTPU (Google Coral USB). Stores images on AWS S3 and sends notifications to iOS device.

ROS package for Coral Edge TPU USB Accelerator

This is a PyTorch implementation of the Unsupervised Domain Adaptation method proposed in the paper Deep CORAL: Correlation Alignment for Deep Domain Adaptation. Baochen Sun and Kate Saenko (ECCV 2016).

This example will help you deploy a streaming camera feed with realtime people detection using the Coral Edge TPU for on-device ML inferencing.

Tools for annotating and developing ML models for benthic imagery

TPU accelerated traffic lane segmentation engine for your Raspberry Pi

some scripts I used to test Google's Edge TPU

Raspberry Pi Supplement to Coral Edge TPU Demo

ThinkBioT is an Bioacoustic sensor framework for the collection, processing and satellite transmission of Bio-Taxa Classification and Acoustic Indices data.

Bachelor Thesis. This work consists of designing a miniature autonomous car that can follow a road, detect signalisations and obstacles.

A Keras-based Python implementation of U-Net, capable of identifying annual density boundaries present in coral skeletons

Webstreaming classification with Google edge TPU on the picamera and balenaFin