Spectacular AI SDK (open source parts and public releases)

Python scripts for performing 6D pose estimation and shape reconstruction using the CenterSnap model in ONNX

This is a vision-based 3d model manipulation and control UI

Provides a conversion flow for YOLACT_Edge to models compatible with ONNX, TensorRT, OpenVINO and Myriad (OAK). My own implementation of post-processing allows for e2e inference. Support for Multi-Class NonMaximumSuppression, CombinedNonMaxSuppression.

Latest main K9 robot repository with 3D vision, local STT/TTS with GPT-3 and 360 LIDAR.

my ROS workspace

Lawn robot for spraying weeds

This package enables the integration and operation of the OAK-D camera in ROS 2, allowing users to select different sensors and process image data. It provides configurable options for RGB, stereo, depth, disparity, and point cloud publishing, along with visualization in RViz, making it a versatile tool for computer vision applications

Camera Viewer app for OpenCV OAK-D camera

Data recorder for OAK-D (deprecated, use vio_record.py in OAK-D Python SDK instead)

Single Shot MultiBox Detector deployed on a OAK-D Lite cam via DepthAI

Leg detection and following robot controller using the OAK-D stereoscopic camera and AI accelerator.

Record RGB and stereo video with timestamp using DepthAI OAK-D

A ROS package that captures a target user and reidentifies that target when tracking is lost. Targeted for OAK-D.

Embedded AI solution to aid people with visual impairement involved in research by converting equations and texts from scientific books into Nemeth-Braille

Real-time-hand-held-insect-detection-and-tracking-using-opencv-cameras-in-the-field-the-movie-TM

An easy-to-use and robust library for seamless interaction with OAK cameras and the DepthAI API. It aims to bridge the gap between the DepthAI API and SDK, allowing for built-in integration with OpenCV and Open3D "out-of-the-box."

Person re-identification in open-world settings of retail stores and public spaces

Python package provinding tools for artistic interactive applications using AI

Human Exercise Detection. Depth AI pipeline on device (Luxonis OAK-D light) and host (Raspberry PI 4) for the Tension Terminator. Camera device is installed overhead. Detection is for exercise informations (type, time, correct movement).