This repository is based on shouxieai/tensorRT_Pro, with adjustments to support YOLOv8.

Converting COCO annotation (CVAT) to annotation for YOLO-seg (instance segmentation) and YOLO-obb (oriented bounding box detection)

Tensorrt codebase to inference in c++ for all major neural arch using onnx

This powerful and flexible application, developed using PyQt6, processes 4 video streams in real-time with the YOLOv8-OBB model, supporting cameras, video files, for efficient object detection and result saving, tailored to meet specific client requirements.

This project is a YOLO based surveillance system designed to assist wildlife conservation efforts. It utilizes a dual-model computer vision pipeline to detect wildlife species and identify potential poaching threats in real-time.

End-to-end, reproducible pipeline for fine-tuning YOLOv8-OBB on SAR imagery, including dataset extraction and validation, exploratory data analysis, annotation cleaning, DOTA-to-YOLO OBB conversion, optimized training, rigorous evaluation, and interactive Gradio deployment for accurate oriented vehicle detection on SIVED.

Diamorph object detection

YOLOv8 Oriented Bounding Boxes tester

This project interacts with an EPSON VT6-A901S 6-axis articulated industrial manipulator to pick and place microelectonic modules from a table into a depo box using OpenCV, TensorFlow, and TCP/IP messaging.