tensorrt for yolo series (YOLOv11,YOLOv10,YOLOv9,YOLOv8,YOLOv7,YOLOv6,YOLOX,YOLOv5), nms plugin support

Aim-bot based on AI for all FPS games

Aim-bot based on AI for all FPS and TPS games

Train Yolo with C#

Web-based real-time object detection for YOLO model.

EasyShield Anti Spoofing AI Model for edge devices (State-of-the-art) performance (Open Source) Deep Learning Model

YOLOv9 / YOLOv10/YOLO11/YOLO12 - Players Identification of CS2

Real-time monitoring, object tracking, and line-crossing detection for CCTV camera streams.

YOLO and TensorFlow.js to find and recognize objects in image, video, and webcam content.

In this project, we built a real-time object detection and tracking system using YOLOv12, leveraging the COCO dataset for its diverse object classes. It combines state-of-the-art detection accuracy with live tracking capabilities for seamless and efficient performance.

Automate the YOLO training by Ultralytics for custome COCO datasets

[2026 IEEE Conference on Artificial Intelligence (CAI26)] · A modular computer vision and NLP pipeline for automated extraction of personal names from broadcast news videos, combining YOLOv12-based news graphic detection, OCR text recognition, and NER models to generate structured name timelines.

AIegis Beam (formerly known as Mini C-RAM (Counter Rocket, Artillery & Mortar)), the real-time drone detection/tracking system (university capstone project).

High-performance browser-based AI library for real-time object detection (YOLO12) and pose estimation (RTMW) using ONNX Runtime Web

model training example

A YOLO model is fine-tuned to detect explicit and harmful content in images and videos. The model’s bounding box coordinates are used by a Python script to automatically blur the identified content.

Real-time Road Sign Detection using YOLO12 with a web demo

This project uses a YOLO-based computer vision model to detect falls from video input and trigger alerts if a person remains on the ground for more than 10 seconds.

Aiming to be a more modular YOLO training and detection script pairing. Designed for custom model development and deployment with built-in surveying / logging tools.

This project was presented at the 2025 6th International Conference on Computers and Artificial Intelligence Technology (CAIT 2025). The work has been accepted for publication in the IEEE conference proceedings and will be updated with the official DOI and publication link once available.