# High-precision Object Detection

PaliGemma 2 is an upgraded vision-language model launched by Google, combining the capabilities of Gemma 2 and SigLIP vision models, supporting multilingual image-text interaction tasks.

Florence-2 is an advanced vision foundation model developed by Microsoft, employing a prompt-based approach to handle a wide range of vision and vision-language tasks.

Florence-2 is an advanced vision foundation model developed by Microsoft, employing a prompt-based approach to handle a wide range of vision and vision-language tasks.

Object detection model based on DETR architecture, using ResNet50 as the backbone network, fine-tuned on a specific dataset

An object detection model based on YOLOv8, specifically designed for detecting handwritten text content

An object detection model based on YOLOv8m, specifically designed for smoke detection with high accuracy.

A retail shelf object detection model based on YOLOv8, capable of identifying empty shelves and product locations, suitable for inventory management in supermarkets and malls.

A YOLOv5-based object detection model specifically designed for recognizing American Sign Language (ASL) gestures

An object detection model based on YOLOv5l, specifically designed for detecting leaf diseases.

An object detection model based on YOLOv8, specifically designed to recognize 12 hand seals from 'Naruto'.

A hard hat detection model based on YOLOv8s, used to identify whether safety helmets are worn in images.

A table detection model based on YOLOv8 for identifying table regions in images, supporting both bordered and borderless table detection.

A table detection model based on YOLOv8, capable of identifying table regions in documents, supporting both bordered and borderless table types.

A YOLOv8m-based object detection model specifically designed to detect players and their head positions in CS:GO.

This is a YOLOv5-based object detection model specifically designed for recognizing Rock-Paper-Scissors gestures.

An object detection model based on YOLOv8m, specifically designed for detecting forklifts and personnel, suitable for safety monitoring in industrial scenarios.

A YOLOv5m-based aerial sheep object detection model, specifically designed for detecting sheep in aerial images.

A YOLOv5s-based aerial sheep object detection model, specifically designed for detecting sheep in aerial images.

A smoke object detection model based on YOLOv5s architecture, specifically designed to identify smoke regions in images.

A lightweight smoke object detection model based on YOLOv5n, optimized for smoke recognition tasks

A forklift object detection model based on the YOLOv5m architecture, trained on the keremberke/forklift object detection dataset, achieving an mAP@0.5 of 0.85.

A forklift object detection model based on YOLOv5s, suitable for forklift recognition and positioning in industrial scenarios.

A license plate object detection model based on the YOLOv5m architecture, excelling in license plate detection tasks.

Lightweight license plate detection model based on YOLOv5n, optimized for license plate recognition tasks

A lightweight blood cell object detection model based on the YOLOv5n architecture, optimized for medical image analysis