Roboflow Changelog: April 2022

April showers brings May flowers, and here's a bouquet of flower datasets from Roboflow Universe (opens in a new tab) you can use today! Each month, we share a recap of product and company updates; if you missed last month's edition of the Roboflow Changelog, you can find it here.

A note on licensing: YOLOv5 is released under AGPL-3.0, which affects commercial use:

• On Roboflow cloud: a commercial license is included for every user, including the free plan.
• Self-hosted: you need an Enterprise license add-on, or you must open-source your application under AGPL-3.0.
• Permissive alternative: RF-DETR (opens in a new tab) is Apache 2.0, free for commercial use anywhere.

Roboflow Organize and Annotate

• Updated onboarding flow to make sign up and inviting team members easier
• Launched Instance Segmentation as a new project type
• Improvements to image & usage counting

Roboflow Train and Deploy

• Added Segmentation as an export type
• Offline support for enterprise GPU inference
• Launched private beta of native OAK deploy (contact sales to get on the list)
• Launched private beta of native iOS & react native deploy (contact sales to get on the list)

Roboflow Universe (opens in a new tab)

• New search engine to help users search by subject and metadata
• Released 65k datasets to the public for download
• Improved error messages for inference widget

Other

• Company onsite in Miami!
• Added 3 new team members
• Opened several positions (come help us democratize computer vision!)
• 19 bug fixes
• 32 discussions on the Roboflow Forum (opens in a new tab)
• 65k new Universe projects (opens in a new tab)
• 5 new blog posts
• 1 new YouTube videos (opens in a new tab)
• Featured in/by: OpenCV Weekly (opens in a new tab), Los Angeles Inoculum (opens in a new tab), Sydney Informatics Hub (opens in a new tab), Red Buffer (opens in a new tab), Sparkfun series (1st (opens in a new tab), 2nd (opens in a new tab), 3rd (opens in a new tab)), AI Express (opens in a new tab), Vantage (opens in a new tab)
• User projects: Trust-driven reinforcement selection strategy for federated learning on IoT devices (opens in a new tab), Intelligent automation of invoice parsing using computer vision techniques (opens in a new tab), Image-Based Parking Occupancy Detection Using Deep Learning and Faster R-CNN (opens in a new tab), Fruits and Vegetables Recognition using YOLO, (opens in a new tab) Fire detect using custom datas and yolov5 From Colab (opens in a new tab), A Framework for Pothole Detection via the AI-Blockchain Integration (opens in a new tab), Detecting key Soccer match events to create highlights using Computer Vision (opens in a new tab), Convolutional Neural Networks Hyperparameter Tunning for Classifying Firearms on Images (opens in a new tab), Tutorial Anotasi dan Augmentasi Dataset pada Roboflow (opens in a new tab), Flower Detection with YOLOv5 (opens in a new tab), YOLO-Object-Detection-for-Pick-and-Place-task-using-ROS-on-KUKA-iiwa (opens in a new tab), PCB-Defect-Detection-using-Deepstream (opens in a new tab), A9-Dataset: Multi-Sensor Infrastructure-Based Dataset for Mobility Research (opens in a new tab), Image Detection and Recognition of different species of animals using Deep Learning (opens in a new tab), Face Mask Detection Based on Machine Learning and Edge Computing (opens in a new tab), Detection of Plant Diseases Using Leaf Images and Machine Learning (opens in a new tab), FD-YOLOv5: A Fuzzy Image Enhancement Based Robust Object Detection Model for Safety Helmet Detection (opens in a new tab), Pothole Detection Using Deep Learning: A Real-Time and AI-on-the-Edge Perspective (opens in a new tab), ArkiCity: Analysing the Object Detection Performance of Cloud-Based Image Processing Services Using Crowdsourced Data (opens in a new tab), Traffic Images Captured from UAVs for Use in Training Machine Vision Algorithms for Traffic Management (opens in a new tab), Ping Pong (opens in a new tab), YOLOX Roboflow 2022 (opens in a new tab), Computer Vision for Road Imaging and Pothole Detection: A State-of-the-Art Review of Systems and Algorithms (opens in a new tab), A two-stage automatic labeling method for detecting abnormal food items in X-ray images (opens in a new tab), City of Rochester (opens in a new tab)