High-speed performance is a must for today's computer vision applications, but it comes with many challenges. These include processing a high volume of frames per second (FPS), which requires not only fast algorithms, but also efficient data storage to handle the large quantities of images being processed in real time.

Traditional annotation methods are often time-consuming and labor-intensive for training machine learning models. In other words, they create bottlenecks that slow down projects from getting done.

At the same time, Roboflow was designed to address the challenges associated with annotating data, but manually labeling all images is often tedious and unrealistic. In this case, ReductStore can provide the tools to query, filter, and replicate specific images for further annotation and training.

In this article, we'll explain how Roboflow can help reduce the time and effort required to annotate images, and how ReductStore can be used to store and filter important images.

Deploying a vision model like YOLOv10 at the edge has become a game-changer for real-time object detection. Developed by researchers at Tsinghua University, YOLOv10 introduces architectural innovations that optimizes speed and accuracy, making it ideal for vision tasks that require low inference latency.

This article provides resources for training a YOLOv10 model and managing data storage for real-time performance on edge devices. We will look at a combination of tools, including Roboflow for dataset preparation, Ultralytics for model training, and ReductStore for efficient data storage.

We are pleased to announce the release of the latest minor version of ReductStore, 1.12.0. ReductStore is a time series database designed for storing and managing large amounts of blob data.

To download the latest released version, please visit our Download Page.

What's new in 1.12.0?​

Over the last few months we've been working hard to make ReductStore even more powerful and efficient as a central repository for your time series data. Where you can collect data from a variety of sources, including IoT and edge devices, and store it in one place for further analysis and processing.

In this release, we've added a new record delete API that allows you to remove specific records from an entry. This can be useful if you want to clean up your data or remove obsolete records and need more flexibility than FIFO bucket quotas. We have also optimised the storage engine to improve overall performance when reading and writing data.