RidgeRun Software Developer Blog

Explore the key challenges of embedded vision in robotics and how RidgeRun helps teams integrate cameras, LiDAR, ROS 2, Edge AI, real-time perception, and low-latency teleoperation into production-ready robotic systems.

Explore the NVIDIA Jetson Thor T2000 and T3000, compact Blackwell-powered modules for robotics and edge AI. Compare their specifications, applications, and benefits, and learn how RidgeRun supports integration, migration, AI optimization, camera development, and production deployment.

Embedded vision and Edge AI are transforming medical and healthcare systems by enabling real-time imaging, low-latency streaming, patient privacy protection, and smarter medical device workflows directly at the edge.

As embedded systems and IoT solutions continue to adopt AI-driven capabilities, the demand for powerful and energy-efficient platforms continues to grow.. The Dragonwing IQ-9075 EVK board maximizes the features of the Dragonwing IQ-9075 processor, optimized for industrial IoT, Edge AI, and robotics applications, being able to sustain through demanding workloads and offering a high-performance power efficient computing power, on-device AI with a dedicated NPU, and a camera an

Qualcomm Dragonwing IQ-9075 is an embedded SoC platform designed for demanding edge AI, multimedia, robotics, drone, and industrial vision applications. As part of Qualcomm’s Dragonwing portfolio, it targets industrial, enterprise, and embedded systems that require high-performance processing, power-efficient AI, advanced connectivity, and long-term deployment support. About the board The Dragonwing IQ-9075 platform delivers high-compute, power-efficient AI performance with t

RidgeRun helps industrial automation teams integrate embedded vision, Edge AI, real-time video processing, and sensor systems to improve quality inspection, remote monitoring, predictive maintenance, and smarter decision-making on the production floor.**

Real-time AI at the edge is reshaping industries from medical devices to broadcast media. NVIDIA’s ecosystem—GStreamer, DeepStream, Holoscan SDK, and Holoscan for Media—offers multiple approaches to building streaming AI pipelines, each with distinct trade-offs in latency, scalability, and architecture. This deep dive clarifies how these frameworks differ and when to use each.

The NXP i.MX95 platform is designed to meet the growing demands of edge AI and modern embedded systems, combining heterogeneous processing, a dedicated Neural Processing Unit (NPU), and advanced multimedia capabilities. This article provides a decision-focused overview of its architecture, software ecosystem, and key use cases, helping technical leaders evaluate its suitability for industrial, automotive, and intelligent IoT applications.

In previous articles, we discussed camera interfaces and camera shutter technologies. Now, we'll explore how embedded vision applications increasingly use multiple cameras for stereo depth, 360° vision, or just increased coverage...

This post explains camera interfaces used in embedded vision applications, so you can select the right fit for your use case...

Enable Data Plane Development Kit DPDK on NVIDIA Jetson

We demonstrate that it is possible to reduce the glass to glass latency by almost 10% by optimizing the ISP pipeline with CUDA ISP

Measuring the glass to glass latency of the Holoscan Sensor Bridge and the NVIDIA Jetson AGX Orin interconnected over ethernet

Accelerating Deep Learning with FPGAs in a nutshell. Exploring the different architectures and implementations for low-latency inference

Select the best hardware device for AI and deep learning inference acceleration

FPGA development flow, part 1. Using Hardware Description Languages to get started using System Verilog.

RidgeRun Video Stabilization Libary is the novel IMU-aid video stabilization for embedded systems on drones, robotics and surveillance

Reduce sensor capture latency with the Low Latency Holoscan Sensor Bridge

CPU, GPU and FPGA help to perform hardware acceleration. Here, we detail some of the considerations to consider each of them

FPGAs are versatile and powerful devices and outstand the traditional processing circuits like CPUs and GPUs in latency