RidgeRun Software Developer Blog

Discover how embedded vision and Edge AI enable smarter cities through real-time traffic monitoring, intelligent transportation, public safety, parking management, and infrastructure monitoring while reducing latency and bandwidth requirements.

Embedded products become harder to validate as they evolve. New drivers, peripherals, services, and hardware configurations increase the number of components that must continue working after every software change. When validation happens late, several changes may already be involved. Developers spend more time identifying the cause, QA work may need to be repeated, and releases can be delayed. Frequent validation keeps regressions closer to the changes that introduced them. O

Modern vehicles are expected to do more than transport passengers. They must perceive their surroundings, assist drivers, identify risks, and react in real time. Embedded vision and Edge AI make this possible by processing information from cameras, radar, lidar, and other sensors directly inside the vehicle. Local processing reduces latency and supports reliable operation without depending entirely on cloud connectivity. How Embedded Vision Works in Automotive Systems Embedde

Compare RAM consumption on the NVIDIA Jetson AGX Orin using JetPack 7.2 and a minimal Yocto image. The results show that Yocto reduced idle RAM usage by approximately 32.1%, leaving more memory available for AI models, video pipelines, and other embedded workloads.

Learn how NVIDIA Jetson Agent Skills help developers inspect memory usage, disable unnecessary services, customize the BSP, and validate optimizations to reclaim RAM for larger Edge AI workloads.

Discover how embedded vision and Edge AI support smart agriculture through camera and sensor integration, real-time processing, autonomous machinery, drone video pipelines, remote monitoring, and optimized embedded platforms.

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.

Enabling Secure Boot on an NVIDIA Jetson is often the first milestone toward securing an embedded product. NVIDIA provides excellent documentation explaining how to generate signing keys, and fuse devices, making it possible to establish a trusted boot chain. However, enabling Secure Boot is only the beginning. One of the most common mistakes teams make is assuming that the same process used during development can also be used in production. While this may work for early prot