AI Video Analytics Edge Box — Operating Guide
How to power on the AI video analytics edge box, put it on the LAN, add cameras, configure algorithms and analysis tasks, and review alarms.
Read articleHow to power on the AI video analytics edge box, put it on the LAN, add cameras, configure algorithms and analysis tasks, and review alarms.
Read articleAlarm-push API for the AI video analytics box. A third-party platform receives detection results at a callback URL it configures.
Read articleA GPU (graphics processing unit) and an NPU (neural processing unit) are different kinds of processors. Both speed up computation, but they differ in design goals, architecture, and the jobs they are built for.
Read articleUltralytics has not released YOLO27 yet. This note covers the official preview: COCO mAP 42.3–60.4, dual-scale small models and query-based large models, compared with YOLO26 and YOLOv8 on accuracy and parameter count.
Read articleWhy an on-device agent splits the host from the coprocessor: RK1828 at 20 TOPS, 5 GB of on-chip DRAM, 1 TB/s bandwidth, and about 59 tokens/s on a 7B model.
Read articleCPU, NPU, GPU, memory bandwidth, and video features of three 8 nm AIoT chips, with a choice for vision, multimodal dialogue, and task-running agents.
Read article