Article may be outdated

This article is 69 days old. Some details may have changed since publication.

Hacker News·4 min read·hard

Show HN: Dual YOLOv8n UAV Detection on RK3588S at 42 FPS Using NPU

A
alebal123bal
Show HN: Dual YOLOv8n UAV Detection on RK3588S at 42 FPS Using NPU
AI Summary

Developers have implemented a high-performance computer vision pipeline on the Rockchip RK3588S SoC, achieving 46 FPS for UAV detection using YOLOv8n. The system utilizes fixed-function hardware to keep CPU usage low and integrates an on-device LLM for natural language assessment of tracked objects.

Why it matters

This demonstrates efficient edge computing capabilities, allowing complex AI tasks like object detection and LLM-based analysis to run on low-cost, low-power hardware.

Dive DeeperCreate a free account to unlock

Real-time YOLOv8n UAV detection at the sensor's 46 FPS ceiling, in ~140 MB of RAM. A high-throughput, low-footprint computer-vision pipeline for the Rockchip RK3588S SoC: it captures live 1080p MIPI frames, runs YOLOv8n across all 3 NPU cores in parallel (lifting throughput from ~31 to 46 FPS — the camera, not the pipeline, is now the limit), and streams the annotated result to HDMI or RTSP. Capture, color-convert/resize and inference run entirely on fixed-function silicon (ISP, RGA, NPU), so the CPU stays free and memory holds flat at ~140 MB per stream — small enough to run on even the cheapest 2 GB RK3588S boards, not just high-end dev kits. Targets any RK3588S board; built and tested on the Khadas Edge2 .

Continue reading on Headlinne

Create a free account to read the full article.

Read full article →
technologyscience
Political Bias
Center
LeftLean LCenterLean RRight
Confidence: 95%

The content is a technical project showcase with no political or social bias.

Get smarter about the news

Sign up free for a feed built around what you actually care about, Dive Deeper research on any story, and the full text of every article.

Create free account

Already have an account? Sign in