← Latest products

Dual YOLOv8n UAV Detection on RK3588S at 42 FPS Using NPU

Real-time YOLOv8n UAV detection on the RK3588S NPU | saturates the sensor at 46 FPS | ~140 MB RAM | fully hardware-accelerated (ISP+RGA+NPU) | on-device LLM scene summaries.

Open source

93 stars · GitHubexternal site

Visit github.comexternal site

Reactions (1)

Similar products

by description similarity

  1. Neurox

    github.com

    GPU Observability for AI Infra

    Hacker News25 pts

  2. A 6M-token movable window on a single 46GB GPU

    arxiv.org

    Abstract page for arXiv paper 2607.23806: A Frozen 12B Beats Frontier Models on Verified Work: 100% Accuracy, 0 Tokens, Bit-Exact, Forever

    Hacker News7 pts

  3. DDoS detection in 0.9s

    flowtriq.com

    tested against a 48 Gbps attack live

    Hacker News15 pts

  4. OS Megakernel that match M5 Max Tok/w at 2x the Throughput on RTX 3090

    github.com

    LLM speculative inference server for heterogeneous hardware & consumer GPUs

    Hacker News6 pts

  5. Clearcam

    github.com

    Add AI object detection to your IP CCTV cameras

    Hacker News233 pts