YoloV8-ncnn-Raspberry-Pi-4 and YoloX-Tracking-ncnn-RPi_64-bit

These are competitors, offering different YOLO models (v8 vs. X) for object detection on a bare Raspberry Pi using the ncnn framework, implying a choice between the two for a given deployment.

Maintenance 0/25
Adoption 10/25
Maturity 16/25
Community 14/25
Maintenance 0/25
Adoption 6/25
Maturity 16/25
Community 16/25
Stars: 118
Forks: 13
Downloads:
Commits (30d): 0
Language: C++
License: BSD-3-Clause
Stars: 19
Forks: 7
Downloads:
Commits (30d): 0
Language: C++
License: BSD-3-Clause
Stale 6m No Package No Dependents
Stale 6m No Package No Dependents

About YoloV8-ncnn-Raspberry-Pi-4

Qengineering/YoloV8-ncnn-Raspberry-Pi-4

YoloV8 for a bare Raspberry Pi 4 or 5

This project enables real-time object detection directly on a Raspberry Pi 4 or 5, transforming live camera feeds or images into identified objects with bounding boxes. It's designed for hobbyists, educators, or engineers who need to deploy computer vision solutions on low-cost, embedded hardware without cloud services. You provide video frames or images, and it outputs recognized objects and their locations.

edge-computing robotics computer-vision automation embedded-systems

About YoloX-Tracking-ncnn-RPi_64-bit

Qengineering/YoloX-Tracking-ncnn-RPi_64-bit

YoloX with tracking for a bare Raspberry Pi 4 using ncnn.

This project helps you accurately track multiple individual objects moving within a video stream, even when they temporarily block each other. It takes a video file or live camera feed as input and outputs the same video with bounding boxes and unique IDs for each detected object, allowing you to follow their paths over time. It's designed for engineers or hobbyists building custom computer vision applications on a Raspberry Pi 4.

embedded-vision object-tracking robotics surveillance edge-ai

Scores updated daily from GitHub, PyPI, and npm data. How scores work