Tried AprilTag samples useful for industrial applications.

産業用Raspberry Pi「PL-R4」にカメラを繋ぎ、PiLink株式会社で用意したサンプルプログラムを使い、印刷したAprilTagを検出させてみました。AprilTagの仕組みは、カメラによる位置情報や姿勢を高精度に検出する単純なものです。一見シンプルな仕組みに見えますが、実際には奥深い設計思想と多彩な用途があります。そのため、すべてをご紹介することはできません。 「AprilTagってなに?」、「自社の現場で取り入れられないかな?」とお考えの方に向けて、試した限りではありますが、基本部分に沿った内容でご紹介します。 What is AprilTag? AprilTagは、2011年頃に米国ミシガン大学の研究チーム(主にEdwin Olson氏の研究グループ)によって開発されました。名前の「April」は、「4月」の意味ですが、”4月にプロジェクトを始めたから”といった軽い理由で名付けられたとされています。つまり、名称自体には深い意味はありません。 AprilTagは、一見するとQRコードに似ています。二次元バーコードの種類という意味でも似ています。どうやらQRコードよりも小さいデータ(4ビットから12ビット)を扱うために設計され、検出の精度が高いことや、計算が速くリアルタイム制であること、遠くからの検出も可能な点が特徴的です。暗かったり、低コントラストでも読み取ることが可能です。 サンプルプログラムを使うと分かるのですが、AprilTagをカメラで捉えると、カメラに対する正確な3D位置をリアルタイムで計算し表示できます。かなりの精度だと思いました。3Dボックスを表示させるわけですけど、Raspberry Piでもかなりスムーズです。3Dボックスを表示させるわけですけど、Raspberry Piでもかなりスムーズです。 The lower left image is quite close to the camera, but it can be recognized if all the tags are within the camera.In the lower right image, we made the detection very dark, but you can see that it is properly recognized. QR codes are rather specialized in the amount of information, while AprilTag is specialized only in location and posture information.This is why it has been used in robotics. その意味でも、ミドルウェアのROSを介して利用されるのが一般的です。ただ、AprilTagのライブラリはC言語で書かれているため、簡単な画面・操作インターフェイスであれば、C++やPythonのスタンドアロンで手軽に利用できます。今回のようにテスト目的であれば、Pythonプログラムを使ったRaspberry Pi でも手軽に扱うことができます。産業用Raspberry Piであれば各現場に導入できますね。 A type of TagFamily There are different types of AprilTag, called TagFamily. Each has a different specification. The reason is that they are used…

Announcing the PL-R5 Industrial Raspberry Pi with Raspberry Pi CM5 as a standard feature
-Supports Single Pair Ethernet (SPE) and USB 3.0, ideal for embedded applications-.

The latest model of industrial Raspberry Pi with CM5 This product is the latest model in the industrial Raspberry Pi PL-R series, featuring a design that combines the stability, reliability, and expandability required in industrial settings. The new model is equipped with the Raspberry Pi Compute Module 5 (CM5). The IP65 waterproof design allows for outdoor use. The new interface includes a USB 3.0 port and a single-pair Ethernet (SPE) port*, and an option to add an AI accelerator to the M.2 slot for expansion. The new CM5 offers a more flexible and high-performance option for developing applications for smart factories and robotics. *Single pair Ethernet port is implemented in…

Python programming taught by ChatGPT
Data acquisition and graph display with temperature/humidity sensor SHT30

Not many people can handle programming at will. This is especially true if it is not part of their job. However, it is no longer necessary to know how to program at all. I am also one of those people who cannot write programming code from a completely blank sheet of paper. So far, there was nothing I could do about it, but with ChatGPT, I can now explore mistakes and questions in my code. ChatGPT, which has been available to everyone since 2022, has evolved considerably since its introduction. The ability to ask questions is important because it is used in the form of asking questions and receiving answers,…

Japan IT Week 2025 Spring IoT & Edge Computing EXPO

PiLink Co., Ltd. will exhibit at the 28th IoT Edge Computing EXPO Spring, which will be held within Japan IT Week 2025 Spring at Tokyo Big Sight from April 23 (Wed.) to 25 (Fri.), 2012. At the PiLink booth, we will introduce and demonstrate our latest lineup of industrial Raspberry Pi products. We look forward to seeing you at the show and will be presenting solutions that contribute to IoT, efficiency, and problem solving at manufacturing sites. Pre-registration is required, so please register by clicking the registration link at the bottom of this page. Exhibit Outline Exhibitor Conference “Industry’s Highest Environmental Resistance Industrial Raspberry Pi Enables Smart Factories.” In this…

7 OSes that can be utilized with the Raspberry Pi CM4

The factory image of PiLink’s industrial Raspberry Pi PL-R4 with the CM4 installed has the Raspberry Pi OS installed; Ubuntu can also be run on models with 4GB RAM or more. There are many other operating systems that can be run on the Raspberry Pi, so we will introduce the 7 operating systems that can be installed* on the Raspberry Pi CM4.

Benchmark test comparison of the new Compute Module 5 with the previous CM4

The new Compute Module 5 (“CM5”), like the commercially available Raspberry Pi 5, has a significant performance boost.Therefore, we tried benchmark tests with Compute Module 4 (“CM4”) and CM5.We used Geenbench and PiBenchmarks. The PL-R4 and PL-R5M were used for the trial.The operating system for the “PL-R4” with CM4 is bullseye and the “PL-R5M” with CM5 is bookworm.Each is activated by eMMC. Geekbench Geekbench, the famous benchmark test, can be run on the Raspberry Pi. However, only the preview version, which is treated as a beta version, is supported. This is because the CPU is an Arm. Geekbench preview version: https://www.geekbench.com/preview/ For Linux, I found that it is compatible with…