Smart Goal Keeper Prototype using Computer Vision and Raspberry Pi

Ahmed, Syed Umaid; Ayaz, Hamza; Khalid, Hamza; Ahmed, Anas Fouad; Affan, Mohammad; Din, Muhammad

doi:10.1109/acit49673.2020.9208910

Cited by 2 publications

(2 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The applications of CV proved to be a great problem solver in real-time applications. Several CV application studies have been carried out, such as detecting a compact fluorescence lamp [ 1 ], recognizing speed limit traffic signs using a shape-based approach [ 2 ], detecting sugar beetroot crops with mechanical damage [ 3 ], designing of an autonomous underwater vehicle that performs computer-vision-driven intervention tasks [ 4 ], tracking of ball movement in a smart goalkeeper prototype [ 5 ], and recognizing an obstacle on a powered prosthetic leg [ 6 ]. These papers all utilized a single-board computer for real-time deployment.…”

Section: Introductionmentioning

confidence: 99%

Optimizing Face Recognition Inference with a Collaborative Edge–Cloud Network

Oroceo

Kim

Caliwag

et al. 2022

Sensors

View full text Add to dashboard Cite

The rapid development of deep-learning-based edge artificial intelligence applications and their data-driven nature has led to several research issues. One key issue is the collaboration of the edge and cloud to optimize such applications by increasing inference speed and reducing latency. Some researchers have focused on simulations that verify that a collaborative edge–cloud network would be optimal, but the real-world implementation is not considered. Most researchers focus on the accuracy of the detection and recognition algorithm but not the inference speed in actual deployment. Others have implemented such networks with minimal pressure on the cloud node, thus defeating the purpose of an edge–cloud collaboration. In this study, we propose a method to increase inference speed and reduce latency by implementing a real-time face recognition system in which all face detection tasks are handled on the edge device and by forwarding cropped face images that are significantly smaller than the whole video frame, while face recognition tasks are processed at the cloud. In this system, both devices communicate using the TCP/IP protocol of wireless communication. Our experiment is executed using a Jetson Nano GPU board and a PC as the cloud. This framework is studied in terms of the frame-per-second (FPS) rate. We further compare our framework using two scenarios in which face detection and recognition tasks are deployed on the (1) edge and (2) cloud. The experimental results show that combining the edge and cloud is an effective way to accelerate the inferencing process because the maximum FPS achieved by the edge–cloud deployment was 1.91× more than the cloud deployment and 8.5× more than the edge deployment.

show abstract

Section: Introductionmentioning

confidence: 99%

Optimizing Face Recognition Inference with a Collaborative Edge–Cloud Network

Oroceo

Kim

Caliwag

et al. 2022

Sensors

View full text Add to dashboard Cite

show abstract

“…Secara umum, robot sepak bola dibagi menjadi dua kategori, yaitu humanoid dan beroda. Robot humanoid adalah robot yang memiliki bentuk seperti manusia dengan dua tangan, dua kaki, batang tubuh, dan kepala [8]. Namun, robot humanoid memiliki kekurangan di antaranya adalah kebebasan gerak, keseimbangan, dan biaya pembuatan.…”

unclassified

Sistem Deteksi Bola pada Robot Kiper Pemain Sepakbola Beroda

Fatekha¹,

Dewantara²,

Oktavianto³

2021

View full text Add to dashboard Cite

Perkembangan pada dunia robotika pada saat ini semakin pesat, di mana robot dapat berguna dalam setiap kegiatan manusia. Di Indonesia ajang kontes robot sudah dilakukan pada setiap tahunnya baik tingkat regional dan tingkat nasional. Salah satu kategori yang ingin dibahas dalam penelitian ini adalah kategori Kontes Robot Sepakbola Indonesia (KRSBI). Pada kategori ini, robot harus bisa bernavigasi untuk mencari bola dan menendang kearah gawang. Tujuan utama dari robot ini adalah bernavigasi dan mencari bola sampai kearah gawang lawan. Robot sepakbola beroda merupakan salah satu kategori robot yang pertama kali dipertandingkan pada KRI (Kontes Robot Indonesia) 2018 kategori KRSBI (Kontes Robot Sepakbola Indonesia) Beroda. Robot sepakbola dikembangkan agar memiliki fungsi yang mirip dengan pemain sepakbola pada umumnya yaitu mengejar bola, menggiring bola, dan menendang bola. Salah satu permasalahan yang masih dikembangkan sampai saat ini adalah bagaimana robot mampu mendeteksi bola menggunakan sensor kamera (webcam). Deteksi bola merupakan salah satu langkah awal dalam menentukan aksi selanjutnya robot sepakbola beroda seperti mengejar, menggiring, dan menendang bola. Karena bola yang digunakan pada pertandingan berwarna oranye maka pada penelitian ini dikembangkan pendeteksian bola menggunakan metode filter warna. Robot penjaga gawang bertugas untuk dapat menghadang bola berwarna oranye memasuki gawang. Robot tersebut harus mampu mendeteksi bola dengan akurat untuk menentukan pergerakan robot selanjutnya. Artikel ini mendeskripsikan pengembangan robot penjaga gawang yang mampu mendeteksi warna dan bentuk bola dengan metode HoughCircle dan approxPolyDP.

show abstract

Smart Goal Keeper Prototype using Computer Vision and Raspberry Pi

Cited by 2 publications

References 8 publications

Optimizing Face Recognition Inference with a Collaborative Edge–Cloud Network

Optimizing Face Recognition Inference with a Collaborative Edge–Cloud Network

Sistem Deteksi Bola pada Robot Kiper Pemain Sepakbola Beroda

Contact Info

Product

Resources

About