Show simple item record

dc.contributor.advisorSuhardiyanto, Herry
dc.contributor.advisorSolahudin, Mohamad
dc.contributor.authorfansuri, Fakhri amir
dc.date.accessioned2024-12-07T07:15:38Z
dc.date.available2024-12-07T07:15:38Z
dc.date.issued2024
dc.identifier.urihttp://repository.ipb.ac.id/handle/123456789/160094
dc.description.abstractLahan pertanian yang semakin terbatas mendorong penerapan teknologi hidroponik di dalam greenhouse untuk membudidayakan tanaman sayuran daun. Pertumbuhan tanaman sayuran daun di dalam greenhouse perlu dimonitor secara real-time untuk menjadi dasar bagi pengendalian lingkungan pertumbuhan tanaman tersebut. Namun, untuk proses budidaya tanaman sayuran daun di dalam greenhouse yang luas, monitoring pertumbuhan tanaman tersebut secara akurat memerlukan suatu sistem monitoring yang unggul. Penelitian ini bertujuan untuk merancang plant phenotyping system berbasis Internet of Things (IoT), yang mencakup perangkat keras dan perangkat lunak sehingga mampu memonitor pertumbuhan tanaman sayuran daun di dalam greenhouse secara real-time. Plant phenotyping system ini dirancang untuk mengambil citra tanaman menggunakan kamera, mengirim data ke server, dan menampilkan hasilnya secara real-time pada website melalui user interface. Penelitian ini mencakup tahapan-tahapan analisis sistem, perancangan, implementasi, pengujian, dan evaluasi kinerja. Hasil penelitian menunjukkan bahwa plant phenotyping system yang dikembangkan dapat mengambil citra seluruh tanaman yang berada di sebelah kanan dan kiri perangkat sistem tersebut dengan ukuran panjang 80 cm dan lebar 60 cm. Citra yang diambil dalam setiap pengambilan citra meliputi 72 citra tanaman. Mutu seluruh citra tanaman yang diambil memadai untuk dianalisis. Perangkat sistem tersebut dilengkapi motor listrik yang dapat menggerakkan perangkat sistem tersebut untuk maju di atas rel dan mengambil citra setiap 52 cm dengan overlap sebesar 8 cm. Ketinggian kamera bervariasi antara 112 cm dan 124 cm tergantung posisi tanaman terhadap kamera karena tanaman dibudidayakan di saluran larutan hara yang memiliki kemiringan 0,03 %. Waktu total rata-rata yang dibutuhkan untuk pengambilan citra hingga kembali ke titik semula adalah 40 menit. Citra diolah menggunakan deep learning untuk memperoleh nilai luas permukaan daun. Hasil citra dapat diakses secara real-time melalui website, sehingga memudahkan pengguna dalam memonitor kondisi tanaman. Increasingly limited agricultural land is encouraging the application of hydroponic technology in greenhouses for cultivating leafy vegetable crops. The growth of these leafy vegetables in the greenhouse must be monitored in real-time to provide a basis for environmental control of the plants' growth. However, accurately monitoring the growth of leafy vegetables in a large greenhouse requires a robust monitoring system. This research aims to design a plant phenotyping system based on the Internet of Things (IoT), which includes both hardware and software components, enabling real-time monitoring of leafy vegetable plants in the greenhouse. The system is designed to capture images of the plants using a camera, send the data to a server, and display the results in real-time on a website via a user interface. The research encompasses several stages: system analysis, design, implementation, testing, and performance evaluation. The results indicate that the developed plant phenotyping system can capture images of all plants to the right and left of the system device, covering an area with a length of 80 cm and a width of 60 cm. The images taken in each image capture include 72 plant images. The quality of all images is deemed adequate for analysis. The system device is equipped with an electric motor that moves the system device along a rail, capturing images every 52 cm with an overlap of 8 cm. The camera height varies between 112 cm and 124 cm, depending on the position of the plants relative to the camera as the plants are cultivated in a nutrient solution channel with a slope of 0.03%. The average total time required for image capture to return to the original point is 40 minutes. The images are processed using deep learning techniques to obtain leaf surface area values. Image results can be accessed in real-time through the website, facilitating easier monitoring of plant conditions for users.
dc.description.sponsorshipProyek Dosen
dc.language.isoid
dc.publisherIPB Universityid
dc.titlePengembangan Plant Phenotyping System untuk Monitoring Pertumbuhan Tanaman Sayuran Daun di dalam Greenhouseid
dc.title.alternativeDevelopment of a Plant Phenotyping System for Monitoring the Growth of Leafy Vegetables in Greenhouse
dc.typeSkripsi
dc.subject.keywordhidroponikid
dc.subject.keywordInternet of Things (IoT)id
dc.subject.keyworddeep learningid
dc.subject.keywordplant phenotyping systemid
dc.subject.keywordrobotid


Files in this item

Thumbnail
Thumbnail
Thumbnail

This item appears in the following Collection(s)

Show simple item record