Pengembangan Metoda Deteksi Rintangan untuk Traktor Tanpa Awak Menggunakan Kamera CCD
Abstract
Abstrak
Kemampuan menghindari rintangan pada lahan kerja berupa pohon, batu, lubang, pematang, manusia, dan benda-benda lainnya yang tidak mungkin dilewati diperlukan oleh traktor yang dioperasikan tanpa awak berbasis GPS. Sistem pengindera lingkungan sekitar menggunakan kamera CCD memungkinkan untuk mendeteksi rintangan yang berada di depan traktor secaral realtime. Namun dengan kemungkinan beragamnya obyek yang ditangkap oleh kamera, pengolahan citra menjadi kompleks dan membutuhkan waktu yang relatif lama sehingga tidak cocok untuk diaplikasikan. Penelitian ini mencoba mengembangkan metoda deteksi rintangan pada lahan kerja traktor tanpa awak yang lebih sederhana dengan penambahan sinar laser merah pada kamera CCD yang digunakan. Sinar laser merah yang tertahan pada rintangan memberikan informasi pada sistem pengindera bahwa di depan ada rintangan, dan jaraknya dari traktor dihitung berdasarkan prinsip phitagoras. Hasil penelitian menunjukkan bahwa semua rintangan berjarak 1 m, 80% rintangan berjarak 2 m, dan 40% rintangan berjarak 3 m dapat dideteksi. Rintangan yang berjarak lebih dari 3 m dari traktor belum dapat dideteksi karena kekuatan sinar laser yang menurun dengan bertambahnya jarak. Akurasi dalam pendugaan jarak secara keseluruhan untuk rintangan yang terdeteksi juga masih rendah, yaitu 67.5%.
Kata Kunci: traktor tanpa awak, sistem deteksi, rintangan, pengolahan citra
Abstract
For unmanned tractor guided by global positioning system, ability for eluding obstacles such as trees, big stone, cavity, bund, people, and other objects in the work area is very important in order not to stop the operation.Surrounding detection system using CCD camera makes it possible for unmanned tractor to detect obstacles in front of it realtime. However, with so many different objects that may captured by the camera, it will need a lot of image processing steps that takes a lot of time so it is no longer suitable for realtime detection in application. The proposed research is aimed to develop a simpler obstacle detection method by adding a red laser pointer to the CCD camera used to capture scene in front of the tractor. The red laser light that reflected by an obstacle gives an important information in the image, and the distance of the obstacle could be calculated based on phytagoras theory. The results showed that all obstacles with 1 m distance, 80% obstacles with 2 m distance, and 40% obstacles with 3 m distance could be detected. Obstacles with more than 3 m distances could not be detected due to weak laser light for the distances. The accuracy of distance prediction for all situation is 67.5%, which is still need improvements.
Key Words: unmanned tractor, detection system, obstacle, image processing
Diterima: 01 November 2011; Disetujui: 04 Maret 2012
Authors
Authors submitting manuscripts should understand and agree that copyright of manuscripts of the article shall be assigned/transferred to Jurnal Keteknikan Pertanian. This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License (CC BY-SA) where Authors and Readers can copy and redistribute the material in any medium or format, as well as remix, transform, and build upon the material for any purpose, but they must give appropriate credit (cite to the article or content), provide a link to the license, and indicate if changes were made. If you remix, transform, or build upon the material, you must distribute your contributions under the same license as the original.