Early warning flood detector adopting camera by Sobel Canny edge detection algorithm method

Abstract

Early warning of floods is an essential part of disaster management. Various automatic detectors have been developed in flood mitigation, including cameras. But reliability and accuracy have not been improved. Besides, the use of monitoring devices has been employed to monitor water levels in various water building facilities. The early warning flood detector was carried out with a sensor camera using an orange ball that floats near the water level gauge in a bounding box. This approach uses the integration of computer vision and image processing, namely digital image processing techniques, with Sobel Canny edge detection (SCED) algorithms to detect quickly and accurately water levels in real-time. After the water level is measured, a flood detection process is carried out based on the specified water level. According to the results of experiments in the laboratory, it has been shown that the proposed approach can detect objects accurately and fast in real-time. Besides, from the water level detection experiment, good results were obtained. Therefore, the object detection system and water level can be used as an efficient and accurate early detection system for flood disasters.

Perancangan Aplikasi Pengukur Pakaian Berbasis Mobile

“…Canny edge detection adalah sebuah algoritma yang terdiri dari beberapa tahap untuk mendeteksi tepi dalam gambar (Sekehravani et al, 2020). Canny Edge Detection diproses pada 5 langkah yang berbeda (Sundani et al, 2019;Utomo et al, 2021)…”

Perancangan Sistem Detektor Tanaman Kering Berbasis Internet of Things

“…Diantaranya ada alat pendeteksi kelembapan tanaman, penyiram otomatis, pemungut sampah, dan sebagainya. (Mardiana & Riska, 2020;Sugandi & Armentaria, 2021;Utomo et al, 2021). Dari semua alat-alat tersebut mungkin akan lebih baik jika ditambahkan detector tanaman kering.…”

Evaluation of object detectors in recognizing crossroad intersection triangle sign

“…Their results showed a noteworthy classification performance in comparison with the traditional approaches. Utomo et al [10] used integration of digital image processing technique with sobel canny edge detector to estimate the instance water levels in the real world. The experiment showed the technique's validity in detecting an immersing object and the whole system at final can be used in future for flood disasters.…”