Internet of Things for Underwater Shrimp Image Detection Using Blob Detector

Measuring biomass content is an important stage in harvesting shrimp as it will determine the harvest time. Manual detection has caused stress and eventually death; therefore, a new determination required. This research aims to design IoT technique-based measurement, using underwater video with fog cloud computing processes easily detect underwater, irrespective of complex noise. The method consists several steps: image processing grayscale, thresholding, contour edge detection, labeling, blob detection. results revealed that highest SSIM value thresholding process was 0.18, while lowest MSE 91.35. In addition, process, PSNR 3.6, 2.06. produces maximum key performance 566, 411, 387 Laplacian Gaussian (LoG), Difference (DoG), Determinants Hessian (DoH) methods, respectively. Quality Service (QoS) obtained throughput, loss, delay values 832.25, 0%, 7.25 ms, respectively, data acquisition computation processes, three parameters at very good level. conclusion, model suitable for because non-invasive method, contains high QoS level high-speed process.