Measurement of debris flow velocity in flume using normal image by space-time image velocimetry incorporated with machine learning

• Published in: Measurement : journal of the International Measurement Confederation 2022-08, Vol.199, p.111218, Article 111218
• Main Authors: Kim, Yeon-joong, Fujita, Ichiro, Hasegawa, Makoto, Yoon, Jong-sung
• Format: Article
• Language: English
• Subjects: Debris flow; Machine learning; STIV; Velocity
• ISSN: 0263-2241; 1873-412X
• DOI: 10.1016/j.measurement.2022.111218

•A flume experiment for two forms of bed materials was conducted presupposing that the particle size distribution was similar to the mixed-particle size state of the actual sediment environment.•The flow velocity can be evaluated according to the characteristics of each debris flow.•STIV acquires continuous images and arranges the positional relationship and brightness values in the image in the direction of the time axis to produce STIs. This method measures the flow velocity based on the angles of the stripes formed in the spatial image.•To develop a model for understanding the image analysis prediction performance of STIs using CNNs. Various methods have been applied to the velocity measurement in the soil and rocks waterway experiment. Although most velocity measurements use observation sensors, soil and rocks are two-phase flow in which water and soil are mixed, and the velocity measurement method using direct contact with soil and sensors has various problems, including the potential for equipment damage and noise. Therefore, a velocity measurement method that employs high-resolution image analysis using a high-speed camera, which is an indirect velocity measurement method, has been proposed. Although the measurement of the velocity using high-resolution image analysis is associated with a very little risk of equipment damage, several problems have been reported, such as expensive system construction costs, analysis methods to eliminate noise present in images, and the low accuracy of the velocity measurement according to the slope (velocity) evaluation by space–time image (STI), indicating the movement velocity for each frame (moving distance). This study aims to measure the velocity of soil and rocks by applying space–time image velocimetry (STIV), which has not yet been applied to the soil and rocks waterway experiment. To evaluate the STIV performance, an indoor waterway experiment was carried out, and the results were compared with the velocity measured using a general-purpose high-speed camera. Machine learning was applied to the STI slope estimation method to improve the performance of the velocity measurement according to the noise interference included in the image. The use of convolutional neural networks (CNNs) is a useful way of extracting the characteristics of images, and they have learned to detect slopes using STI's 2D Fourier transform images. As a result, the performance of the velocity evaluation was significantly improved. Further