In the context of the problem of water pollution, the movement characteristics and patterns of fish under normal water quality and abnormal water quality are clearly different. This paper proposes a biological water quality monitoring method combining three-dimensional motion trajectory synthesis and integrated learning. The videos of the fish movement are captured by two cameras, and the Kuhn-Munkres (KM) algorithm is used to match the target points of the fish body. The Kalman filter is used to update the current state and find the optimal tracking position as the tracking result. The Kernelized Correlation Filters (KCF) algorithm compensates the targets that are lost in the tracking process and collision or occlusion in the movement process, reducing the errors caused by illumination, occlusion and water surface fluctuation effectively. This algorithm can directly obtain the target motion trajectory, avoiding the re-extraction from the centroid point in the image sequence, which greatly improves the efficiency. In order to avoid the one-sidedness of the two-dimensional trajectory, the experiment combines the pixel coordinates of different perspectives into three-dimensional trajectory pixel coordinates, so as to provide a more authentic fish swimming trajectory. We then select a representative positive and negative sample data set; the number of data sets should have symmetry. The base classifier capable of identifying different water quality is obtained by training. Finally, support vector machine(SVM), eXtreme Gradient Boosting (XGBoost) and pointnet based classifiers are combined into strong classifiers through integrated learning. The experimental results show that the integrated learning model can reflect the water quality effectively and accurately under the three-dimensional trajectory pixel coordinates of fish, and the recognition rate of water quality is above 95%.

Aiming at the problem of integrated environmental monitoring of water quality pollution, a method of water quality anomaly monitoring using Kalman filter and Convolution Neural Network(CNN) is proposed. In this method, the fish is segmented by Mask R-CNN image segmentation method, the positive and negative sample data sets of the backbone and background images of the fish are made, and the model is obtained by using convolution neural network training data set. In the process of tracking, the RANSAC algorithm is used to screen the SIFT feature matching and Kalman filter is used to track the fish and draw the moving track in real time. The motion trajectory is saved every 3 seconds, a total of 150000 samples of normal and abnormal water quality are obtained. The experimental results show that the recognition rate of water quality anomaly based on Kalman filter and Convolution Neural Network is 98.5%, this method is superior to traditional water quality identification methods.