Position and morphology detection of mixed particles based on IPI and YOLOv7

Abstract

The acquisition of microphysical information, such as water or ice content in cloud fields, plays an important role in artificial precipitation and weather forecasting. Here, the position and morphology detection of mixed particles is realized by combining interferometric particle imaging (IPI) with YOLOv7. The simulative and experimental interferometric defocus images of mixed particles are obtained from the optical transfer matrix theory and the IPI system, respectively. The new network with stronger feature extraction capability based on YOLOv7 is proposed and named “RFBCA-YOLO,” which adds the coordinate attention (CA) module and employs the receptive field block (RFB) module. The position accuracy of RFBCA-YOLO is comparable to that of the erosion match algorithm, and the miss and false detections are reduced. Compared with the original YOLOv7 network in morphology detection, RFBCA-YOLO improves the mean average precision (mAP) and mAP0.5:0.95 by 2.0% and 1.3%, respectively, and the F1 score by 1.6%. The floating-point operations per second (FLOPs) and parameters are reduced by 2.4% and 8.7%, respectively.