Pollen particle detection method and device

Abstract

The invention provides a pollen particle detection method and device. The method comprises the steps: acquiring feature maps corresponding to a plurality of image regions in a pollen image to be detected and confidence corresponding to each image region; performing similarity comparison on the feature maps, and determining a maximum feature similarity value corresponding to any target feature map; performing weighting processing on the maximum feature similarity value corresponding to the target feature map to obtain a weighted maximum feature similarity value; and on the basis of the weighted maximum feature similarity value corresponding to the target feature map and the confidence coefficient of the image region corresponding to the target feature map, performing confidence coefficient updating on the image region corresponding to the target feature map, and determining whether the corresponding image region is pollen particles or not on the basis of the updated confidence coefficient. According to the pollen particle detection method provided by the invention, the extracted features can be effectively utilized to reduce the omission ratio of the pollen particles, and the detection accuracy is improved.

Description

technical field [0001] The invention relates to the technical field of computer vision, in particular to a method and device for detecting pollen particles. Background technique [0002] Pollen detection is to detect the position of pollen in a given picture, which belongs to the field of target detection. In the prior art, the direct object detection method based on the idea of ​​regression is to classify and regress bounding boxes directly on the feature map. There are mainly SSD (Single Shot MultiBox Detector) target detection model and YOLO (You Only Look Once) target detection model series. The accuracy of this kind of one-stage detection model needs to be improved. [0003] On the one hand, pollen collection samples are substances in the air in the natural environment, often mixed with pollen, dust, insect eggs, sand grains, etc., so the collected samples contain more impurities. Moreover, the pollen grains are irregular in shape and easy to stick together, making p...

AI Technical Summary

Problems solved by technology

[0005] The invention provides a method and device for detecting pollen particles, which are used to solve the defects of low detection accuracy caused by missed detection and false detection of pollen particles in the prior art, and improve the accuracy of pollen detection

Images