| Summary: | In response to the shortcomings of traditional pest detection methods, such as inadequate accuracy and slow detection speeds, a lightweight forestry pest image recognition model based on an improved YOLOv8 architecture is proposed. Initially, given the limited availability of real deep forest pest image data in the wild, data augmentation techniques, including random rotation, translation, and Mosaic, are employed to expand and enhance the dataset. Subsequently, the traditional Conv (convolution) layers in the neck module of YOLOv8 are replaced with lightweight GSConv, and the Slim Neck design paradigm is utilized for reconstruction to reduce computational costs while preserving model accuracy. Furthermore, the CBAM attention mechanism is introduced into the backbone network of YOLOv8 to enhance the feature extraction of crucial information, thereby improving detection accuracy. Finally, WIoU is employed as a replacement for the traditional CIOU to enhance the overall performance of the detector. The experimental results demonstrate that the improved model exhibits a significant advantage in the field of forestry pest detection, achieving precision and recall rates of 98.9% and 97.6%, respectively. This surpasses the performance of the current mainstream network models.
|
|---|