Yolov5s-CA: An Improved Yolov5 Based on the Attention Mechanism for Mummy Berry Disease Detection

Abstract

Early detection and accurately rating the level of plant diseases plays an important role in protecting crop quality and yield. The traditional method of mummy berry disease (causal agent: Monilinia vaccinii-corymbosi) identification is mainly based on field surveys by crop protection experts and experienced blueberry growers. Deep learning models could be a more effective approach, but their performance is highly dependent on the volume and quality of labeled data used for training so that the variance in visual symptoms can be incorporated into a model. However, the available dataset for mummy berry disease detection does not contain enough images collected and labeled from a real-field environment essential for making highly accurate models. Complex visual characteristics of lesions due to overlapping and occlusion of plant parts also pose a big challenge to the accurate estimation of disease severity. This may become a bigger issue when spatial variation is introduced by using sampling images derived from different angles and distances. In this paper, we first present the “cut-and-paste” method for synthetically augmenting the available dataset by generating additional annotated training images. Then, a deep learning-based object recognition model Yolov5s-CA was used, which integrates the Coordinated Attention (CA) module on the Yolov5s backbone to effectively discriminate useful features by capturing channel and location information. Finally, the loss function GIoU_loss was replaced by CIoU_loss to improve the bounding box regression and localization performance of the network model. The original Yolov5s and the improved Yolov5s-CA network models were trained on real, synthetic, and combined mixed datasets. The experimental results not only showed that the performance of Yolov5s-CA network model trained on a mixed dataset outperforms the baseline model trained with only real field images, but also demonstrated that the improved model can solve the practical problem of diseased plant part detection in various spatial scales with possible overlapping and occlusion by an overall precision of 96.30%. Therefore, our model is a useful tool for the estimation of mummy berry disease severity in a real field environment.

An improved YOLOv5 for identifying pigs postures

“…This method can avoid the loss of feature information during downsampling, decrease the load of calculations, and enhance the speed of analysis of the algorithm. The SPP module, also known as spatial pyramid pooling, can convert input feature maps of different specifications into uniform size feature vectors;Neck uses the Feature Pyramid Networks(FPN)+Path Aggregation Network(PAN) feature pyramid structure [13,14], which combines feature information both from above to below and from below to above, so that features at multiple scales contain rich semantic information [15]; Head is a prediction network with prediction boxes of 20 20  , 40 40  , 80 80  and output sizes for predicting large, medium and small objects.…”

Medical instrument detection with synthetically generated data

“…The first method is used in many publications as it is a simple method for artificially expanding a small existing data set, with the aim to get better training results. Obsie, E. et al 7 use this method, for example, to identify plant diseases more robustly. An application of the first approach in a medical context can be found in the article by Badilla-Solorzano, J. et al 8 .…”

Detecting and Mapping Individual Fruit Trees in Complex Natural Environments via UAV Remote Sensing and Optimized YOLOv5

“…It can fuse both channel and spatial information to enhance the localization accuracy of object detection. Recently, the CA-based YOLOv5s model was used for mummy berry disease detection, which showed that the overall performance of the improved YOLOv5s-CA network model was superior to that of the original YOLOv5s model [56]. b) Split Attention (SA) SA, as a simple and unified computation block (Fig.…”