A YOLOv7 incorporating the Adan optimizer based corn pests identification method

Abstract

Major pests of corn insects include corn borer, armyworm, bollworm, aphid, and corn leaf mites. Timely and accurate detection of these pests is crucial for effective pests control and scientific decision making. However, existing methods for identification based on traditional machine learning and neural networks are limited by high model training costs and low recognition accuracy. To address these problems, we proposed a YOLOv7 maize pests identification method incorporating the Adan optimizer. First, we selected three major corn pests, corn borer, armyworm and bollworm as research objects. Then, we collected and constructed a corn pests dataset by using data augmentation to address the problem of scarce corn pests data. Second, we chose the YOLOv7 network as the detection model, and we proposed to replace the original optimizer of YOLOv7 with the Adan optimizer for its high computational cost. The Adan optimizer can efficiently sense the surrounding gradient information in advance, allowing the model to escape sharp local minima. Thus, the robustness and accuracy of the model can be improved while significantly reducing the computing power. Finally, we did ablation experiments and compared the experiments with traditional methods and other common object detection networks. Theoretical analysis and experimental result show that the model incorporating with Adan optimizer only requires 1/2-2/3 of the computing power of the original network to obtain performance beyond that of the original network. The mAP@[.5:.95] (mean Average Precision) of the improved network reaches 96.69% and the precision reaches 99.95%. Meanwhile, the mAP@[.5:.95] was improved by 2.79%-11.83% compared to the original YOLOv7 and 41.98%-60.61% compared to other common object detection models. In complex natural scenes, our proposed method is not only time-efficient and has higher recognition accuracy, reaching the level of SOTA.

YOLOv7-Plum: Advancing Plum Fruit Detection in Natural Environments with Deep Learning

“…The input image is passed through the backbone module for feature extraction. YOLOv7 has three detection heads; after feature fusion, the detection heads will pass the feature information to the output layer, which predicts the location and class of the target and generates the corresponding bounding box [51,52]. YOLOv7 is the structure introduced in the YOLO series in 2022, and it offers significant improvements in feature extraction for targets compared to previous models [33].…”

“…The input image is passed through the backbone module for feature extraction. YOLOv7 has three detection heads; after feature fusion, the detection heads will pass the feature information to the output layer, which predicts the location and class of the target and generates the corresponding bounding box [51,52].…”

“…The input image is passed through the backbone module for feature extraction. YOLOv7 has three detection heads; after feature fusion, the detection heads will pass the feature information to the output layer, which predicts the location and class of the target and generates the corresponding bounding box[51,52].Two CBAMs were added between the head and backbone in the YOLOv7 network structure to improve the model's ability to perceive different spaces and different channels, enabling the model to pay more attention to the plum fruit as the focal information in the complex background. Then, the nearest neighbor interpolation used in the up-sampling of the original network was changed to the more effective bilinear interpolation, which resulted in a significant improvement of the image quality during the up-sampling process without a significant increase in the training time of the model.…”