Rapid Target Detection of Fruit Trees Using UAV Imaging and Improved Light YOLOv4 Algorithm

Abstract

The detection and counting of fruit tree canopies are important for orchard management, yield estimation, and phenotypic analysis. Previous research has shown that most fruit tree canopy detection methods are based on the use of traditional computer vision algorithms or machine learning methods to extract shallow features such as color and contour, with good results. However, due to the lack of robustness of these features, most methods are hardly adequate for the recognition and counting of fruit tree canopies in natural scenes. Other studies have shown that deep learning methods can be used to perform canopy detection. However, the adhesion and occlusion of fruit tree canopies, as well as background noise, limit the accuracy of detection. Therefore, to improve the accuracy of fruit tree canopy recognition and counting in real-world scenarios, an improved YOLOv4 (you only look once v4) is proposed, using a dataset produced from fruit tree canopy UAV imagery, combined with the Mobilenetv3 network, which can lighten the model and increase the detection speed, combined with the CBAM (convolutional block attention module), which can increase the feature extraction capability of the network, and combined with ASFF (adaptively spatial feature fusion), which enhances the multi-scale feature fusion capability of the network. In addition, the K-means algorithm and linear scale scaling are used to optimize the generation of pre-selected boxes, and the learning strategy of cosine annealing is combined to train the model, thus accelerating the training speed of the model and improving the detection accuracy. The results show that the improved YOLOv4 model can effectively overcome the noise in an orchard environment and achieve fast and accurate recognition and counting of fruit tree crowns while lightweight the model. The mAP reached 98.21%, FPS reached 96.25 and F1-score reached 93.60% for canopy detection, with a significant reduction in model size; the average overall accuracy (AOA) reached 96.73% for counting. In conclusion, the YOLOv4-Mobilenetv3-CBAM-ASFF-P model meets the practical requirements of orchard fruit tree canopy detection and counting in this study, providing optional technical support for the digitalization, refinement, and smart development of smart orchards.

Improved A-Star Search Algorithm for Probabilistic Air Pollution Detection Using UAVs

“…Recently, various machine and deep learning methods have been used to increase the probability of target recognition. Research on probabilistic searches includes [ 20 , 21 , 22 , 23 , 24 , 25 , 26 , 27 ], and search methods using artificial intelligence include [ 28 , 29 , 30 , 31 , 32 ]. Symington et al [ 20 ] conducted an early study on stochastic searches.…”

“…Luo et al [ 30 ] proposed an improved YOLO v5 algorithm using the k-means++ algorithm. Zhu et al [ 31 ] focused on improving the recognition accuracy of fruit tree canopies in orchards captured by UAVs and proposed an improved YOLO v4. Wang et al [ 32 ] proposed an online distributed algorithm for tracking and searching for object detection and search trajectory planning for the security surveillance of UAVs with relative mobility and scalability.…”

Insulator and Its Defect Detection Based on Lightweight YOLOv5s

“…BIFPN simplifies the PA-FPN structure and effectively prevents the loss of small targets by fusing large-scale feature mappings that contain more information about small targets [9] .…”

Intelligent monitoring and analysis of physical education based on IoT and deep learning in the context of big data

“…This enhances the semantic information of the shallow feature layer and elevates its feature extraction ability. Bi-FPN, an improved version of FPN, optimizes and enhances the multi-scale feature fusion (Zhu et al 2023). Bi-FPN performs the fusion of multi-scale feature layers twice, unifying the feature resolution scale via up-sampling and downsampling.…”