Automatic Estimation of Apple Orchard Blooming Levels Using the Improved YOLOv5

Abstract

The estimation of orchard blooming levels and the determination of peak blooming dates are very important because they determine the timing of orchard flower thinning and are essential for apple yield and quality. In this paper, we propose an orchard blooming level estimation method for global-level and block-level blooming level estimation of orchards. The method consists of a deep learning-based apple flower detector, a blooming level estimator, and a peak blooming day finding estimator. The YOLOv5s model is used as the apple flower detector, which is improved by adding a coordinate attention layer and a small object detection layer and by replacing the model neck with a bidirectional feature pyramid network (BiFPN) structure to improve the performance of the apple flower detector at different growth stages. The robustness of the apple flower detector under different light conditions and the generalization across years was tested using apple flower data collected in 2021–2022. The trained apple flower detector achieved a mean average precision of 77.5%. The blooming level estimator estimated the orchard blooming level based on the proportion of flowers detected at different growth stages. Statistical results show that the blooming level estimator follows the trend of orchard blooming levels. The peak blooming day finding estimator successfully positioned the peak blooming time and provided information for the flower thinning timing decision. The method described in this paper is able to provide orchardists with accurate information on apple flower growth status and is highly automated.

An improved YOLOv5s model using feature concatenation with attention mechanism for real-time fruit detection and counting

“…(2021) for apples, Qiao et al. (2022) for red jujube, Chen Z. et al. (2022) for automatic estimation of apple, and Fu et al.…”

YOLO-plum: A high precision and real-time improved algorithm for plum recognition

“…The biggest advantage of YOLO is that it is extremely fast, which makes it a great advantage in real-time detection tasks. YOLOv5 algorithm [32][33][34] makes some improvements on…”

Improved Yolov8-based Approach for Fire Detection

“…These modules serve as feature extraction functions. The Conv adopts the Silu [15] activation function, while the C2f model incorporates feature fusion and residual connections, and the SPPF model utilizes a spatial pyramid pooling structure, which remains the widely adopted PAN-FPN [16]. The downsampling is executed before the upsampling process, and the integration of upsampling and downsampling through cross-layer fusion leads to the formation of three distinct detection heads.…”