Apple flower phenotype detection method based on YOLO-FL and application of intelligent flower thinning robot

In intelligent flower thinning robot applications, accurate and efficient apple flower detection is the key to realizing automated fruit tree thinning operations. However, complex orchard environments and diverse flower characteristics pose many challenges to apple blossom detection, such as shading, light variations, flower densities, and so on. To address these challenges, this study proposes an improved model based on the YOLO target detection framework which is named the YOLO-FL apple flower detection model. The model enhances the feature extraction capability by optimizing the Backbone part with EC3DFM structure, while introducing MFEM structure in the Neck part to improve the feature fusion effect. In addition, the ABRLoss loss function is used to optimize the prediction results of the prediction frame, and it also adds the SimAM attention mechanism to the middle two detection heads in the Neck part, which further improves the detection performance of the model. The experimental results respectively show that YOLO-FL achieves 74.63%, 73.82%, and 79.97% accuracy, recall, and mean average precision on the test set, which shows significant improvement over the benchmark model. Meanwhile, the model size was only 4693 kB, demonstrating high efficiency and storage advantages. After deploying the YOLO-FL model to the intelligent flower thinning robot, the frame rate of the test image was 40.7 FPS, the average missed detection rate was 7.26%, the false detection rate was 6.89%, and the model was able to efficiently complete the apple flower detection in the complex orchard environment. This study provides an effective solution and technical support for the application of image recognition technology in intelligent flower thinning robots.