A key challenge for automated orchard management robots is the rapid and accurate identification of crop growth and maturity conditions for subsequent operations, such as automatic pollination, fertilization, and picking. In particular, strawberries have a short ripening period and the fruits are heavily overlapped and shaded by each other, which is time-consuming and inefficient under traditional detection methods. Therefore, we designed and developed a strawberry growth detection algorithm, SDNet (Strawberry Detect Net). The algorithm is based on the YOLOX model and replaces the original CSP block in the backbone network with a self-designed feature extraction module C3HB block to improve the spatial interaction capability and monitoring accuracy of the detection algorithm; Then, the normalized attention module (NAM) is embedded in the neck to improve the detection accuracy and attention weight of small target fruits; and we use the latest SIOU objective loss function to improve the prediction accuracy of the detection model, which finally achieves the monitoring of strawberry fruits under five growth states. The experimental results show that the mAP, precision, and recall of SDNet are 94.26%, 93.15%, and 90.72%, respectively, and the monitoring speed is 30.5 ms. It is 4.08%, 3.64 and 2.04% higher than the precision, accuracy, and recall of YOLOX, respectively, and there is no significant change in the model size. The research results can effectively solve the problem of low accuracy of strawberry fruit growth state monitoring under complex environments, and provide important technical reference for realizing unmanned farm and precision agriculture.INDEX TERMS Fruit detection,Object detection,Real-time counting,Digital agriculture.

Crop diseases have an important impact on the safe production of food. Therefore, the automated identification of pre-crop diseases is very important for farmers to increase production and income. In this paper, a tomato leaf disease identification method based on the optimized MobileNetV2 model is proposed. A dataset of 20,400 tomato disease images was created based on tomato disease images taken from the greenhouse and obtained from the PlantVillage database. The optimized MobileNetV2 model was trained with the dataset to obtain a classification model for tomato leaf diseases. The average recognition accuracy of the model is 98.3% and the recall rate is 94.9%, which is 1.2% and 3.9% higher than the original model, respectively, after experimental validation. The average prediction speed of the model for a single image is about 76 ms, which is 2.94% better than the original model. To verify the performance of the optimized MobileNetV2 model, it was compared with the Xception, Inception, and VGG16 feature extraction network models using migration learning, respectively. The experimental results show that the average recognition accuracy of the model is 0.4 to 2.4 percentage points higher than that of the Xception, Inception, and VGG16 models. It can provide technical support for the identification of tomato diseases, and is also important for plant growth monitoring under precision agriculture.

Existing target detection models are large and have multiple network parameters, which can severely slow down the detection speed when deployed on small, low-cost GPU-free Industrial Personal Computers (IPC). As a result, this study proposes a lightweight real-time tomato detection and point-picking integrated network model based on YOLOv5 (TDPPL-Net). Firstly, the algorithm replaces the YOLOv5 backbone with a four-group lightweight downsampling model consisting of Ghost Conv and Ghost Bottleneck to reduce the model size, while adding the attention mechanism SimAM module to improve detection accuracy after each scale's feature map. Secondly, the Spatial Pyramid Pooling-Fast(SPPF) network structure is used and the convolutional layers in the (Feature Pyramid Network and Path Aggregation Network)FPN+PAN structure are replaced with a depth-separable convolution to reduce the computational effort. Finally, the center of the bounding box is used as the picking point, and the corresponding depth information is obtained in combination with the Intel RealSense D435 camera, which is converted into 3D coordinates under the robot arm coordinate system after hand-eye calibration. The experimental results show that TDPPL-Net reduces the number of parameters by 59.84% compared with the original YOLOv5, the model volume is only 40% of the original, the mAP is 93.36, and the real-time detection speed on the IPC without GPU acceleration is 31.41 FPS, which is 170.31% higher than YOLOv5. The TDPPL-Net increases detection speed on low-performance equipment without compromising detection accuracy. It can detect and locate tomato picking points in real-time in the complex natural environment, which can meet the working requirements of harvesting robots.INDEX TERMS Lightweight, Real-time tomato detection, Location of picking points, Harvesting robot.