Guo Li

With the rapid development of Internet of Things (IoT) technology, smart home control has become an indispensable part of modern life. This study designs a smart home control system based on the STM32 microcontroller, combined with Tencent CloudBase and WiFi communication technology, to achieve remote control of home devices and real-time monitoring of home environments. The system uses the MQTT protocol to transmit data and send control commands. At the same time, a WeChat mini-program is developed as the client for controlling devices. The feasibility of the system has been verified through testing.

When monitoring crop growth using top-down images of the plant canopies, leaves in agricultural fields appear very dense and significantly overlap each other. Moreover, the image can be affected by external conditions such as background environment and light intensity, impacting the effectiveness of image segmentation. To address the challenge of segmenting dense and overlapping plant leaves under natural lighting conditions, this study employed a Bilayer Convolutional Network (BCNet) method for accurate leaf segmentation across various lighting environments. The major contributions of this study are as follows: (1) Utilized Fully Convolutional Object Detection (FCOS) for plant leaf detection, incorporating ResNet-50 with the Convolutional Block Attention Module (CBAM) and Feature Pyramid Network (FPN) to enhance Region of Interest (RoI) feature extraction from canopy top-view images. (2) Extracted the sub-region of the RoI based on the position of the detection box, using this region as input for the BCNet, ensuring precise segmentation. (3) Utilized instance segmentation of canopy top-view images using BCNet, improving segmentation accuracy. (4) Applied the Varifocal Loss Function to improve the classification loss function in FCOS, leading to better performance metrics. The experimental results on cucumber canopy top-view images captured in glass greenhouse and plastic greenhouse environments show that our method is highly effective. For cucumber leaves at different growth stages and under various lighting conditions, the Precision, Recall and Average Precision (AP) metrics for object recognition are 97%, 94% and 96.57%, respectively. For instance segmentation, the Precision, Recall and Average Precision (AP) metrics are 87%, 83% and 84.71%, respectively. Our algorithm outperforms commonly used deep learning algorithms such as Faster R-CNN, Mask R-CNN, YOLOv4 and PANet, showcasing its superior capability in complex agricultural settings. The results of this study demonstrate the potential of our method for accurate recognition and segmentation of highly overlapping leaves in diverse agricultural environments, significantly contributing to the application of deep learning algorithms in smart agriculture.

Accurate detection and reconstruction of branches aid the accuracy of harvesting robots and extraction of plant phenotypic information. However, the complex orchard background and twisting growing branches of vine fruit trees make this challenging. To solve these problems, this study adopted a Mask Region-based convolutional neural network (Mask R-CNN) architecture incorporating deformable convolution to segment branches in complex backgrounds. Based on the growth posture, a branch reconstruction algorithm with bidirectional sector search was proposed to adaptively reconstruct the segmented branches obtained by an improved model. The average precision, average recall, and F1 scores of the improved Mask R-CNN model for passion fruit branch detection were found to be 64.30%, 76.51%, and 69.88%, respectively, and the average running time on the test dataset was 0.75 s per image, which is better than the compared model. We randomly selected 40 images from the test dataset to evaluate the branch reconstruction. The branch reconstruction accuracy, average error, average relative error of reconstructed diameter, and mean intersection-over-union (mIoU) were 88.83%, 1.98 px, 7.98, and 83.44%, respectively. The average reconstruction time for a single image was 0.38 s. This would promise the proposed method to detect and reconstruct plant branches under complex orchard backgrounds.

The extraction and analysis of plant phenotypic characteristics are critical issues for many precision agriculture applications. An improved YOLOv5 model was proposed in this study for accurate node detection and internode length estimation of crops by using an end-to-end approach. In this improved YOLOv5, a feature extraction module was added in front of each detection head, and the bounding box loss function used in the original network of YOLOv5 was replaced by the SIoU bounding box loss function. The results of the experiments on three different crops (chili, eggplant, and tomato) showed that the improved YOLOv5 reached 90.5% AP (average precision) and the average detection time was 0.019 s per image. The average error of the internode length estimation was 41.3 pixels, and the relative error was 7.36%. Compared with the original YOLOv5, the improved YOLOv5 had an average error reduction of 5.84 pixels and a relative error reduction of 1.61%.

The accuracy detection of individual citrus fruits in a citrus orchard environments is one of the key steps in realizing precision agriculture applications such as yield estimation, fruit thinning, and mechanical harvesting. This study proposes an improved object detection YOLOv5 model to achieve accurate the identification and counting of citrus fruits in an orchard environment. First, the latest visual attention mechanism coordinated attention module (CA) was inserted into an improved backbone network to focus on fruit-dense regions to recognize small target fruits. Second, an efficient two-way cross-scale connection and weighted feature fusion BiFPN in the neck network were used to replace the PANet multiscale feature fusion network, giving effective feature corresponding weights to fully fuse the high-level and bottom-level features. Finally, the varifocal loss function was used to calculate the model loss for better model training results. The results of the experiments on four varieties of citrus trees showed that our improved model proposed to this study could effectively identify dense small citrus fruits. Specifically, the recognized AP (average precision) reached 98.4%, and the average recognition time was 0.019 s per image. Compared with the original YOLOv5 (including deferent variants of n, s, m, l, and x), the increase in the average accuracy precision of the improved YOLOv5 ranged from 7.5% to 0.8% while maintaining similar average inference time. Four different citrus varieties were also tested to evaluate the generalization performance of the improved model. The method can be further used as a part in a vision system to provide technical support for the real-time and accurate detection of multiple fruit targets during mechanical picking in citrus orchards.

The leaf is the organ that is crucial for photosynthesis and the production of nutrients in plants; as such, the number of leaves is one of the key indicators with which to describe the development and growth of a canopy. The irregular shape and distribution of the blades, as well as the effect of natural light, make the segmentation and detection process of the blades difficult. The inaccurate acquisition of plant phenotypic parameters may affect the subsequent judgment of crop growth status and crop yield. To address the challenge in counting dense and overlapped plant leaves under natural environments, we proposed an improved deep-learning-based object detection algorithm by merging a space-to-depth module, a Convolutional Block Attention Module (CBAM) and Atrous Spatial Pyramid Pooling (ASPP) into the network, and applying the smooth_L1 function to improve the loss function of object prediction. We evaluated our method on images of five different plant species collected under indoor and outdoor environments. The experimental results demonstrated that our algorithm which counts dense leaves improved average detection accuracy of 85% to 96%. Our algorithm also showed better performance in both detection accuracy and time consumption compared to other state-of-the-art object detection algorithms.