Accurate and rapid detection of tea shoots within the tea canopy is essential for achieving the automatic picking of famous tea. The current detection models suffer from two main issues: low inference speed and difficulty in deployment on movable platforms, which constrain the development of intelligent tea picking equipment. Furthermore, the detection of tea canopy shoots is currently limited to natural daylight conditions, with no reported studies on detecting tea shoots under artificial light during the nighttime. Developing an all-day tea picking platform would significantly improve the efficiency of tea picking. In view of these problems, the research objective was to propose an all-day lightweight detection model for tea canopy shoots (TS-YOLO) based on YOLOv4. Firstly, image datasets of tea canopy shoots sample were collected under low light (6:30–7:30 and 18:30–19:30), medium light (8:00–9:00 and 17:00–18:00), high light (11:00–15:00), and artificial light at night. Then, the feature extraction network of YOLOv4 and the standard convolution of the entire network were replaced with the lightweight neural network MobilenetV3 and the depth-wise separable convolution. Finally, to compensate for the lack of feature extraction ability in the lightweight neural network, a deformable convolutional layer and coordinate attention modules were added to the network. The results showed that the improved model size was 11.78 M, 18.30% of that of YOLOv4, and the detection speed was improved by 11.68 FPS. The detection accuracy, recall, and AP of tea canopy shoots under different light conditions were 85.35%, 78.42%, and 82.12%, respectively, which were 1.08%, 12.52%, and 8.20% higher than MobileNetV3-YOLOv4, respectively. The developed lightweight model could effectively and rapidly detect tea canopy shoots under all-day light conditions, which provides the potential to develop an all-day intelligent tea picking platform.

Plant height is a crucial indicator of crop growth. Rapid measurement of crop height facilitates the implementation and management of planting strategies, ensuring optimal crop production quality and yield. This paper presents a low-cost method for the rapid measurement of multiple lettuce heights, developed using an improved YOLOv8n-seg model and the stacking characteristics of planes in depth images. First, we designed a lightweight instance segmentation model based on YOLOv8n-seg by enhancing the model architecture and reconstructing the channel dimension distribution. This model was trained on a small-sample dataset augmented through random transformations. Secondly, we proposed a method to detect and segment the horizontal plane. This method leverages the stacking characteristics of the plane, as identified in the depth image histogram from an overhead perspective, allowing for the identification of planes parallel to the camera’s imaging plane. Subsequently, we evaluated the distance between each plane and the centers of the lettuce contours to select the cultivation substrate plane as the reference for lettuce bottom height. Finally, the height of multiple lettuce plants was determined by calculating the height difference between the top and bottom of each plant. The experimental results demonstrated that the improved model achieved a 25.56% increase in processing speed, along with a 2.4% enhancement in mean average precision compared to the original YOLOv8n-seg model. The average accuracy of the plant height measurement algorithm reached 94.339% in hydroponics and 91.22% in pot cultivation scenarios, with absolute errors of 7.39 mm and 9.23 mm, similar to the sensor’s depth direction error. With images downsampled by a factor of 1/8, the highest processing speed recorded was 6.99 frames per second (fps), enabling the system to process an average of 174 lettuce targets per second. The experimental results confirmed that the proposed method exhibits promising accuracy, efficiency, and robustness.

To address the problems of traditional methods that rely on destructive sampling, the poor adaptability of fixed equipment, and the susceptibility of single-view angle measurements to occlusions, a non-destructive and portable device for three-dimensional phenotyping and biomass detection in lettuce was developed. Based on the Structure-from-Motion Multi-View Stereo (SFM-MVS) algorithms, a high-precision three-dimensional point cloud model was reconstructed from multi-view RGB image sequences, and 12 phenotypic parameters, such as plant height, crown width, were accurately extracted. Through regression analyses of plant height, crown width, and crown height, and the R² values were 0.98, 0.99, and 0.99, respectively, the RMSE values were 2.26 mm, 1.74 mm, and 1.69 mm, respectively. On this basis, four biomass prediction models were developed using Adaptive Boosting (AdaBoost), Support Vector Regression (SVR), Gradient Boosting Decision Tree (GBDT), and Random Forest Regression (RFR). The results indicated that the RFR model based on the projected convex hull area, point cloud convex hull surface area, and projected convex hull perimeter performed the best, with an R² of 0.90, an RMSE of 2.63 g, and an RMSEn of 9.53%, indicating that the RFR was able to accurately simulate lettuce biomass. This research achieves three-dimensional reconstruction and accurate biomass prediction of facility lettuce, and provides a portable and lightweight solution for facility crop growth detection.