Efficient Intelligent detection is a key technology in automatic harvesting robots. However, citrus detection is still a challenging task because of varying illumination, random occlusion and colour similarity between fruits and leaves in natural conditions. In this paper, a detection method called Lemon‐YOLO (L‐YOLO) is proposed to improve the accuracy and real‐time performance of lemon detection in the natural environment. The SE_ResGNet34 network is designed to replace DarkNet53 network in YOLOv3 algorithm as a new backbone of feature extraction. It can enhance the propagation of features, and needs less parameter, which helps to achieve higher accuracy and speed. Moreover, the SE_ResNet module is added to the detection block, to improve the quality of representations produced from the network by strengthening the convolutional features of channels. The experimental results show that the proposed L‐YOLO has an average accuracy(AP) of 96.28% and a detection speed of 106 frames per second (FPS) on the lemon test set, which is 5.68% and 28 FPS higher than the YOLOv3, respectively. The results indicate that the L‐YOLO method has superior detection performance. It can recognize and locate lemons in the natural environment more efficiently, providing technical support for the machine's picking lemon and other fruits.

Dragon fruit (Hylocereus undatus) is a tropical and subtropical fruit that undergoes multiple ripening cycles throughout the year. Accurate monitoring of the flower and fruit quantities at various stages is crucial for growers to estimate yields, plan orders, and implement effective management strategies. However, traditional manual counting methods are labor-intensive and inefficient. Deep learning techniques have proven effective for object recognition tasks but limited research has been conducted on dragon fruit due to its unique stem morphology and the coexistence of flowers and fruits. Additionally, the challenge lies in developing a lightweight recognition and tracking model that can be seamlessly integrated into mobile platforms, enabling on-site quantity counting. In this study, a video stream inspection method was proposed to classify and count dragon fruit flowers, immature fruits (green fruits), and mature fruits (red fruits) in a dragon fruit plantation. The approach involves three key steps: (1) utilizing the YOLOv5 network for the identification of different dragon fruit categories, (2) employing the improved ByteTrack object tracking algorithm to assign unique IDs to each target and track their movement, and (3) defining a region of interest area for precise classification and counting of dragon fruit across categories. Experimental results demonstrate recognition accuracies of 94.1%, 94.8%, and 96.1% for dragon fruit flowers, green fruits, and red fruits, respectively, with an overall average recognition accuracy of 95.0%. Furthermore, the counting accuracy for each category is measured at 97.68%, 93.97%, and 91.89%, respectively. The proposed method achieves a counting speed of 56 frames per second on a 1080ti GPU. The findings establish the efficacy and practicality of this method for accurate counting of dragon fruit or other fruit varieties.

A design method of neural network adaptive interval observer for the continuous‐time unknown nonlinear system is proposed. The bounds of unknown nonlinear functions are described by the state and the input, so that the bounds of the nonlinear function vector are unmeasurable. Therefore, this method can be used to observe systems with higher degree of nonlinearity and any priori knowledge about systems. In this work, the hyper basis function neural network (HBFNN) is presented to estimate the boundary (including lower and upper bounds) of the unknown nonlinear function vector. Furthermore, the non‐negativity and stability of the error dynamic system are given, and the convergence and non‐negativity are also guaranteed. Compared with the traditional interval observer, the efficiency of the proposed approach is verified through a numerical simulation example.

Sugar and moisture contents in sugarcane stalks serve as critical quality indicators that directly determine the processing value and sugar production efficiency. However, conventional detection methods are limited by destructive sampling, time-consuming procedures, and complex operations, making them unable to meet the demands of rapid on-site detection and real-time quality grading. In this study, visible-near-infrared transmission spectroscopy combined with an optimized wavelength selection strategy was applied to achieve non-destructive quantitative analysis of sugar and moisture contents in intact sugarcane stalks. A total of 223 sugarcane samples were prepared, and their transmission spectra were collected in the wavelength range of 350–2500 nm. Comparative experiments were conducted to determine the optimal spectral range (670–950 nm), measurement angle (0°) and preprocessing method (three-step preprocessing method: GF + SNV + ZN). To overcome the drawback of traditional uninformative variable elimination (UVE) that neglects prior contribution information of spectral variables, an improved UVE algorithm based on variable regression coefficients (VRC-UVE) was proposed, which introduces regression coefficient weights into the variable stability evaluation index. partial least squares quantitative prediction models were established based on full spectra and characteristic wavelengths screened by different variable selection algorithms. The results showed that the VRC-UVE method only retained 59 characteristic wavelengths for sugar content and 57 characteristic wavelengths for moisture content, respectively. The optimized models achieved prediction correlation coefficients ( r _p ) of 0.9554 and 0.9504, with root mean square errors of prediction of 1.1841 °Brix and 0.0121%, respectively. In comparison with the traditional UVE and competitive adaptive reweighted sampling algorithms, the proposed VRC-UVE method presents comprehensive superiorities in both model simplicity and prediction accuracy. This study provides a reliable technical framework for the non-destructive field quality evaluation of sugarcane, supporting the application of intelligent management in precision agriculture and the sugar processing industry.