The key to precise weeding in the field lies in the efficient detection of weeds. There are no studies on weed detection in potato fields. In view of the difficulties brought by the cross-growth of potatoes and weeds to the detection of weeds, the existing detection methods cannot meet the requirements of detection speed and detection accuracy at the same time. This study proposes an improved YOLOv4 model for weed detection in potato fields. The proposed algorithm replaces the backbone network CSPDarknet53 in the YOLOv4 network structure with the lightweight MobileNetV3 network and introduces Depthwise separable convolutions instead of partial traditional convolutions in the Path Aggregation Network (PANet), which reduces the computational cost of the model and speeds up its detection. In order to improve the detection accuracy, the convolutional block attention module (CBAM) is fused into the PANet structure, and the CBAM will process the input feature map with a channel attention mechanism (CAM) and spatial attention mechanism (SAM), respectively, which can enhance the extraction of useful feature information. The K-means++ clustering algorithm is used instead of the K-means clustering algorithm to update the anchor box information of the model so that the anchor boxes are more suitable for the datasets in this study. Various image processing methods such as CLAHE, MSR, SSR, and gamma are used to increase the robustness of the model, which eliminates the problem of overfitting. CIoU is used as the loss function, and the cosine annealing decay method is used to adjust the learning rate to make the model converge faster. Based on the above-improved methods, we propose the MC-YOLOv4 model. The mAP value of the MC-YOLOv4 model in weed detection in the potato field was 98.52%, which was 3.2%, 4.48%, 2.32%, 0.06%, and 19.86% higher than YOLOv4, YOLOv4-tiny, Faster R-CNN, YOLOv5 l, and SSD(MobilenetV2), respectively, and the average detection time of a single image was 12.49ms. The results show that the optimized method proposed in this paper outperforms other commonly used target detection models in terms of model footprint, detection time consumption, and detection accuracy. This paper can provide a feasible real-time weed identification method for the system of precise weeding in potato fields with limited hardware resources. This model also provides a reference for the efficient detection of weeds in other crop fields and provides theoretical and technical support for the automatic control of weeds.

To guide grape picking robots to recognize and classify the grapes with different maturity quickly and accurately in the complex environment of the orchard, and to obtain the spatial position information of the grape clusters, an algorithm of grape maturity detection and visual pre-positioning based on improved YOLOv4 is proposed in this study. The detection algorithm uses Mobilenetv3 as the backbone feature extraction network, uses deep separable convolution instead of ordinary convolution, and uses the h-swish function instead of the swish function to reduce the number of model parameters and improve the detection speed of the model. At the same time, the SENet attention mechanism is added to the model to improve the detection accuracy, and finally the SM-YOLOv4 algorithm based on improved YOLOv4 is constructed. The experimental results of maturity detection showed that the overall average accuracy of the trained SM-YOLOv4 target detection algorithm under the verification set reached 93.52%, and the average detection time was 10.82 ms. Obtaining the spatial position of grape clusters is a grape cluster pre-positioning method based on binocular stereo vision. In the pre-positioning experiment, the maximum error was 32 mm, the mean error was 27 mm, and the mean error ratio was 3.89%. Compared with YOLOv5, YOLOv4-Tiny, Faster_R-CNN, and other target detection algorithms, which have greater advantages in accuracy and speed, have good robustness and real-time performance in the actual orchard complex environment, and can simultaneously meet the requirements of grape fruit maturity recognition accuracy and detection speed, as well as the visual pre-positioning requirements of grape picking robots in the orchard complex environment. It can reliably indicate the growth stage of grapes, so as to complete the picking of grapes at the best time, and it can guide the robot to move to the picking position, which is a prerequisite for the precise picking of grapes in the complex environment of the orchard.

As the end execution tool of agricultural robots, the manipulator directly determines whether the grasping task can be successfully completed. The human hand can adapt to various objects and achieve stable grasping, which is the highest goal for manipulator design and development. Thus, this study combines a multi-sensor fusion tactile glove to simulate manual grasping, explores the mechanism and characteristics of the human hand, and formulates rational grasping plans. According to the shape and size of fruits and vegetables, the grasping gesture library is summarized to facilitate the matching of optimal grasping gestures. By analyzing inter-finger curvature correlations and inter-joint pressure correlations, we investigated the synergistic motion characteristics of the human hand. In addition, the force data were processed by the wavelet transform algorithms and then the thresholds for sliding detection were set to ensure robust grasping. The acceleration law under the interaction with the external environment during grasping was also discussed, including stable movement, accidental collision, and placement of the target position. Finally, according to the analysis and summary of the manual gripping mechanism, the corresponding pre-gripping planning was designed to provide theoretical guidance and ideas for the gripping of robots.

Uninformative biological variability elimination methods were studied in the near-infrared calibration model for predicting the soluble solids content of apples. Four different preprocessing methods, namely, Savitzky-Golay smoothing, multiplicative scatter correction, standard normal variate, and mean normalization, as well as their combinations were conducted on raw Fourier transform near-infrared spectra to eliminate the uninformative biological variability. Subsequently, robust calibration models were established by using partial least squares regression analysis and wavelength selection algorithms. Results indicated that the partial least squares calibration models with characteristic variables selected by CARS method coupled with preprocessing of Savitzky-Golay smoothing and multiplicative scatter correction had a considerable potential for predicting apple soluble solids content regardless of the biological variability.

The relative position of the orchard robot to the rows of fruit trees is an important parameter for achieving autonomous navigation. The current methods for estimating the position parameters between rows of orchard robots obtain low parameter accuracy. To address this problem, this paper proposes a machine vision-based method for detecting the relative position of orchard robots and fruit tree rows. First, the fruit tree trunk is identified based on the improved YOLOv4 model; second, the camera coordinates of the tree trunk are calculated using the principle of binocular camera triangulation, and the ground projection coordinates of the tree trunk are obtained through coordinate conversion; finally, the midpoints of the projection coordinates of different sides are combined, the navigation path is obtained by linear fitting with the least squares method, and the position parameters of the orchard robot are obtained through calculation. The experimental results show that the average accuracy and average recall rate of the improved YOLOv4 model for fruit tree trunk detection are 5.92% and 7.91% higher, respectively, than those of the original YOLOv4 model. The average errors of heading angle and lateral deviation estimates obtained based on the method in this paper are 0.57° and 0.02 m. The method can accurately calculate heading angle and lateral deviation values at different positions between rows and provide a reference for the autonomous visual navigation of orchard robots.

Significant research has been carried out on the applications of imaging and spectroscopy technologies for a variety of foods and agricultural products, and the technical fundamentals and their feasibilities have also been widely demonstrated in the past decade. Imaging technologies, including computer vision, Raman, X-ray, magnetic resonance (MR), fluorescence imaging, spectroscopy technology, as well as spectral imaging technologies, including hyperspectral or multi-spectral imaging, have found their applications in non-destructive tea quality assessment. Tea quality can be assessed by considering their external qualities (color, texture, shape, and defect), internal qualities (contents of polyphenols, amino acids, caffeine, theaflavin, etc.), and safety. In recent years, numerous studies have been published to advance non-destructive methods for assessing tea quality using imaging and spectroscopy technologies. This review aims to give a thorough overview of imaging and spectroscopy technologies, data processing and analyzing methods, as well as their applications in tea quality non-destructive assessment. The challenges and directions of tea quality inspection by using imaging and spectroscopy technologies for future research and development will also be reported and formulated in this review.