Subsoiling has been acknowledged worldwide to break compacted hardpan, improve soil permeability and water storage capacity, and promote topsoil deepening and root growth. However, there exist certain factors which limit the wide in-field application of subsoiling machines. Of these factors, the main two are poor subsoiling quality and high energy consumption, especially the undesired tillage depth obtained in the field with cover crops. Based on the analysis of global adoption and benefits of subsoiling technology, and application status of subsoiling machines, this article reviewed the research methods, technical characteristics, and developing trends in five key aspects, including subsoiling shovel design, anti-drag technologies, technologies of tillage depth detection and control, and research on soil mechanical interaction. Combined with the research progress and application requirements of subsoiling machines across the globe, current problems and technical difficulties were analyzed and summarized. Aiming to solve these problems, improve subsoiling quality, and reduce energy consumption, this article proposed future directions for the development of subsoiling machines, including optimizing the soil model in computer simulation, strengthening research on the subsoiling mechanism and comprehensive effect, developing new tillage depth monitoring and control systems, and improving wear-resisting properties of subsoiling shovels.

Harvesting robots had difficulty extracting filament phenotypes for small, numerous filaments, heavy cross-obscuration, and similar phenotypic characteristics with organs. Robots experience difficulty in localizing under near-colored backgrounds and fuzzy contour features. It cannot accurately harvest filaments for robots. Therefore, a method for detecting and locating filament picking points based on an improved DeepLabv3+ algorithm is proposed in this study. A lightweight network structure, ShuffletNetV2, was used to replace the backbone network Xception of the traditional DeepLabv3+. Convolutional branches for 3 different sampling rates were added to extract information on the safflower features under the receptive field. Convolutional block attention was incorporated into feature extraction at the coding and decoding layers to solve the interference problem of the near-color background in the feature-fusion process. Then, using the region of interest of the safflower branch obtained by the improved DeepLabv3+, an algorithm for filament picking-point localization was designed based on barycenter projection. The tests demonstrated that this method was capable of accurately localizing the filament. The mean pixel accuracy and mean intersection over union of the improved DeepLabv3+ were 95.84% and 96.87%, respectively. The detection rate and weights file size required were superior to those of other algorithms. In the localization test, the depth-measurement distance between the depth camera and target safflower filament was 450 to 510 mm, which minimized the visual-localization error. The average localization and picking success rates were 92.50% and 90.83%, respectively. The results show that the proposed localization method offers a viable approach for accurate harvesting localization.

The accurate acquisition of safflower filament information is the prerequisite for robotic picking operations. To detect safflower filaments accurately in different illumination, branch and leaf occlusion, and weather conditions, an improved Faster R-CNN model for filaments was proposed. Due to the characteristics of safflower filaments being dense and small in the safflower images, the model selected ResNeSt-101 with residual network structure as the backbone feature extraction network to enhance the expressive power of extracted features. Then, using Region of Interest (ROI) Align improved ROI Pooling to reduce the feature errors caused by double quantization. In addition, employing the partitioning around medoids (PAM) clustering was chosen to optimize the scale and number of initial anchors of the network to improve the detection accuracy of small-sized safflower filaments. The test results showed that the mean Average Precision (mAP) of the improved Faster R-CNN reached 91.49%. Comparing with Faster R-CNN, YOLOv3, YOLOv4, YOLOv5, and YOLOv6, the improved Faster R-CNN increased the mAP by 9.52%, 2.49%, 5.95%, 3.56%, and 1.47%, respectively. The mAP of safflower filaments detection was higher than 91% on a sunny, cloudy, and overcast day, in sunlight, backlight, branch and leaf occlusion, and dense occlusion. The improved Faster R-CNN can accurately realize the detection of safflower filaments in natural environments. It can provide technical support for the recognition of small-sized crops.

Discrete element modeling and parameter calibration of safflower biomechanical properties

Subsoiling can break the compacted hardpan without turning or mixing soil layers. It has significant advantages in improving soil structure, promoting rainwater infiltration, and increasing air permeability of soil. The soil compacted hardpan will not be completely broken and more power consumption will be generated unless the desired tillage depth is obtained. However, due to uneven surface between and within each row of subsoiling shovel in the field, the existing adjustment methods, adjusting via the lifting device of the whole machine or a group of tillage components, cannot ensure each subsoiling shovel avoiding undesired tillage depth. Therefore, a tillage depth monitoring and control system for the independent adjustment of each subsoiling shovel was developed, and the methods of detecting, adjusting, displaying, and recording tillage depth were described. Field experiments were conducted to evaluate detecting accuracy, stability of tillage depth, transient response time, and advantages. The results showed that the value obtained by sensor differed from manual measurement at the speed of 3 km/h, 4 km/h, and 5 km/h averagely by 8.28%. The mean value of the coefficient of the tillage depth stability at three speeds were all greater than 94%. The mean transient response time was 0.6 s. The standard deviation of tillage depth obtained under system control was 38.31, which was less than the 51.52 obtained by only adjusting on the three-point suspension. The subsoiler equipped with this system was capable of obtaining a desired tillage depth of each subsoiling shovel in every second.

Accurate safflower recognition is a critical research challenge in the field of automated safflower harvesting. The growing environment of safflowers, including factors such as variable weather conditions in unstructured environments, shooting distances, and diverse morphological characteristics, presents significant difficulties for detection. To address these challenges and enable precise safflower target recognition in complex environments, this study proposes an improved safflower detection model, WED-YOLO, based on YOLOv8n. Firstly, the original bounding box loss function is replaced with the dynamic non-monotonic focusing mechanism Wise Intersection over Union (WIoU), which enhances the model’s bounding box fitting ability and accelerates network convergence. Then, the upsampling module in the network’s neck is substituted with the more efficient and versatile dynamic upsampling module, DySample, to improve the precision of feature map upsampling. Meanwhile, the EMA attention mechanism is integrated into the C2f module of the backbone network to strengthen the model’s feature extraction capabilities. Finally, a small-target detection layer is incorporated into the detection head, enabling the model to focus on small safflower targets. The model is trained and validated using a custom-built safflower dataset. The experimental results demonstrate that the improved model achieves Precision (P), Recall (R), mean Average Precision (mAP), and F₁ score values of 93.15%, 86.71%, 95.03%, and 89.64%, respectively. These results represent improvements of 2.9%, 6.69%, 4.5%, and 6.22% over the baseline model. Compared with Faster R-CNN, YOLOv5, YOLOv7, and YOLOv10, the WED-YOLO achieved the highest mAP value. It outperforms the module mentioned by 13.06%, 4.85%, 4.86%, and 4.82%, respectively. The enhanced model exhibits superior precision and lower miss detection rates in safflower recognition tasks, providing a robust algorithmic foundation for the intelligent harvesting of safflowers.