Rapid and accurate detection of Camellia oleifera fruit is beneficial to improve the picking efficiency. However, detection faces new challenges because of the complex field environment. A Camellia oleifera fruit detection method based on YOLOv7 network and multiple data augmentation was proposed to detect Camellia oleifera fruit in complex field scenes. Firstly, the images of Camellia oleifera fruit were collected in the field to establish training and test sets. Detection performance was then compared among YOLOv7, YOLOv5s, YOLOv3-spp and Faster R-CNN networks. The YOLOv7 network with the best performance was selected. A DA-YOLOv7 model was established via the YOLOv7 network combined with various data augmentation methods. The DA-YOLOv7 model had the best detection performance and a strong generalisation ability in complex scenes, with mAP, Precision, Recall, F1 score and average detection time of 96.03%, 94.76%, 95.54%, 95.15% and 0.025 s per image, respectively. Therefore, YOLOv7 combined with data augmentation can be used to detect Camellia oleifera fruit in complex scenes. This study provides a theoretical reference for the detection and harvesting of crops under complex conditions.

In order to solve the problems of traditional seeders, such as low seeding efficiency, tangled straw, a large amount of clay, easy ridge breakage in sowing operations, low qualified rate of high-speed seeding, and poor uniformity, this paper takes the pneumatic corn planter as the research object, the Beidou automatic driving unit as the carrier, the CAN (Controller Area Network) bus as the communication medium, and the double closed-loop fuzzy PID (proportion-integral-derivative) algorithm as the control core and designs a high-speed precision corn seeding control system based on Beidou navigation. It solves the problems that exist in traditional planters. In the bench experiment, the stability of the system is judged by comparing the motor control accuracy with ordinary PID and measuring the motor response time of the system at different speeds. The bench test results show that when the theoretical seeding speed is 0~34 r·min⁻¹, the response time of the motor is shortened by 0.51 s compared with the ordinary PID control, and the error between the actual speed and the target value is less than 0.35%. The field experiment results show that when the unit runs for 5~13 km·h⁻¹, the qualified rate of average planting spacing is greater than 95.81%, the reseeding rate is less than 10.11%, and the coefficient of variation is less than 16.72%, which complies with the standard of a corn sowing operation.

This study examines the means of reducing the damage to the branches of Camellia oleifera in the process of vibration picking and solving the problems of low equipment-development efficiency and slow product renewal caused by using traditional test methods to determine vibration picking parameters. In this study, the optimal vibration parameters were determined by using the self-response (branch acceleration and strain) law of the Camellia oleifera tree, and finite element analysis and experiments are used to solve this problem. The 3D model of Camellia oleifera was built by Solidworks. The natural frequencies of Camellia oleifera were analyzed by modal analysis, the vibration frequency and amplitude were determined by harmonic response analysis, and transient analysis was used to compare with the test results. The results show that the optimal vibration frequency range of Camellia oleifera is 4~10 Hz, and the average correlation coefficient between the maximum synthetic acceleration and the simulated value is 0.85, which shows that the model can reliably predict the vibration response. At the same time, the best vibration parameters were determined to be 9 Hz, 60 mm and 10 s. Under these parameters, the abscission rate of the Camellia oleifera fruit was 90%, and the damage rate of the flower bud was 13%. The mechanized picking effect of Camellia oleifera fruit was good. This study can quickly determine the vibration picking parameters of Camellia oleifera fruit and effectively improve the development speed of vibration picking of Camellia oleifera fruit.

This study aimed to resolve the problems of full wheat straw returning to the field, which might readily cause stalk obstruction, poor sowing quality, and serious weeds at the seedling stage, affecting the growth of maize. Based on the idea of “simultaneous seeding and spraying, closed weeding”, this paper presented a design method for designing a corn seed-fertilizer-herbicide simultaneous operation machine, which focuses on the design of vertical active straw-removing anti-blocking device mechanism, design of nozzle key parameters, nozzle selection, seeding monomer analysis and spatial layout design of seed-fertilizer-herbicide mechanism. In addition, the interrelated formulas were deduced and machine design and field experiment were conducted. The experiment results showed that the average variation coefficient of spray uniformity of machines was 17.70%. The post-experiment weed amount was 8.9%, which was lower than that before sowing, 8.5% lower than that before artificially closed weeding, and 14.3% lower than that in unenclosed weeding area. Moreover, the weeds were less in the working area of the machine, and the growth of corn was better. Compared with manual closed weeding, the average plant height uniformity and average stem diameter uniformity increased by 4.4% and 5.1%, respectively. Compared with unclosed weeding, the average plant height uniformity and average stem diameter uniformity increased by 18.3% and 10.8%, respectively. Overall, the rationality of the design method proposed in this paper was validated, and these can lay a foundation for the research and development of the same type of machine. Keywords: seed-fertilizer-herbicide, combined application, precision seeding machine, spray device, closed weeding DOI: 10.25165/j.ijabe.20191204.4679 Citation: Huang X, Wang W W, Li Z D, Wang Q Q, Zhu C X, Chen L Q. Design method and experiment of machinery for combined application of seed, fertilizer and herbicide. Int J Agric & Biol Eng, 2019; 12(4): 63–71.

Introduction: In order to promote sugarcane pre-cut seed good seed and good method planting technology, we combine the development of sugarcane pre-cut seed intelligent 0p99oposeed cutting machine to realize the accurate and fast identification and cutting of sugarcane stem nodes.Methods: In this paper, we proposed an algorithm to improve YOLOv4-Tiny for sugarcane stem node recognition. Based on the original YOLOv4-Tiny network, the three maximum pooling layers of the original YOLOv4-tiny network were replaced with SPP (Spatial Pyramid Pooling) modules, which fuse the local and global features of the images and enhance the accurate localization ability of the network. And a 1×1 convolution module was added to each feature layer to reduce the parameters of the network and improve the prediction speed of the network.Results: On the sugarcane dataset, compared with the Faster-RCNN algorithm and YOLOv4 algorithm, the improved algorithm yielded an mean accuracy precision (MAP) of 99.11%, a detection accuracy of 97.07%, and a transmission frame per second (fps) of 30, which can quickly and accurately detect and identify sugarcane stem nodes.Discussion: In this paper, the improved algorithm is deployed in the sugarcane stem node fast identification and dynamic cutting system to achieve accurate and fast sugarcane stem node identification and cutting in real time. It improves the seed cutting quality and cutting efficiency and reduces the labor intensity.

For the current sowing machine, unavoidable reasons such as clogging of the seed row disc type opener and the seed guide tube, slipping off the ground wheel, and other unavoidable reasons lead to sowing machine leakage. This paper designs a system to detect and compensate for missed sowing of maize precision seeds. The system mainly consists of a missed seeding detection system module, a control system module, a display system module, an actuation system module, a compensation system module, etc. Detection of missed seedings uses a microcontroller as the controller and a fiber optic sensor as the detection element. Through the microcontroller’s input capture and timer timing function, the total number of rows of missed and reseeded seeds is displayed on the LED display and fed back to the replenishment system to realize the alarm of missed seeds and automatic compensation. The results show that: the detection accuracy of missed seeding is more than 96%, and the highest detection accuracy can reach 100%. Less than 4% error occurred in missed seeding compensation (0.3% error in stepper motor speed, 4% error in rotation angle). The replanting rate of replanters is more than 90%; the replanting pass rate is more than 95%. When the tractor driving speed is 3~8 km/h, the sowing qualified rate is more than 90% to meet the sowing and replanting requirements.