Search

• Farmland unevenness is indispensible reference to agricultural machinery design. • The unevenness of the bottom layer of paddy field can be acquired by proposed method. • Proposal of the corresponding multi-sensor data processing method. • The unevenness can be described in terms of PSD and classified according to ISO8608. In recent years, increasing attention has been paid to the unevenness of farmlands since uneven land could reduce the working quality and service life of agricultural machinery. Due to the special constitution of paddy fields, the prevalent road profilers, such as laser range finders or 3D cameras, are unable to profile the bottom layer on which tractor wheels travel. Based on the concept that the acceleration of a working tractor is a direct response to an uneven path, a novel acquisition platform consisting of a real time kinematic global satellite system (RTK–GNSS), an attitude and heading reference system (AHRS) and a rice-transplanter was developed. Then, the corresponding data processing method was proposed in order to describe the unevenness in terms of the displacement power spectral density (DPSD), and the characteristic parameter G d (n 0) was determined in order to classify the unevenness. Experiments on a cement path, a gravel path and a paddy field path were carried out to validate the proposed methodology, and the results showed the following. (1) The travelling speed of the transplanter had little effect on the unevenness classification. (2) The unevenness classifications for the tested cement, gravel, and paddy field paths were class A, B and C, respectively, in terms of the ISO 8608 standard, which was in accordance with the driver's perception. (3) For all the applied paths, the calculated ω values of the PSD were greater than 2, which indicated that long waves were prevalent in the spatial frequency range of interest. In summary, the proposed approach is an efficient and effective way to acquire, describe and classify the unevenness of the bottom layer of paddy fields. This work can serve as a basis for future studies of soil structure monitoring, components' reliability design and adaptive controller development for intelligent farm machinery. [ABSTRACT FROM AUTHOR]

• A cutting-edge network YOLOX-S was deployed to detect tea buds in high-density canopy. • An improved pointer network (PtrNet) was proposed to find the optimal solution to the picking sequence planning problem. • YOLOX-S only needed 17.43 ms to process a single image with an average precision of 0.642. • The improved pointer network only required 1.69 ms to output an optimal path for the problem up to 100 tea buds. Real-time robotic tea picking ensures the economic benefits of the well-known high-quality tea industry. Efficient tea bud detection and picking sequence planning are two challenges that hinder the development of these robots. To this end, two lightweight neural networks are investigated to tackle these two problems. A state-of-the-art detection network YOLOX-S is first deployed to quickly identify tea buds. Second, the picking sequence planning of the detected tea buds is formulated as a traveling salesman problem (TSP). Then a modified pointer network is proposed to solve the TSP, improving the pointer network by replacing its recurrent neural network with a simple self-attention layer and optimizing its parameters using a reinforcement learning algorithm. The experimental results show that YOLOX-S achieves an average precision of 0.642 and an average running time of 17.43 ms; for the problem of up to 100 tea buds in the two-dimensional interval [0, 1] × [0, 1], the modified pointer network solves the TSP with an average path length of 8.30 and an average running time of 1.69 ms. These results demonstrate that YOLOX-S and the modified pointer network can efficiently solve the tea bud detection and picking sequence planning problem without losing too much accuracy, which provides technical support for real-time tea-harvesting robots. [ABSTRACT FROM AUTHOR]

• Described the current status of land-leveling implements. • Analyzed the current status of laser-controlled leveling technology. • Analyzed the current status of GNSS-control leveling technology. • Analyzed the benefits of the application of land-leveling technology. • Discussed the challenges and future trends of land-leveling technology. Land leveling technology is necessary for land cultivation and is an important support for sustainable agricultural development. First, this paper reviews the current status of land-leveling implements, including dry-land and paddy-field leveling implements. Second, two precision land-leveling technologies, laser-controlled systems and the Global Navigation Satellite System (GNSS), are reviewed. The current status of laser-controlled leveling technology is considered in terms of its three primary components, the laser transmitter, laser receiver, and control terminal. The current status of GNSS-controlled leveling technology is also considered in terms of three aspects: three-dimensional (3D) topographical measurement of farmland, calculation of reference height and soil volume, and planning of work paths. The actual benefits of land-leveling technology applied to the production of different crops are statistically analyzed using metrics including improved land utilization, water savings, and increased yields. Finally, the challenges and future trends in land-leveling implements and technologies are discussed. [ABSTRACT FROM AUTHOR]

Highlights • This paper proposed an external acceleration roll angle Kalman filter. • The external acceleration was estimated using a simplified acceleration model. • The error was less than 1° in paddy field dynamic situation. Abstract The agricultural machinery implements in paddy field are required to measure the roll angle dynamically. In order to reduce the effects of external acceleration on roll estimation thus improving dynamic measurement precision with low cost, this paper proposed an algorithm, the external acceleration roll angle Kalman filter (EARAKF), which estimated the external acceleration model with a one-order low pass filter and Gaussian white noise. After subtracting the estimated real roll angle from the value of accelerometers, the external acceleration superimposing on the single-axis accelerometer was estimated. Eventually, the roll angle estimation without external acceleration effect was obtained after the estimated external acceleration being subtracted from the Kalman filter (KF) in the measurement equation. Furthermore, a parallel track platform was used to impose external acceleration on the accelerometer. The test results shown that the acceleration on Y-axis increased significantly. The root mean square error (RMSE) of the EARAKF was 0.49°, while that of the KF algorithm was 1.91°, which demonstrated that the EARAKF was less influenced by the external acceleration. In the paddy field tests, the RMSE of the KF algorithm were figured out as 1.74°, while that of the EARAKF algorithm was 0.77°, which concluded that the EARAKF can estimate the external acceleration of the accelerometer and obtain a more accurate roll angle. The proposed algorithm presented a roll angle measurement method for the agricultural implements which working in paddy field dynamic scenario and could get less affected by the external acceleration with low cost and high accuracy. [ABSTRACT FROM AUTHOR]

• An improved RGB-D multimodal tea shoot detection model based on YOLOv7 is proposed. • It created a parallel lightweight backbone network for depth images. • It designed a new cross-module spatial attention fusion module. • Experiments were conducted on normal and extreme environment datasets respectively to verify the advanced and robustness of the model. Due to the increasing scarcity of tea pickers, the implementation of intelligent harvesting for premium tea is a crucial prerequisite for the sustainable development of the premium tea industry. The initial step towards achieving intelligent and precise harvesting is the accurate detection of tender shoots, which consist of one bud and one leaf. However, accurately identifying tea shoots poses a challenging visual task due to their small size, variable shapes, as well as similar colors and backgrounds. The existing model, based on RGB images, can only detect partial targets. To address this issue and further enhance the detection of tea buds, this study proposes the utilization of multi-modal features encompassing red, green, blue, and depth (RGB-D) for identification. In addition, a unidirectional complementary multi-modal fusion method is introduced to minimize the adverse effects caused by low-quality depth information. Firstly, an RGB-D dataset comprising high-quality tea leaves is constructed, and the samples are carefully calibrated. Subsequently, an enhanced end-to-end RGB-D multi-modal object detection network, referred to as YOLO-RGBDtea, is developed based on You Only Look Once version 7 (YOLOv7). This model incorporates a parallel lightweight depth image feature extraction backbone network and incorporates a self-attention mechanism to prioritize contextual information. Lastly, a cross-modal spatial attention fusion module (CSFM) is devised to collaboratively integrate depth features with RGB features in a unidirectional manner. The experimental results reveal that YOLO-RGBDtea achieves an AP50 of 91.12% when confronting complex outdoor tea shoots, exhibiting significant performance improvements compared to YOLOv7, especially in scenarios involving small targets, overlapping target groups, and highly overexposed images. Notably, the parameter increment in YOLO-RGBDtea compared to the original YOLOv7 model is merely 17.8%, and the additional components can be seamlessly transferred to other models. Overall, this study introduces a straightforward yet effective multi-modal fusion method that bears theoretical and practical significance in advancing the detection of high-quality tea shoots in complex outdoor environments. [ABSTRACT FROM AUTHOR]

Leveling technology of paddy fields is an important part of the mechanization of rice production, which ensures the consistent depth of water layers to restrain the growth of weeds and improve the utilization of pesticides and fertilizers. However, when the working distance increases in paddy fields (due to laser energy attenuation and laser spot diffusion), the reliability and efficiency of existing laser-leveling technology decreases. To address those problems, a new leveling technology that uses water surface as a benchmark is introduced. The proposed method of water surface as a benchmark to measure the height of the scraper and a benchmark-Recognition algorithm embedded in the proposed method was developed. Experiments were conducted to validate the effectiveness and accuracy of the proposed method by comparing the results with those of existing methods (height measurement for scraper with laser plane as benchmark). The results obtained by the proposed method have similar trends in variation and higher resolution. [ABSTRACT FROM AUTHOR]

• Localization with the growth direction may enhance the plucking accuracy. • Planning motion sequence improves the efficiency of harvesting tea. • Field experiments validate the effectiveness of the proposed harvesting system. The critical issue of the robotic harvesting high-quality tea is to realize tea shoot detection, plucking point localization, and motion planning. In addition, the accuracy and efficiency of the robotic plucking of high-quality tea in the field are essential. Therefore, a robotic harvesting system is proposed in this paper by combining deep learning, point cloud processing, and spatial path planning. First, the deep learning method and the compressed YOLOv3 network are used to quickly and accurately identify tea shoots. Second, an efficient point cloud processing-based 3D localization algorithm for high-quality tea plucking points was proposed. The genetic algorithm is then used to shorten the end-effector's motion path by optimizing the plucking sequences. Eventually, a harvester robot with a parallel manipulator was developed to conduct field plucking experiments and evaluate the effectiveness of the proposed harvesting system. All experimental results demonstrate that the success rates of detection, localization, and motion plucking are 85.16 %, 78.90 %, and 80.23 %, respectively. Furthermore, the overall process harvesting success rate is 53.91 %, and the average plucking time for a single shoot is 2.233 s. Therefore, the proposed harvesting approach can provide technical support for the precise and rapid harvesting of high-quality tea. [ABSTRACT FROM AUTHOR]