The improved stratified transformer for organ segmentation of Arabidopsis.

Segmenting plant organs is a crucial step in extracting plant phenotypes. Despite the advancements in point-based neural networks, the field of plant point cloud segmentation suffers from a lack of adequate datasets. In this study, we addressed this issue by generating Arabidopsis models using L-system and proposing the surface-weighted sampling method. This approach enables automated point sampling and annotation, resulting in fully annotated point clouds. To create the Arabidopsis dataset, we employed Voxel Centroid Sampling and Random Sampling as point cloud downsampling methods, effectively reducing the number of points. To enhance the efficiency of semantic segmentation in plant point clouds, we introduced the Plant Stratified Transformer. This network is an improved version of the Stratified Transformer, incorporating the Fast Downsample Layer. Our improved network underwent training and testing on our dataset, and we compared its performance with PointNet++, PAConv, and the original Stratified Transformer network. For semantic segmentation, our improved network achieved mean Precision, Recall, F1-score and IoU of 84.20, 83.03, 83.61 and 73.11%, respectively. It outperformed PointNet++ and PAConv and performed similarly to the original network. Regarding efficiency, the training time and inference time were 714.3 and 597.9 ms, respectively, which were reduced by 320.9 and 271.8 ms, respectively, compared to the original network. The improved network significantly accelerated the speed of feeding point clouds into the network while maintaining segmentation performance. We demonstrated the potential of virtual plants and deep learning methods in rapidly extracting plant phenotypes, contributing to the advancement of plant phenotype research.

Design and experiments with a SLAM system for low-density canopy environments in greenhouses based on an improved Cartographer framework.

To address the problem that the low-density canopy of greenhouse crops affects the robustness and accuracy of simultaneous localization and mapping (SLAM) algorithms, a greenhouse map construction method for agricultural robots based on multiline LiDAR was investigated. Based on the Cartographer framework, this paper proposes a map construction and localization method based on spatial downsampling. Taking suspended tomato plants planted in greenhouses as the research object, an adaptive filtering point cloud projection (AF-PCP) SLAM algorithm was designed. Using a wheel odometer, 16-line LiDAR point cloud data based on adaptive vertical projections were linearly interpolated to construct a map and perform high-precision pose estimation in a greenhouse with a low-density canopy environment. Experiments were carried out in canopy environments with leaf area densities (LADs) of 2.945-5.301 m2/m3. The results showed that the AF-PCP SLAM algorithm increased the average mapping area of the crop rows by 155.7% compared with that of the Cartographer algorithm. The mean error and coefficient of variation of the crop row length were 0.019 m and 0.217%, respectively, which were 77.9% and 87.5% lower than those of the Cartographer algorithm. The average maximum void length was 0.124 m, which was 72.8% lower than that of the Cartographer algorithm. The localization experiments were carried out at speeds of 0.2 m/s, 0.4 m/s, and 0.6 m/s. The average relative localization errors at these speeds were respectively 0.026 m, 0.029 m, and 0.046 m, and the standard deviation was less than 0.06 m. Compared with that of the track deduction algorithm, the average localization error was reduced by 79.9% with the proposed algorithm. The results show that our proposed framework can map and localize robots with precision even in low-density canopy environments in greenhouses, demonstrating the satisfactory capability of the proposed approach and highlighting its promising applications in the autonomous navigation of agricultural robots.

Sprayer boom height measurement in wheat field using ultrasonic sensor: An exploratory study.

In order to explore the influencing factors and laws of ultrasonic sensor detecting wheat canopy height, designed an ultrasonic sensor detection height test platform with speed adjustable function. Taking step surface, bare soil and wheat canopy as the research objects, a canopy height calculation method based on K-mean clustering is proposed, and the response characteristics of ultrasonic detection to three media under different operating speeds are explored. Firstly, the step detection test results show that the average detection error of ultrasonic sensor is 1.35%. When the sensor detection distance is switched at the step, with the increase of detection distance, the actual offset at the step increases first and then tends to be stable, and the maximum offset is 10.4cm. The test results of bare soil slope show that the relative error between the detection distance and the manual measurement distance is 1.4% under quasi-static conditions. The leading or lagging of detection under moving conditions is affected by multiple factors such as terrain undulation, speed and detection range. The detection test results of wheat canopy showed that the detection distance was larger than the manual measurement distance, and the smaller the canopy density, the greater the detection error and error variance. When the moving speed is 0.3m/s-1.2m/s, the average detection deviation of the ultrasonic sensor for five kinds of wheat canopy density is 0.14m, and the maximum variance of the detection deviation is 0.07cm2. In this paper, the research on the response characteristics of ultrasonic to the detection of bare soil and sparse canopy in wheat field can provide technical support for the detection of crop canopy in the field.

Cabbage and Weed Identification Based on Machine Learning and Target Spraying System Design.

The complexity of natural elements seriously affects the accuracy and stability of field target identification, and the speed of an identification algorithm essentially limits the practical application of field pesticide spraying. In this study, a cabbage identification and pesticide spraying control system based on an artificial light source was developed. With the image skeleton point-to-line ratio and ring structure features of support vector machine classification and identification, a contrast test of different feature combinations of a support vector machine was carried out, and the optimal feature combination of the support vector machine and its parameters were determined. In addition, a targeted pesticide spraying control system based on an active light source and a targeted spraying delay model were designed, and a communication protocol for the targeted spraying control system based on electronic control unit was developed to realize the controlled pesticide spraying of targets. According to the results of the support vector machine classification test, the feature vector comprised of the point-to-line ratio, maximum inscribed circle radius, and fitted curve coefficient had the highest identification accuracy of 95.7%, with a processing time of 33 ms for a single-frame image. Additionally, according to the results of a practical field application test, the average identification accuracies of cabbage were 95.0%, average identification accuracies of weed were 93.5%, and the results of target spraying at three operating speeds of 0.52 m/s, 0.69 m/s and 0.93 m/s show that the average invalid spraying rate, average missed spraying rate, and average effective spraying rate were 2.4, 4.7, and 92.9%, respectively. Moreover, it was also found from the results that with increasing speeds, the offset of the centre of the mass of the target increased and reached a maximum value of 28.6 mm when the speed was 0.93 m/s. The void rate and pesticide saving rate were 65 and 33.8% under continuous planting conditions and 76.6 and 53.3% under natural seeding deficiency conditions, respectively.

A LiDAR Sensor-Based Spray Boom Height Detection Method and the Corresponding Experimental Validation.

Sprayer boom height (Hb) variations affect the deposition and distribution of droplets. An Hb control system is used to adjust Hb to maintain an optimum distance between the boom and the crop canopy, and an Hb detection sensor is a key component of the Hb control system. This study presents a new, low-cost light detection and ranging (LiDAR) sensor for Hb detection developed based on the principle of single-point ranging. To examine the detection performance of the LiDAR sensor, a step height detection experiment, a field ground detection experiment, and a wheat stubble (WS) height detection experiment as well as a comparison with an ultrasonic sensor were performed. The results showed that the LiDAR sensor could be used to detect Hb. When used to detect the WS height (HWS), the LiDAR sensor primarily detected the WS roots and the inside of the WS canopy. HWS and movement speed of the LiDAR sensor (VLiDAR) has a greater impact on the detection performance of the LiDAR sensor for the WS canopy than that for the WS roots. The detection error of the LiDAR sensor for the WS roots is less than 5.00%, and the detection error of the LiDAR sensor for the WS canopy is greater than 8.00%. The detection value from the LiDAR sensor to the WS root multiplied by 1.05 can be used as a reference basis for adjusting Hb, and after the WS canopy height is added to the basis, the value can be used as an index for adjusting Hb in WS field spraying. The results of this study will promote research on the boom height detection method and autonomous Hb control system.