Analysis of Visual Navigation Extraction Algorithm Of Farm Robot Based on Dark Primary Colour

For the standardized apple orchards in China, which are mainly dwarfed and densely planted, firstly, according to the spatial distribution characteristics of fruits within the tree canopy, a clamping-pull-off apple picking robot was developed by analyzing the parameters of apple cultivation and picking methods, in order to replace the manual harvesting operation. Then, the D-H method was used to establish the kinematic Equations of the apple-picking robot, the forward and inverse kinematic calculations were carried out, and the Monte Carlo method was used to analyze the workspace of the robot. Through the robot picking task planning and the simulation of the trajectory of the robotic arm, the scheme of the robot's picking strategy was given, and MATLAB software was applied to simulate the motion trajectory as well as to verify the feasibility of the trajectory planning scheme and the picking strategy. Finally, an apple-picking test bed was set up, the corresponding picking control system program was designed, and 45 apples were selected for picking tests. The results showed that during the robot's picking process, the average time for picking each fruit was 7.59 seconds, the fruit recognition success rate was 86.67%, and the picking damage rate was 5.13%.

Section: Introductionmentioning

confidence: 99%

Design and Experiment of Clamping-Pull-Off Apple Picking Robot

GUO,

FU,

CUI

et al. 2023

“…In view of the poor real-time performance and the difficulty of peak detection of the traditional Hough transform to extract the centerline, the researchers proposed a variety of improved Hough transform algorithms such as probabilistic Hough transform and Hough transform based on known points (Chen et al, 2019;Mukhopadhyay et al, 2015;Zhang et al, 2017), which improve the efficiency to some extent. Least squares method is also a common method for crop row centerline detection (Hou, 2020); in view of the shortcoming of this algorithm that is easily affected by noise points, some scholars have also improved it to improve its robustness (Meng et al, 2013).…”

Section: Introductionmentioning

confidence: 99%

Extraction Method for Centerlines of Rice Seedlings Based on Fast-SCNN Semantic Segmentation

Chen

Geng

Wang

et al. 2021

For the extraction of paddy rice seedling centerline, this study proposed a method based on Fast-SCNN (Fast Segmentation Convolutional Neural Network) semantic segmentation network. By training the FAST-SCNN network, the optimal model was selected to separate the seedling from the picture. Feature points were extracted using the FAST (Features from Accelerated Segment Test) corner detection algorithm after the pre-processing of original images. All the outer contours of the segmentation results were extracted, and feature point classification was carried out based on the extracted outer contour. For each class of points, Hough transformation based on known points was used to fit the seedling row centerline. It has been verified by experiments that this algorithm has high robustness in each period within three weeks after transplanting. In a 1280×1024-pixel PNG format color image, the accuracy of this algorithm is 95.9% and the average time of each frame is 158ms, which meets the real-time requirement of visual navigation in paddy field.

Research on Semantic Segmentation of Greenhouse Road Image

YANG,

WANG,

XIE

et al. 2023

In order to realize the automatic driving of agricultural machinery in greenhouse, this paper uses image acquisition equipment to collect road images in greenhouse and makes data sets, builds SETR model based on Transformer framework and DeepLabv3+ model based on convolution neural network for semantic segmentation of road images in greenhouse, and verifies the semantic segmentation ability of the two models to road images in greenhouse. Several groups of training periods are set as observation points to observe the semantic segmentation effect of the two models on the greenhouse road image, and the test set which has not been trained by the model is used as the prediction object to verify the performance of the two models on the semantic segmentation of greenhouse road image. The SETR model reached 94.64% PA on the greenhouse road data set, and 82.72% mIoU, DeepLabv3+ model reached 90.80% PA and 72.35% mIoU on the greenhouse road data set. Both models have excellent performance in semantic segmentation of greenhouse road images, and the performance of SETR model is slightly better than that of DeepLabv3+ model. The semantic segmentation performance of the two models for greenhouse road images can meet the needs of actual deployment.