scholarly journals A peduncle detection method of tomato for autonomous harvesting

Author(s):  
Jiacheng Rong ◽  
Guanglin Dai ◽  
Pengbo Wang

AbstractFor automating the harvesting of bunches of tomatoes in a greenhouse, the end-effector needs to reach the exact cutting point and adaptively adjust the pose of peduncles. In this paper, a method is proposed for peduncle cutting point localization and pose estimation. Images captured in real time at a fixed long-distance are detected using the YOLOv4-Tiny detector with a precision of 92.7% and a detection speed of 0.0091 s per frame, then the YOLACT +  + Network with mAP of 73.1 and a time speed of 0.109 s per frame is used to segment the close-up distance. The segmented peduncle mask is fitted to the curve using least squares and three key points on the curve are found. Finally, a geometric model is established to estimate the pose of the peduncle with an average error of 4.98° in yaw angle and 4.75° in pitch angle over the 30 sets of tests.

Agronomy ◽  
2020 ◽  
Vol 10 (4) ◽  
pp. 590
Author(s):  
Zhenqian Zhang ◽  
Ruyue Cao ◽  
Cheng Peng ◽  
Renjie Liu ◽  
Yifan Sun ◽  
...  

A cut-edge detection method based on machine vision was developed for obtaining the navigation path of a combine harvester. First, the Cr component in the YCbCr color model was selected as the grayscale feature factor. Then, by detecting the end of the crop row, judging the target demarcation and getting the feature points, the region of interest (ROI) was automatically gained. Subsequently, the vertical projection was applied to reduce the noise. All the points in the ROI were calculated, and a dividing point was found in each row. The hierarchical clustering method was used to extract the outliers. At last, the polynomial fitting method was used to acquire the straight or curved cut-edge. The results gained from the samples showed that the average error for locating the cut-edge was 2.84 cm. The method was capable of providing support for the automatic navigation of a combine harvester.


2013 ◽  
Vol 378 ◽  
pp. 478-482
Author(s):  
Yoshihiro Mitani ◽  
Toshitaka Oki

The microbubble has been widely used and shown to be effective in various fields. Therefore, there is an importance of measuring accurately its size by image processing techniques. In this paper, we propose a detection method of microbubbles by the approach based on the Hough transform. Experimental results show only 4.49% of the average error rate of the undetected microbubbles and incorrectly detected ones. This low percentage of the error rate shows the effectiveness of the proposed method.


2019 ◽  
Vol 8 (3) ◽  
pp. 882-889
Author(s):  
Sharif Shah Newaj Bhuiyan ◽  
Othman O. Khalifa

In this paper, an algorithm is developed in 3D Stereo vision to improve image stabilization process for multi-camera viewpoints. Finding accurate unique matching key-points using Harris Laplace corner detection method for different photometric changes and geometric transformation in images. Then improved the connectivity of correct matching pairs by minimizing the global error using spanning tree algorithm. Tree algorithm helps to stabilize randomly positioned camera viewpoints in linear order. The unique matching key-points will be calculated only once with our method. Then calculated planar transformation will be applied for real time video rendering. The proposed algorithm can process more than 200 camera viewpoints within two seconds.


2021 ◽  
Vol 2021 ◽  
pp. 1-18
Author(s):  
Mingrui Luo ◽  
En Li ◽  
Rui Guo ◽  
Jiaxin Liu ◽  
Zize Liang

Redundant manipulators are suitable for working in narrow and complex environments due to their flexibility. However, a large number of joints and long slender links make it hard to obtain the accurate end-effector pose of the redundant manipulator directly through the encoders. In this paper, a pose estimation method is proposed with the fusion of vision sensors, inertial sensors, and encoders. Firstly, according to the complementary characteristics of each measurement unit in the sensors, the original data is corrected and enhanced. Furthermore, an improved Kalman filter (KF) algorithm is adopted for data fusion by establishing the nonlinear motion prediction of the end-effector and the synchronization update model of the multirate sensors. Finally, the radial basis function (RBF) neural network is used to adaptively adjust the fusion parameters. It is verified in experiments that the proposed method achieves better performances on estimation error and update frequency than the original extended Kalman filter (EKF) and unscented Kalman filter (UKF) algorithm, especially in complex environments.


2021 ◽  
Vol 48 (3) ◽  
pp. 325-333
Author(s):  
Jeongin Kwon ◽  
Sohee Son ◽  
Jinwoo Jeon ◽  
Injae Lee ◽  
Jihun Cha ◽  
...  

Author(s):  
Frima Setyawan Nur Rohman ◽  
Ahmadan Ainul Fikri ◽  
Ahmad nur Fuad ◽  
Rahmat Rohim ◽  
Rifki Firmansyah

Abstract - In the 20th century this distance is still a constraint in efforts to measure and retrieve data. In an efficiency effort, a long distance measuring device is required. One method to measure from a distance is to use the Telemetry method. Telemetry is a method for measuring a variable in which monitoring is done remotely. The use of telemetry can be used to transmit data from the flowmeter sensor to be received by the receiver. This study discusses the effect of obstacles on transmitter work to send data to the receiver and test the accuracy of the flowmeter sensor. From this study it can be concluded that the effective distance of data transmission depends on the obstacle, the farthest distance is the moment without obstacles, then decreases when there is a hitch, and will decrease again when one receiver or transmitter is placed in a closed room. And for the accuracy of the sensor, the percentage of accuracy is low at the time of the slow water current, and vice versa high accuracy is obtained when the water current is fast. Based on the research we poured in this journal, water flow measurements using RF Arduino-based 433MHz Modules can measure the flow of water at a distance of up to 35meter with an average error of only 4.1%.


2019 ◽  
Vol 11 (3) ◽  
Author(s):  
Xi Kang ◽  
Jian S. Dai

The parallel mechanism with a reconfigurable platform retains all advantages of parallel mechanisms and provides additional functions by virtue of the reconfigurable platform, leading to kinematic coupling between limbs that restricts development of the mechanism. This paper aims at dealing with kinematic coupling between limbs by investigating the transferability of limb constraints and their degrees of relevance to the platform constraints based on the geometric model of the mechanism. The paper applies screw-system theory to verifying the degree of relevance between limb constraint wrenches and platform constraint wrenches, and reveals the transferability of limb constraints, to obtain the final resultant wrenches and twists of the end effector. The proposed method is extended to parallel mechanisms with planar n-bar reconfigurable platforms, spherical n-bar reconfigurable platforms, and other spatial reconfigurable platforms and lends itself to a way of studying a parallel mechanism with a reconfigurable platform.


2015 ◽  
Vol 2015 ◽  
pp. 1-11 ◽  
Author(s):  
Shuang-biao Zhang ◽  
Xing-cheng Li ◽  
Zhong Su

Due to the fact that attitude error of vehicles has an intense trend of divergence when vehicles undergo worsening coning environment, in this paper, the model of dynamic coning environment is derived firstly. Then, through investigation of the effect on Euler attitude algorithm for the equivalency of traditional attitude algorithm, it is found that attitude error is actually the roll angle error including drifting error and oscillating error, which is induced directly by dynamic coning environment and further affects the pitch angle and yaw angle through transferring. Based on definition of the cone frame and cone attitude, a cone algorithm is proposed by rotation relationship to calculate cone attitude, and the relationship between cone attitude and Euler attitude of spinning vehicle is established. Through numerical simulations with different conditions of dynamic coning environment, it is shown that the induced error of Euler attitude fluctuates by the variation of precession and nutation, especially by that of nutation, and the oscillating frequency of roll angle error is twice that of pitch angle error and yaw angle error. In addition, the rotation angle is more competent to describe the spinning process of vehicles under coning environment than Euler angle gamma, and the real pitch angle and yaw angle are calculated finally.


1992 ◽  
Vol 112 (7) ◽  
pp. 77-91 ◽  
Author(s):  
Ginzo Katsuta ◽  
Atsushi Toya ◽  
Takeshi Endoh ◽  
Hiroshi Suzuki ◽  
Yasuo Sekii

Sign in / Sign up

Export Citation Format

Share Document