scholarly journals Research on Lightweight Citrus Flowering Rate Statistical Model Combined with Anchor Frame Clustering Optimization

Sensors ◽  
2021 ◽  
Vol 21 (23) ◽  
pp. 7929
Author(s):  
Jianqiang Lu ◽  
Weize Lin ◽  
Pingfu Chen ◽  
Yubin Lan ◽  
Xiaoling Deng ◽  
...  
Keyword(s):  
Statistical Model ◽  
Test Results ◽  
Fast Detection ◽  
Backbone Network ◽  
Feature Extractor ◽  
Flowering Rate ◽  
Enhancement Method ◽  
Clustering Optimization ◽  
Improved Model ◽  
Detection Speed

At present, learning-based citrus blossom recognition models based on deep learning are highly complicated and have a large number of parameters. In order to estimate citrus flower quantities in natural orchards, this study proposes a lightweight citrus flower recognition model based on improved YOLOv4. In order to compress the backbone network, we utilize MobileNetv3 as a feature extractor, combined with deep separable convolution for further acceleration. The Cutout data enhancement method is also introduced to simulate citrus in nature for data enhancement. The test results show that the improved model has an mAP of 84.84%, 22% smaller than that of YOLOv4, and approximately two times faster. Compared with the Faster R-CNN, the improved citrus flower rate statistical model proposed in this study has the advantages of less memory usage and fast detection speed under the premise of ensuring a certain accuracy. Therefore, our solution can be used as a reference for the edge detection of citrus flowering.

scholarly journals YOLOv3-Litchi Detection Method of Densely Distributed Litchi in Large Vision Scenes

2021 ◽  
Vol 2021 ◽  
pp. 1-11
Author(s):  
Hongjun Wang ◽  
Lizhong Dong ◽  
Hao Zhou ◽  
Lufeng Luo ◽  
Guichao Lin ◽  
...  
Keyword(s):  
Detection Performance ◽  
Detection Methods ◽  
Natural Environments ◽  
Test Results ◽  
Detection Time ◽  
Proposed Model ◽  
Bounding Boxes ◽  
Improved Model ◽  
Detection Speed ◽  
Detection Effect

Accurate and reliable fruit detection in the orchard environment is an important step for yield estimation and robotic harvesting. However, the existing detection methods often target large and relatively sparse fruits, but they cannot provide a good solution for small and densely distributed fruits. This paper proposes a YOLOv3-Litchi model based on YOLOv3 to detect densely distributed litchi fruits in large visual scenes. We adjusted the prediction scale and reduced the network layer to improve the detection ability of small and dense litchi fruits and ensure the detection speed. From flowering to 50 days after maturity, we collected a total of 266 images, including 16,000 fruits, and then used them to construct the litchi dataset. Then, the k-means++ algorithm is used to cluster the bounding boxes in the labeled data to determine the priori box size suitable for litchi detection. We trained an improved YOLOv3-Litchi model, tested its litchi detection performance, and compared YOLOv3-Litchi with YOLOv2, YOLOv3, and Faster R-CNN on the actual detection effect of litchi and used the F1 value and the average detection time as the assessed value. The test results show that the F1 of YOLOv3-Litchi is higher than that of YOLOv2 algorithm 0.1, higher than that of YOLOv3 algorithm 0.08, and higher than that of Faster R-CNN algorithm 0.05; the average detection time of YOLOv3-Litchi is 29.44 ms faster than that of YOLOv2 algorithm, 19.56 ms faster than that of YOLOv3 algorithm ms, and 607.06 ms faster than that of Faster R-CNN algorithm. And the detection speed of the improved model is faster. The proposed model remits optimal detection performance for small and dense fruits. The work presented here may provide a reference for further study on fruit-detection methods in natural environments.

scholarly journals A new multi-scale backbone network for object detection based on asymmetric convolutions

2021 ◽  
Vol 104 (2) ◽  
pp. 003685042110113
Author(s):  
Xianghua Ma ◽  
Zhenkun Yang
Keyword(s):  
Object Detection ◽  
Image Features ◽  
Detection Accuracy ◽  
Mobile Platforms ◽  
Multi Scale ◽  
Backbone Network ◽  
Aspect Ratios ◽  
Pascal Voc ◽  
Scale Characteristics ◽  
Detection Speed

Real-time object detection on mobile platforms is a crucial but challenging computer vision task. However, it is widely recognized that although the lightweight object detectors have a high detection speed, the detection accuracy is relatively low. In order to improve detecting accuracy, it is beneficial to extract complete multi-scale image features in visual cognitive tasks. Asymmetric convolutions have a useful quality, that is, they have different aspect ratios, which can be used to exact image features of objects, especially objects with multi-scale characteristics. In this paper, we exploit three different asymmetric convolutions in parallel and propose a new multi-scale asymmetric convolution unit, namely MAC block to enhance multi-scale representation ability of CNNs. In addition, MAC block can adaptively merge the features with different scales by allocating learnable weighted parameters to three different asymmetric convolution branches. The proposed MAC blocks can be inserted into the state-of-the-art backbone such as ResNet-50 to form a new multi-scale backbone network of object detectors. To evaluate the performance of MAC block, we conduct experiments on CIFAR-100, PASCAL VOC 2007, PASCAL VOC 2012 and MS COCO 2014 datasets. Experimental results show that the detection precision can be greatly improved while a fast detection speed is guaranteed as well.

An improved nonlinear model considering relative velocity for the friction behavior between untwisted glass-fiber tow and roller

2021 ◽  
pp. 004051752110308
Author(s):  
Yang Liu ◽  
Zhong Xiang ◽  
Xiangqin Zhou ◽  
Zhenyu Wu ◽  
Xudong Hu
Keyword(s):  
Friction Coefficient ◽  
Glass Fiber ◽  
Relative Velocity ◽  
Friction Model ◽  
Woven Fabric ◽  
Test Results ◽  
Application Process ◽  
Friction Behavior ◽  
Improved Model

Friction between the tow and tool surface normally happens during the tow production, fabric weaving, and application process and has an important influence on the quality of the woven fabric. Based on this fact, this paper studied the influence of tension and relative velocity on the three kinds of untwisted-glass-fiber tow-on-roller friction with a Capstan-based test setup. Furthermore, an improved nonlinear friction model taking both tension and velocity into account was proposed. According to statistical test results, firstly, the friction coefficient was found to be positively correlated with tension and relative velocity. Secondly, tension and velocity were complementary on the tow-on-roller friction behavior, with neither being superior to the other. Thirdly, an improved model was found to present well the nonlinear characteristics between friction coefficient and tension and velocity, and predicational results of the model were found to agree well with the observations from Capstan tests.

scholarly journals Prediction of Milk Production per Cow Lactation in the Mexican Tropics

2021 ◽  
Vol 13 (12) ◽  
Author(s):  
Mónica Yazmín Herrera-Sotero ◽  
Julio César Vinay-Vadillo ◽  
Elizabeth León-García ◽  
Javier Francisco Enríquez-Quiroz ◽  
Benjamín Alfredo Piña-Cárdenas ◽  
...  
Keyword(s):  
Statistical Model ◽  
Mathematical Models ◽  
Milk Production ◽  
Design Methodology ◽  
Linear Interpolation ◽  
Test Results ◽  
Birth Season ◽  
Monthly Data ◽  
Brown Swiss ◽  
Mexican Tropics

Objective: To evaluate non-linear and linear mathematical models used to estimate milk production per lactation, at different frequencies of milk weighing from records of Holstein (Ho), Brown Swiss (BS) cows and their crosses with Zebu (Z). Design/Methodology/Approach: The models evaluated were: Wood, Wilmink and Linear Interpolation. Daily records of milk production from 471 lactations of 72 cows were used; 1,884 records were created with frequencies of weekly, biweekly and monthly milk production. The following were included in the statistical model: the genotype (Ho X Z andSP X Z), birth season (rainy and dry), and number of lactation (1 and 2) with double and triple interactions. The statistical analyses were performed with GLM from MINITAB v17. The means were compared with Tukey’s test. Results: No differences were found (P?0.05) between the models for the average milk production per lactation in kg, obtained from daily measurements or estimated from weekly, biweekly and monthly data, although for the factors of birth season, number of lactation, and genotype they showed differences (P ? 0.05) in milk production per lactation. Study Limitations/Implications: Daily records of milk production are necessary to obtain production per lactation; the models applied predict milk production in a similar way in different frequencies of weighing in Holstein, Brown Swiss cows and their crosses with Zebu. Findings/Conclusions: The models used allow predicting the milk production per cow in a similar way in different frequencies of weighing.

scholarly journals Detection of Collapsed Buildings in Post-Earthquake Remote Sensing Images Based on the Improved YOLOv3

2019 ◽  
Vol 12 (1) ◽  
pp. 44 ◽  
Author(s):  
Haojie Ma ◽  
Yalan Liu ◽  
Yuhuan Ren ◽  
Jingxian Yu
Keyword(s):  
Remote Sensing ◽  
Object Detection ◽  
Spatial Resolution ◽  
High Spatial Resolution ◽  
Detection Methods ◽  
Remote Sensing Images ◽  
Sensing Technology ◽  
Collapsed Buildings ◽  
Improved Model ◽  
Detection Speed

An important and effective method for the preliminary mitigation and relief of an earthquake is the rapid estimation of building damage via high spatial resolution remote sensing technology. Traditional object detection methods only use artificially designed shallow features on post-earthquake remote sensing images, which are uncertain and complex background environment and time-consuming feature selection. The satisfactory results from them are often difficult. Therefore, this study aims to apply the object detection method You Only Look Once (YOLOv3) based on the convolutional neural network (CNN) to locate collapsed buildings from post-earthquake remote sensing images. Moreover, YOLOv3 was improved to obtain more effective detection results. First, we replaced the Darknet53 CNN in YOLOv3 with the lightweight CNN ShuffleNet v2. Second, the prediction box center point, XY loss, and prediction box width and height, WH loss, in the loss function was replaced with the generalized intersection over union (GIoU) loss. Experiments performed using the improved YOLOv3 model, with high spatial resolution aerial remote sensing images at resolutions of 0.5 m after the Yushu and Wenchuan earthquakes, show a significant reduction in the number of parameters, detection speed of up to 29.23 f/s, and target precision of 90.89%. Compared with the general YOLOv3, the detection speed improved by 5.21 f/s and its precision improved by 5.24%. Moreover, the improved model had stronger noise immunity capabilities, which indicates a significant improvement in the model’s generalization. Therefore, this improved YOLOv3 model is effective for the detection of collapsed buildings in post-earthquake high-resolution remote sensing images.

scholarly journals ISSD: Improved SSD for Insulator and Spacer Online Detection Based on UAV System

Sensors ◽  
2020 ◽  
Vol 20 (23) ◽  
pp. 6961
Author(s):  
Xuan Liu ◽  
Yong Li ◽  
Feng Shuang ◽  
Fang Gao ◽  
Xiang Zhou ◽  
...  
Keyword(s):  
Capture Rate ◽  
Aerial Images ◽  
Detection Accuracy ◽  
Single Shot ◽  
Online Detection ◽  
Feature Maps ◽  
Fast Detection ◽  
Model Size ◽  
Small Model ◽  
Detection Speed

In power inspection tasks, the insulator and spacer are important inspection objects. UAV (unmanned aerial vehicle) power inspection is becoming more and more popular. However, due to the limited computing resources carried by a UAV, a lighter model with small model size, high detection accuracy, and fast detection speed is needed to achieve online detection. In order to realize the online detection of power inspection objects, we propose an improved SSD (single shot multibox detector) insulator and spacer detection algorithm using the power inspection images collected by a UAV. In the proposed algorithm, the lightweight network MnasNet is used as the feature extraction network to generate feature maps. Then, two multiscale feature fusion methods are used to fuse multiple feature maps. Lastly, a power inspection object dataset containing insulators and spacers based on aerial images is built, and the performance of the proposed algorithm is tested on real aerial images and videos. Experimental results show that the proposed algorithm can efficiently detect insulators and spacers. Compared with existing algorithms, the proposed algorithm has the advantages of small model size and fast detection speed. The detection accuracy can achieve 93.8%. The detection time of a single image on TX2 (NVIDIA Jetson TX2) is 154 ms and the capture rate on TX2 is 8.27 fps, which allows realizing online detection.

Creep Model Based on Theta Projection and Omega Method for Predicting the Creep Behavior of Alloy

2007 ◽  
Vol 353-358 ◽  
pp. 533-536
Author(s):  
Bong Min Song ◽  
Jong Yup Kim ◽  
Joon Hyun Lee
Keyword(s):  
Creep Behavior ◽  
Constant Load ◽  
Control Mode ◽  
Creep Model ◽  
Test Results ◽  
Creep Data ◽  
Creep Tests ◽  
Omega Method ◽  
Improved Model ◽  
Term Creep

Creep testing of Alloy 718 has been carried out at various loads in the temperature range near 650°C in constant load control mode in order to understand how to predict the creep behavior including tertiary creep. The test results have been used for evaluating the existed models, such as Theta projection and Omega method that have been widely used for predicting long term creep strain and rupture time. After determining variables and material parameters of each method with the test results, estimated creep data from each model have been compared with the each measured creep data from the creep tests. The root cause of the discrepancy between estimated and measured data has been analyzed in order to improve the existed methods. The reliability of the improved model has been evaluated in relation to creep data.

The Pumping Dynamics of Swash Plate Piston Pumps

1989 ◽  
Vol 111 (2) ◽  
pp. 307-312 ◽  
Author(s):  
K. A. Edge ◽  
J. Darling
Keyword(s):  
Cross Section ◽  
Cylinder Pressure ◽  
Test Results ◽  
Axial Piston Pump ◽  
Flow Ripple ◽  
Swash Plate ◽  
Hydraulic Axial Piston Pump ◽  
Relief Groove ◽  
Improved Model ◽  
Axial Piston

This paper describes a study of the cylinder pressure and flow in an oil hydraulic axial piston pump. A comparison is made between a theoretical model based on the effects of fluid compliance within the cylinder, and an improved model which accounts for the influence of oil momentum in the port plate region. The improved model is validated by comparison with experimental test results and is used to analyze the influence of port plate and relief groove design on cylinder pressure and pump flow ripple. A steeply sloping triangular cross-section groove was found to be the most satisfactory design.

scholarly journals A New Method for Detecting Compensation Hole Parameters of Automobile Brake Master Cylinder Based on Machine Vision

2021 ◽  
Vol 2021 ◽  
pp. 1-14
Author(s):  
Changfu Zhao ◽  
Hongchang Ding ◽  
Guohua Cao ◽  
Ying Zhang
Keyword(s):  
Hough Transform ◽  
New Method ◽  
Zernike Moment ◽  
Machining Accuracy ◽  
Detection Accuracy ◽  
Master Cylinder ◽  
Fast Detection ◽  
Detection Technology ◽  
Center Position ◽  
Detection Speed

The machining accuracy of the compensation hole of the automobile brake master cylinder directly determines the safety of the automobile and the reliability of parking. How to detect the parameters of the compensation hole with high precision becomes a crucial issue. In this paper, by analyzing the principle of Hough transform detection technology and several optimization algorithms, a new method combining Zernike moment and improved gradient Hough transform is proposed to detect the circular hole parameters. The simulation experiment shows that the proposed algorithm satisfies 0.1 pixels in the coordinate detection of the center position, and the radius detection accuracy is 0.05 pixels, with fast detection speed and good robustness. Compared with the random Hough transform algorithm and the gradient Hough transform algorithm, the algorithm proposed in this paper has higher detection accuracy, faster detection speed, and better robustness, which meets the online detection accuracy requirements of the brake master cylinder compensation hole.

Sign in / Sign up

Export Citation Format

Share Document