It is important to detect and classify foreign fibers in cotton, especially white and transparent foreign fibers, to produce subsequent yarn and textile quality. There are some problems in the actual cotton foreign fiber removing process, such as some foreign fibers missing inspection, low recognition accuracy of small foreign fibers, and low detection speed. A polarization imaging device of cotton foreign fiber was constructed based on the difference in optical properties and polarization characteristics between cotton fibers. An object detection and classification algorithm based on an improved YOLOv5 was proposed to achieve small foreign fiber recognition and classification. The methods were as follows: (1) The lightweight network Shufflenetv2 with the Hard-Swish activation function was used as the backbone feature extraction network to improve the detection speed and reduce the model volume. (2) The PANet network connection of YOLOv5 was modified to obtain a fine-grained feature map to improve the detection accuracy for small targets. (3) A CA attention module was added to the YOLOv5 network to increase the weight of the useful features while suppressing the weight of invalid features to improve the detection accuracy of foreign fiber targets. Moreover, we conducted ablation experiments on the improved strategy. The model volume, mAP@0.5, mAP@0.5:0.95, and FPS of the improved YOLOv5 were up to 0.75 MB, 96.9%, 59.9%, and 385f/s, respectively, compared to YOLOv5, and the improved YOLOv5 increased by 1.03%, 7.13%, and 126.47%, respectively, which proves that the method can be applied to the vision system of an actual production line for cotton foreign fiber detection.
Non-destructive testing technology for large grinding wheel geometry is getting more and more attention from the industry. A device based on machine vision technology for intelligent measurement of large grinding wheel size is introduced. After calibrating and measuring the inside and outside radius of the grinding wheel and the thickness of the grinding wheel, intelligent detection is realized through a series of operations such as binarization of the original map, filling, expanding, outline extraction and outline coordinate extraction through hardware design and software programming. The hardware requirements of this design are simple. When measuring the radius of a grinding wheel, the method described in this paper gives the results of radius and height measurements with accuracy up to 5mm and 1mm, respectively. Finally, through repeated measurement experiments, the intelligent detection device of large grinding wheel size established in this paper can effectively solve the problems of field calibration of large grinding wheel and fast detection of inside and outside diameters.
The existing fire alarm system has strict distance and installation requirements between the fire point and the detector, and is easy to be interfered by environmental factors. It is not suitable for places with large space and many interference factors such as Climbazole production line. This paper proposed a flame image detection technology based on RGB+HSI color model and the detection system is designed and developed. The experimental results show that the flame image detection system based on RGB+HSI color model has the better recognition efficiency, which meets the real-time and accuracy requirements for early flame image detection in Climbazole production line.
The train wheelset is a crucial part of railway vehicles, and its damage may lead to serious safety accidents. Therefore, it is imperative to detect tread damage timely and accurately. With the rapid development of deep learning, the image detection method based on a convolutional neural network (CNN) has played an important role. Single Shot MultiBox Detector (SSD) is one of the fastest algorithms in the target detection field. The algorithm has achieved excellent results in target detection, but there is a low recognition rate for small targets. Therefore, we propose an improved SSD target detection algorithm. The Original SSD algorithm is ineffective in detecting small targets with pits and cracks, so conv3-3 is selected to join the detection. We optimize convolution kernel parameters; the convolution layer contains more small target details. Compared with the original SSD, the Mean Average Precision (MAP) of tread defect is improved by 4.38%, and the MAP of small target detection is enhanced by 7.24%. This algorithm has a better performance in detection accuracy.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.