A novel approach for fruit shape detection in RGB space was proposed,which was based on fast level set and Chan-Vese model named as Modified Chan-Vese model(MCV) . This new algorithm is fast and suitable for fruit sor...A novel approach for fruit shape detection in RGB space was proposed,which was based on fast level set and Chan-Vese model named as Modified Chan-Vese model(MCV) . This new algorithm is fast and suitable for fruit sorting because it does not need re-initializing. MCV has three advantages compared to the traditional methods. First,it provides a unified frame-work for detecting fruit shape boundary,and does not need any preprocessing even though the raw image is noisy or blurred. Second,if the fruit has different colors at the edges,it can detect perfect boundary. Third,it processed directly in color space without any transformations that may lose much information. The proposed method has been applied to fruit shape detection with promising result.展开更多
Considering the spatial position and shape detection properties of the fiber Bragg grating(FBG)curve sensor used in the human body,the positioning accuracy of the FBG curve sensor plays a major role in the pre-diagnos...Considering the spatial position and shape detection properties of the fiber Bragg grating(FBG)curve sensor used in the human body,the positioning accuracy of the FBG curve sensor plays a major role in the pre-diagnosis and treatment of diseases.We present a new type of shape-sensing catheter(diameter of 2.0 mm and length of 810 mm)that is integrated with an array of four optical fibers,where each contains five nodes,to track the shape.Firstly,the distribution of the four orthogonal fiber gratings is wound around a nitinol wire using novel packaging technology,and the spatial curve shape is rebuilt based on the positioning of discrete points in space.An experimental platform is built,and then a reconstruction algorithm for coordinate point fitting of the Frenet frame is used to perform the reconstruction experiment on millimeter paper.The results show that,compared with those in previous studies,in 2D test,the maximum relative error for the end position is reduced to 2.74%,and in 3D reconstruction experiment,the maximum shape error is 3.43%,which verifies both the applicability of the sensor and the feasibility of the proposed method.The results reported here will provide an academic foundation and the key technologies required for navigation and positioning of noninvasive and minimally invasive surgical robots,intelligent structural health detection,and search and rescue operations in debris.展开更多
Shape matching plays an important role in various computer vision and graphics applications such as shape retrieval, object detection, image editing,image retrieval, etc. However, detecting shapes in cluttered images ...Shape matching plays an important role in various computer vision and graphics applications such as shape retrieval, object detection, image editing,image retrieval, etc. However, detecting shapes in cluttered images is still quite challenging due to the incomplete edges and changing perspective. In this paper, we propose a novel approach that can efficiently identify a queried shape in a cluttered image. The core idea is to acquire the transformation from the queried shape to the cluttered image by summarising all pointto-point transformations between the queried shape and the image. To do so, we adopt a point-based shape descriptor, the pyramid of arc-length descriptor(PAD),to identify point pairs between the queried shape and the image having similar local shapes. We further calculate the transformations between the identified point pairs based on PAD. Finally, we summarise all transformations in a 4 D transformation histogram and search for the main cluster. Our method can handle both closed shapes and open curves, and is resistant to partial occlusions. Experiments show that our method can robustly detect shapes in images in the presence of partial occlusions, fragile edges, and cluttered backgrounds.展开更多
The damage or loss of urban road manhole covers may cause great risk to residents＇ lives and property if they cannot be discovered in time. Most existing research recommendations for solving this problem are difficul...The damage or loss of urban road manhole covers may cause great risk to residents＇ lives and property if they cannot be discovered in time. Most existing research recommendations for solving this problem are difficult to implement. This paper proposes an algorithm that combines the improved Hough transform and image comparison to identify the damage or loss of the manhole covers in complicated surface conditions by using existing urban road video images. Focusing on the pre-processed images, the edge contour tracking algorithm is applied to find all of the edges. Then with the improved Hough transformation, color recognition and image matching algorithm, the manhole cover area is found and the change rates of the manhole cover area are calculated. Based on the threshold of the change rates, it can be determined whether there is potential damage or loss in the manhole cover. Compared with the traditional Hough transform, the proposed method can effectively improve the processing speed and reduce invalid sampling and accumulation. Experimental results indicate that the proposed algorithm has the functions of effective positioning and early warning in the conditions of complex background, different perspectives, and different videoing time and conditions, such as when the target is partially covered.展开更多
A high-precision shape detecting system of cold rolling strip is developed to meet industrial application, which mainly consists of the shape detecting roller, the collecting ring, the digital signal processing （DSP...A high-precision shape detecting system of cold rolling strip is developed to meet industrial application, which mainly consists of the shape detecting roller, the collecting ring, the digital signal processing （DSP） shape signal processing board and the shape control model. Based on the shape detecting principle, the shape detecting roller is designed with a new integral structure for improving the precision of shape detecting and avoiding scratching strip surface. Based on the DSP technology, the DSP shape signal processing circuit board is designed and embedded in the shape detecting system for the reliability and stability of shape signal processing. The shape detecting system was successfully used in Angang 1 250 mm HC 6-high reversible cold rolling mill. The precision of shape detecting is 0.2 I and the shape deviation is controlled within 6 1 after the close loop shape control is input.展开更多
In specific condition, when wrapping angle of cold rolling strip covering surface of shape detecting roll dynamically changes, online radial compression of the shape detecting roll is changed too, and it seriously aff...In specific condition, when wrapping angle of cold rolling strip covering surface of shape detecting roll dynamically changes, online radial compression of the shape detecting roll is changed too, and it seriously affects online shape detecting precision of cold strip. Based on the latest intelligent shape meter developed by Yanshan University, using PSO-BP neural network and actual working condition datum, the cold strip online dynamic wrapping angle compensation model is established, and successfully applied in 1250 mm 6-high cold mill, remarkable results are achieved. The error between calculated values and measured values of total tensions is within 3 %展开更多
Deep boreholes are secured by steel tubes(casings)which are run in the hole and cemented in place.In most cases,these casings are considered a permanent installation.However,sometimes they have to be removed in order ...Deep boreholes are secured by steel tubes(casings)which are run in the hole and cemented in place.In most cases,these casings are considered a permanent installation.However,sometimes they have to be removed in order to repair or abandon the well.As the casing is cemented in place,it cannot be pulled,but needs to be milled to small chips which are flushed out of the borehole by the drilling mud.One of the main challenges in casing milling operations is continuous and complete chip removal.If the metal chips are too long,chip nests will grow around the milling string.As a result,this will restrict the annulus flow area and affect the chip removal in boreholes.The obvious solution in such condition is to do round tripping and clean the chip nest which is associated with the risk of injuries,as well as,increasing the none-productive time.In the worst case,the poor cleaning and circulation of chips can even end up with the milling string stucking problem in boreholes,consequently long-time fishing job.According to the available literatures,hardly any study for identifying the chip shapes and accordingly adapting the operation parameters to the casing milling process environment downhole to keep milling within desired generated chip shapes and sizes could be found.This paper presents an encouraging idea to monitor the milling process in real time by utilizing the acoustic emission signals(vibration modes)accompanied with the milling process to identify the desired chip shape and size range.Initial laboratory tests have been carried out to investigate and study the acoustic emission signals accompanying the casing milling process to identify the chip shapes and sizes.The preliminary test results show very good correlation and agreement between the chip length formed during those specific tests and the observed burst events in the measured signals.The study results have demonstrated the functionality of the new concept,and thus confirmed that it is a very promising idea towards developing a practical real time downhole monitoring system for milling operations.Adapting the milling operation parameters downhole in real time to keep the milling process within the desired generated chip shapes and sizes will offer better cleaning and removal of the chips and will prevent the development of chip nest around the drill string and its consequences such as round tripping,risk of drilling crew injury,none-productive time and even milling string stucking problems.展开更多
Rutting is one of the dominant pavement distresses, hence, the accuracy of rut depth measurements can have a substantial impact on the maintenance and rehabilitation （M 8： R） strategies and funding allocation. Diff...Rutting is one of the dominant pavement distresses, hence, the accuracy of rut depth measurements can have a substantial impact on the maintenance and rehabilitation （M 8： R） strategies and funding allocation. Different computation algorithms such as straight- edge method and wire line method, which are based on the same raw data, may lead to rut depth estimation which are not always consistent. Therefore, there is an urgent need to assess the impact of algorithm types on the accuracy of rut depth computation. In this paper, a 1B-point-based laser sensor detection technology, commonly accepted in China for rut depth measurements, was used to obtain a database of 85,000 field transverse profiles having three representative rutting shapes with small, medium and high severity rut levels. Based on the reconstruction of real transverse profiles, the consequences from two different algorithms were compared. Results showed that there is a combined effect of rut depth and profile shape on the rut depth computation accuracy. As expected, the dif- ference between the results obtained with the two computation methods increases with deeper rutting sections： when the distress is above 15 mm （severe level）, the average dif- ference between the two computation methods is above 1.5 mm, normally, the wire line method provides larger results. The computation suggests that the rutting shapes have a minimal influence on the results. An in-depth analysis showed that the upheaval outside of the wheel path is a dominant shape factor which results in higher computation differences.展开更多
基金Project supported by the National Natural Science Foundation ofChina (No. 30671197)the Program for New Century ExcellentTalents in University (No. NCET-04-0524), China
文摘A novel approach for fruit shape detection in RGB space was proposed,which was based on fast level set and Chan-Vese model named as Modified Chan-Vese model(MCV) . This new algorithm is fast and suitable for fruit sorting because it does not need re-initializing. MCV has three advantages compared to the traditional methods. First,it provides a unified frame-work for detecting fruit shape boundary,and does not need any preprocessing even though the raw image is noisy or blurred. Second,if the fruit has different colors at the edges,it can detect perfect boundary. Third,it processed directly in color space without any transformations that may lose much information. The proposed method has been applied to fruit shape detection with promising result.
基金This work was jointly supported by the National Nature Science Foundation of China(Grant No.51275282)Major Basic Projects of the Shanghai Science and Technology Commission(Grant No.18JC1410402).
文摘Considering the spatial position and shape detection properties of the fiber Bragg grating(FBG)curve sensor used in the human body,the positioning accuracy of the FBG curve sensor plays a major role in the pre-diagnosis and treatment of diseases.We present a new type of shape-sensing catheter(diameter of 2.0 mm and length of 810 mm)that is integrated with an array of four optical fibers,where each contains five nodes,to track the shape.Firstly,the distribution of the four orthogonal fiber gratings is wound around a nitinol wire using novel packaging technology,and the spatial curve shape is rebuilt based on the positioning of discrete points in space.An experimental platform is built,and then a reconstruction algorithm for coordinate point fitting of the Frenet frame is used to perform the reconstruction experiment on millimeter paper.The results show that,compared with those in previous studies,in 2D test,the maximum relative error for the end position is reduced to 2.74%,and in 3D reconstruction experiment,the maximum shape error is 3.43%,which verifies both the applicability of the sensor and the feasibility of the proposed method.The results reported here will provide an academic foundation and the key technologies required for navigation and positioning of noninvasive and minimally invasive surgical robots,intelligent structural health detection,and search and rescue operations in debris.
基金supported by the Research Grants Council of the Hong Kong Special Administrative Region,under the RGC General Research Fund(Project No.CUHK 14217516)
文摘Shape matching plays an important role in various computer vision and graphics applications such as shape retrieval, object detection, image editing,image retrieval, etc. However, detecting shapes in cluttered images is still quite challenging due to the incomplete edges and changing perspective. In this paper, we propose a novel approach that can efficiently identify a queried shape in a cluttered image. The core idea is to acquire the transformation from the queried shape to the cluttered image by summarising all pointto-point transformations between the queried shape and the image. To do so, we adopt a point-based shape descriptor, the pyramid of arc-length descriptor(PAD),to identify point pairs between the queried shape and the image having similar local shapes. We further calculate the transformations between the identified point pairs based on PAD. Finally, we summarise all transformations in a 4 D transformation histogram and search for the main cluster. Our method can handle both closed shapes and open curves, and is resistant to partial occlusions. Experiments show that our method can robustly detect shapes in images in the presence of partial occlusions, fragile edges, and cluttered backgrounds.
基金The Natural Science Fundation of Education Department of Anhui Province(No.KJ2012B051)
文摘The damage or loss of urban road manhole covers may cause great risk to residents＇ lives and property if they cannot be discovered in time. Most existing research recommendations for solving this problem are difficult to implement. This paper proposes an algorithm that combines the improved Hough transform and image comparison to identify the damage or loss of the manhole covers in complicated surface conditions by using existing urban road video images. Focusing on the pre-processed images, the edge contour tracking algorithm is applied to find all of the edges. Then with the improved Hough transformation, color recognition and image matching algorithm, the manhole cover area is found and the change rates of the manhole cover area are calculated. Based on the threshold of the change rates, it can be determined whether there is potential damage or loss in the manhole cover. Compared with the traditional Hough transform, the proposed method can effectively improve the processing speed and reduce invalid sampling and accumulation. Experimental results indicate that the proposed algorithm has the functions of effective positioning and early warning in the conditions of complex background, different perspectives, and different videoing time and conditions, such as when the target is partially covered.
基金Foundation item: Project(2009AA04Z143) supported by the National High Technology Research and Development Program of ChinaProject (E2011203004) supported by Natural Science Foundation of Hebei Province, ChinaProjects(2011BAF15B03, 2011BAF15B02) supported by the National Science Plan of China
文摘A high-precision shape detecting system of cold rolling strip is developed to meet industrial application, which mainly consists of the shape detecting roller, the collecting ring, the digital signal processing （DSP） shape signal processing board and the shape control model. Based on the shape detecting principle, the shape detecting roller is designed with a new integral structure for improving the precision of shape detecting and avoiding scratching strip surface. Based on the DSP technology, the DSP shape signal processing circuit board is designed and embedded in the shape detecting system for the reliability and stability of shape signal processing. The shape detecting system was successfully used in Angang 1 250 mm HC 6-high reversible cold rolling mill. The precision of shape detecting is 0.2 I and the shape deviation is controlled within 6 1 after the close loop shape control is input.
基金Item Sponsored by National Science and Technology Support Plan of China(2007BAF02B10)Natural Science Foundation of Hebei Province of China(E2011203004)
文摘In specific condition, when wrapping angle of cold rolling strip covering surface of shape detecting roll dynamically changes, online radial compression of the shape detecting roll is changed too, and it seriously affects online shape detecting precision of cold strip. Based on the latest intelligent shape meter developed by Yanshan University, using PSO-BP neural network and actual working condition datum, the cold strip online dynamic wrapping angle compensation model is established, and successfully applied in 1250 mm 6-high cold mill, remarkable results are achieved. The error between calculated values and measured values of total tensions is within 3 %
文摘Deep boreholes are secured by steel tubes(casings)which are run in the hole and cemented in place.In most cases,these casings are considered a permanent installation.However,sometimes they have to be removed in order to repair or abandon the well.As the casing is cemented in place,it cannot be pulled,but needs to be milled to small chips which are flushed out of the borehole by the drilling mud.One of the main challenges in casing milling operations is continuous and complete chip removal.If the metal chips are too long,chip nests will grow around the milling string.As a result,this will restrict the annulus flow area and affect the chip removal in boreholes.The obvious solution in such condition is to do round tripping and clean the chip nest which is associated with the risk of injuries,as well as,increasing the none-productive time.In the worst case,the poor cleaning and circulation of chips can even end up with the milling string stucking problem in boreholes,consequently long-time fishing job.According to the available literatures,hardly any study for identifying the chip shapes and accordingly adapting the operation parameters to the casing milling process environment downhole to keep milling within desired generated chip shapes and sizes could be found.This paper presents an encouraging idea to monitor the milling process in real time by utilizing the acoustic emission signals(vibration modes)accompanied with the milling process to identify the desired chip shape and size range.Initial laboratory tests have been carried out to investigate and study the acoustic emission signals accompanying the casing milling process to identify the chip shapes and sizes.The preliminary test results show very good correlation and agreement between the chip length formed during those specific tests and the observed burst events in the measured signals.The study results have demonstrated the functionality of the new concept,and thus confirmed that it is a very promising idea towards developing a practical real time downhole monitoring system for milling operations.Adapting the milling operation parameters downhole in real time to keep the milling process within the desired generated chip shapes and sizes will offer better cleaning and removal of the chips and will prevent the development of chip nest around the drill string and its consequences such as round tripping,risk of drilling crew injury,none-productive time and even milling string stucking problems.
基金sponsored by China Postdoctoral Science Foundation(2014M562287)National Natural Science Foundation of China(51508034,51408083,51508064)
文摘Rutting is one of the dominant pavement distresses, hence, the accuracy of rut depth measurements can have a substantial impact on the maintenance and rehabilitation （M 8： R） strategies and funding allocation. Different computation algorithms such as straight- edge method and wire line method, which are based on the same raw data, may lead to rut depth estimation which are not always consistent. Therefore, there is an urgent need to assess the impact of algorithm types on the accuracy of rut depth computation. In this paper, a 1B-point-based laser sensor detection technology, commonly accepted in China for rut depth measurements, was used to obtain a database of 85,000 field transverse profiles having three representative rutting shapes with small, medium and high severity rut levels. Based on the reconstruction of real transverse profiles, the consequences from two different algorithms were compared. Results showed that there is a combined effect of rut depth and profile shape on the rut depth computation accuracy. As expected, the dif- ference between the results obtained with the two computation methods increases with deeper rutting sections： when the distress is above 15 mm （severe level）, the average dif- ference between the two computation methods is above 1.5 mm, normally, the wire line method provides larger results. The computation suggests that the rutting shapes have a minimal influence on the results. An in-depth analysis showed that the upheaval outside of the wheel path is a dominant shape factor which results in higher computation differences.
