Fatigue cracks that develop in civil infrastructure such as steel bridges due to repetitive loads pose a major threat to structural integrity.Despite being the most common practice for fatigue crack detection,human vi...Fatigue cracks that develop in civil infrastructure such as steel bridges due to repetitive loads pose a major threat to structural integrity.Despite being the most common practice for fatigue crack detection,human visual inspection is known to be labor intensive,time-consuming,and prone to error.In this study,a computer vision-based fatigue crack detection approach using a short video recorded under live loads by a moving consumer-grade camera is presented.The method detects fatigue crack by tracking surface motion and identifies the differential motion pattern caused by opening and closing of the fatigue crack.However,the global motion introduced by a moving camera in the recorded video is typically far greater than the actual motion associated with fatigue crack opening/closing,leading to false detection results.To overcome the challenge,global motion compensation(GMC)techniques are introduced to compensate for camera-induced movement.In particular,hierarchical model-based motion estimation is adopted for 2D videos with simple geometry and a new method is developed by extending the bundled camera paths approach for 3D videos with complex geometry.The proposed methodology is validated using two laboratory test setups for both in-plane and out-of-plane fatigue cracks.The results confirm the importance of motion compensation for both 2D and 3D videos and demonstrate the effectiveness of the proposed GMC methods as well as the subsequent crack detection algorithm.展开更多
A new motion model and estimation algorithm is proposed to compute the general rigid motion object＇s 6-DOF motion parameters and center of rotation based on stereo vision. The object＇s 6-DOF motion model is designed...A new motion model and estimation algorithm is proposed to compute the general rigid motion object＇s 6-DOF motion parameters and center of rotation based on stereo vision. The object＇s 6-DOF motion model is designed from the rigid object＇s motion character under the two defined reference frames. According to the rigid object＇s motion model and motion dynamics knowledge, the corresponding motion algorithm to compute the 6-DOF motion parameters is worked out. By the rigid object pure rotation motion model and space sphere geometry knowledge, the center of rotation may be calculated after eliminating the translation motion out of the 6-DOF motion. The motion equations are educed based on the motion model and the closed-form solutions are figured out. To heighten the motion estimation algorithm＇s robust, RANSAC algorithm is applied to delete the outliers. Simulation and real experiments are conducted and the experiment results are analyzed. The results prove the motion model＇s correction and algorithm＇s validity.展开更多
After the analysis of the beauty contained in motion vision, the paper had pointed out that motion vision was the link for spectators relating and communicating with aesthetic objects and decided landscape space const...After the analysis of the beauty contained in motion vision, the paper had pointed out that motion vision was the link for spectators relating and communicating with aesthetic objects and decided landscape space construction sequence. It further analyzed the relations between architectural space and visual perception which could be divided into inner experience and external experience. By taking landscape space construction of Sichuan Olympic Sports School for example, based on the analysis of design principles and objective of landscape space, the paper had focused on the discussion of landscape concept in terms of motion vision. In the perspective of two-dimensional vision, landscape effects of White Pigeon Square and Bright Eyes Square had been introduced. In the perspective of three-dimensional vision, landscape effects of the Olympic Rings waterscape and the Olympic Rings gallery had been illustrated. Finally, based on the integration between landscapes and architectures under visual perception, the coordination between campus architectures and landscape construction in Olympic Sports School had been analyzed.展开更多
Motion time study is employed by manufacturing industries to determine operation time.An accurate estimate of operation time is crucial for effective process improvement and production planning.Traditional motion time...Motion time study is employed by manufacturing industries to determine operation time.An accurate estimate of operation time is crucial for effective process improvement and production planning.Traditional motion time study is conducted by human analysts with stopwatches,which may be exposed to human errors.In this paper,an automated time study model based on computer vision is proposed.The model integrates a convolutional neural network,which analyzes a video of a manual operation to classify work elements in each video frame,with a time study model that automatically estimates the work element times.An experiment is conducted using a grayscale video and a color video of a manual assembly operation.The work element times from the model are statistically compared to the reference work element time values.The result shows no statistical difference among the time data,which clearly demonstrates the effectiveness of the proposed model.展开更多
An object learning and recognition system is implemented for humanoid robots to discover and memorize objects only by simple interactions with non-expert users. When the object is presented, the system makes use of th...An object learning and recognition system is implemented for humanoid robots to discover and memorize objects only by simple interactions with non-expert users. When the object is presented, the system makes use of the motion information over consecutive frames to extract object features and implements machine learning based on the bag of visual words approach. Instead of using a local feature descriptor only, the proposed system uses the co-occurring local features in order to increase feature discriminative power for both object model learning and inference stages. For different objects with different textures, a hybrid sampling strategy is considered. This hybrid approach minimizes the consumption of computation resources and helps achieving good performances demonstrated on a set of a dozen different daily objects.展开更多
基金NCHRP Project,IDEA 223:Fatigue Crack Inspection using Computer Vision and Augmented Reality。
文摘Fatigue cracks that develop in civil infrastructure such as steel bridges due to repetitive loads pose a major threat to structural integrity.Despite being the most common practice for fatigue crack detection,human visual inspection is known to be labor intensive,time-consuming,and prone to error.In this study,a computer vision-based fatigue crack detection approach using a short video recorded under live loads by a moving consumer-grade camera is presented.The method detects fatigue crack by tracking surface motion and identifies the differential motion pattern caused by opening and closing of the fatigue crack.However,the global motion introduced by a moving camera in the recorded video is typically far greater than the actual motion associated with fatigue crack opening/closing,leading to false detection results.To overcome the challenge,global motion compensation(GMC)techniques are introduced to compensate for camera-induced movement.In particular,hierarchical model-based motion estimation is adopted for 2D videos with simple geometry and a new method is developed by extending the bundled camera paths approach for 3D videos with complex geometry.The proposed methodology is validated using two laboratory test setups for both in-plane and out-of-plane fatigue cracks.The results confirm the importance of motion compensation for both 2D and 3D videos and demonstrate the effectiveness of the proposed GMC methods as well as the subsequent crack detection algorithm.
基金National Natural Science Foundation of China (No.50275040)
文摘A new motion model and estimation algorithm is proposed to compute the general rigid motion object＇s 6-DOF motion parameters and center of rotation based on stereo vision. The object＇s 6-DOF motion model is designed from the rigid object＇s motion character under the two defined reference frames. According to the rigid object＇s motion model and motion dynamics knowledge, the corresponding motion algorithm to compute the 6-DOF motion parameters is worked out. By the rigid object pure rotation motion model and space sphere geometry knowledge, the center of rotation may be calculated after eliminating the translation motion out of the 6-DOF motion. The motion equations are educed based on the motion model and the closed-form solutions are figured out. To heighten the motion estimation algorithm＇s robust, RANSAC algorithm is applied to delete the outliers. Simulation and real experiments are conducted and the experiment results are analyzed. The results prove the motion model＇s correction and algorithm＇s validity.
文摘After the analysis of the beauty contained in motion vision, the paper had pointed out that motion vision was the link for spectators relating and communicating with aesthetic objects and decided landscape space construction sequence. It further analyzed the relations between architectural space and visual perception which could be divided into inner experience and external experience. By taking landscape space construction of Sichuan Olympic Sports School for example, based on the analysis of design principles and objective of landscape space, the paper had focused on the discussion of landscape concept in terms of motion vision. In the perspective of two-dimensional vision, landscape effects of White Pigeon Square and Bright Eyes Square had been introduced. In the perspective of three-dimensional vision, landscape effects of the Olympic Rings waterscape and the Olympic Rings gallery had been illustrated. Finally, based on the integration between landscapes and architectures under visual perception, the coordination between campus architectures and landscape construction in Olympic Sports School had been analyzed.
基金This work is jointly supported by the SIIT Young Researcher Grant,under a Contract No.SIIT 2019-YRG-WP01the Excellent Research Graduate Scholarship,under a Contract No.MOU-CO-2562-8675.
文摘Motion time study is employed by manufacturing industries to determine operation time.An accurate estimate of operation time is crucial for effective process improvement and production planning.Traditional motion time study is conducted by human analysts with stopwatches,which may be exposed to human errors.In this paper,an automated time study model based on computer vision is proposed.The model integrates a convolutional neural network,which analyzes a video of a manual operation to classify work elements in each video frame,with a time study model that automatically estimates the work element times.An experiment is conducted using a grayscale video and a color video of a manual assembly operation.The work element times from the model are statistically compared to the reference work element time values.The result shows no statistical difference among the time data,which clearly demonstrates the effectiveness of the proposed model.
基金The National Natural Science Foundation of China(No.60672094,60971098)
文摘An object learning and recognition system is implemented for humanoid robots to discover and memorize objects only by simple interactions with non-expert users. When the object is presented, the system makes use of the motion information over consecutive frames to extract object features and implements machine learning based on the bag of visual words approach. Instead of using a local feature descriptor only, the proposed system uses the co-occurring local features in order to increase feature discriminative power for both object model learning and inference stages. For different objects with different textures, a hybrid sampling strategy is considered. This hybrid approach minimizes the consumption of computation resources and helps achieving good performances demonstrated on a set of a dozen different daily objects.
