Hand gesture recognition is a popular topic in computer vision and makes human-computer interaction more flexible and convenient.The representation of hand gestures is critical for recognition.In this paper,we propose...Hand gesture recognition is a popular topic in computer vision and makes human-computer interaction more flexible and convenient.The representation of hand gestures is critical for recognition.In this paper,we propose a new method to measure the similarity between hand gestures and exploit it for hand gesture recognition.The depth maps of hand gestures captured via the Kinect sensors are used in our method,where the 3D hand shapes can be segmented from the cluttered backgrounds.To extract the pattern of salient 3D shape features,we propose a new descriptor-3D Shape Context,for 3D hand gesture representation.The 3D Shape Context information of each 3D point is obtained in multiple scales because both local shape context and global shape distribution are necessary for recognition.The description of all the 3D points constructs the hand gesture representation,and hand gesture recognition is explored via dynamic time warping algorithm.Extensive experiments are conducted on multiple benchmark datasets.The experimental results verify that the proposed method is robust to noise,articulated variations,and rigid transformations.Our method outperforms state-of-the-art methods in the comparisons of accuracy and efficiency.展开更多
Time-encoded imaging is useful for identifying potential special nuclear materials and other radioactive sources at a distance.In this study,a large field-of-view time-encoded imager was developed for gamma-ray and ne...Time-encoded imaging is useful for identifying potential special nuclear materials and other radioactive sources at a distance.In this study,a large field-of-view time-encoded imager was developed for gamma-ray and neutron source hotspot imaging based on a depth-of-interaction(DOI)detector.The imager primarily consists of a DOI detector system and a rotary dual-layer cylindrical coded mask.An EJ276 plastic scintillator coupled with two SiPMs was designed as the DOI detector to increase the field of view and improve the imager performance.The difference in signal time at both ends and the log of the signal amplitude ratio were used to calculate the interaction position resolution.The position resolution of the DOI detector was calibrated using a collimated Cs-137 source,and the full width at half maximum of the reconstruction position of the Gaussian fitting curve was approximately 4.4 cm.The DOI detector can be arbitrarily divided into several units to independently reconstruct the source distribution images.The unit length was optimized via Am-Be source-location experiments.A multidetector filtering method is proposed for image denoising.This method can effectively reduce image noise caused by poor DOI detector position resolution.The vertical field of view of the imager was(-55°,55°)when the detector was placed in the center of the coded mask.A DT neutron source at 20 m standoff could be located within 2400 s with an angular resolution of 3.5°.展开更多
Purpose Coded aperture imaging was a widely used imaging method for radiation sources.However,the traditional gamma camera based on two-dimensional projection information for coded aperture imaging ignored the influen...Purpose Coded aperture imaging was a widely used imaging method for radiation sources.However,the traditional gamma camera based on two-dimensional projection information for coded aperture imaging ignored the influence of the interaction depth of particles and detectors on the projection information,which reduced the imaging quality of the camera to some extent.Therefore,a method of correcting the coded gamma camera based on the interaction depth of particles and detectors is proposed to improve the location accuracy of detectors.Methods The camera developed in this work uses a 7×7 YSO crystal array coupled with two 7×7 Si-PM arrays.The crystal is evenly divided into 11 parts in the depth direction,with a voxel size of 3×3×3 mm3.The coded mask is a 13×13 array,which is a mosaic of two cycles of 7×7 modified uniformly redundant array mask.The depth resolution of the detector is obtained via the subsurface laser engraving dual-end readout method.After obtaining the three-dimensional position information of the interaction point the projection information obtained by the detector is layered,and the image is reconstructed.According to the spatial position information of the detector and the coded mask,the corresponding field of view of each layer of the detector is calculated,and the reconstructed image of each layer is amplified and superimposed according to the ratio of the field of view to obtain the reconstructed image combined with the depth information.Results and conclusion According to Monte Carlo simulation and radiation source imaging experiment results,this method can effectively improve the positioning ability of the detector.For the experimental scenario mentioned in the paper,the location accuracy can be improved by up to 1.54°.展开更多
基金supported by the National Natural Science Foundation of China(61773272,61976191)the Six Talent Peaks Project of Jiangsu Province,China(XYDXX-053)Suzhou Research Project of Technical Innovation,Jiangsu,China(SYG201711)。
文摘Hand gesture recognition is a popular topic in computer vision and makes human-computer interaction more flexible and convenient.The representation of hand gestures is critical for recognition.In this paper,we propose a new method to measure the similarity between hand gestures and exploit it for hand gesture recognition.The depth maps of hand gestures captured via the Kinect sensors are used in our method,where the 3D hand shapes can be segmented from the cluttered backgrounds.To extract the pattern of salient 3D shape features,we propose a new descriptor-3D Shape Context,for 3D hand gesture representation.The 3D Shape Context information of each 3D point is obtained in multiple scales because both local shape context and global shape distribution are necessary for recognition.The description of all the 3D points constructs the hand gesture representation,and hand gesture recognition is explored via dynamic time warping algorithm.Extensive experiments are conducted on multiple benchmark datasets.The experimental results verify that the proposed method is robust to noise,articulated variations,and rigid transformations.Our method outperforms state-of-the-art methods in the comparisons of accuracy and efficiency.
基金supported by the National Natural Science Foundation of China(Nos.11975121,12205131)the Fundamental Research Funds for the Central Universities(No.lzujbky-2021-sp58)the Postgraduate Research&Practice Innovation Program of Jiangsu Province(No.KYCX22_0354)。
文摘Time-encoded imaging is useful for identifying potential special nuclear materials and other radioactive sources at a distance.In this study,a large field-of-view time-encoded imager was developed for gamma-ray and neutron source hotspot imaging based on a depth-of-interaction(DOI)detector.The imager primarily consists of a DOI detector system and a rotary dual-layer cylindrical coded mask.An EJ276 plastic scintillator coupled with two SiPMs was designed as the DOI detector to increase the field of view and improve the imager performance.The difference in signal time at both ends and the log of the signal amplitude ratio were used to calculate the interaction position resolution.The position resolution of the DOI detector was calibrated using a collimated Cs-137 source,and the full width at half maximum of the reconstruction position of the Gaussian fitting curve was approximately 4.4 cm.The DOI detector can be arbitrarily divided into several units to independently reconstruct the source distribution images.The unit length was optimized via Am-Be source-location experiments.A multidetector filtering method is proposed for image denoising.This method can effectively reduce image noise caused by poor DOI detector position resolution.The vertical field of view of the imager was(-55°,55°)when the detector was placed in the center of the coded mask.A DT neutron source at 20 m standoff could be located within 2400 s with an angular resolution of 3.5°.
基金supported by the National Natural Science Foundation of China under Grant Nos.12005234 and 12105307.
文摘Purpose Coded aperture imaging was a widely used imaging method for radiation sources.However,the traditional gamma camera based on two-dimensional projection information for coded aperture imaging ignored the influence of the interaction depth of particles and detectors on the projection information,which reduced the imaging quality of the camera to some extent.Therefore,a method of correcting the coded gamma camera based on the interaction depth of particles and detectors is proposed to improve the location accuracy of detectors.Methods The camera developed in this work uses a 7×7 YSO crystal array coupled with two 7×7 Si-PM arrays.The crystal is evenly divided into 11 parts in the depth direction,with a voxel size of 3×3×3 mm3.The coded mask is a 13×13 array,which is a mosaic of two cycles of 7×7 modified uniformly redundant array mask.The depth resolution of the detector is obtained via the subsurface laser engraving dual-end readout method.After obtaining the three-dimensional position information of the interaction point the projection information obtained by the detector is layered,and the image is reconstructed.According to the spatial position information of the detector and the coded mask,the corresponding field of view of each layer of the detector is calculated,and the reconstructed image of each layer is amplified and superimposed according to the ratio of the field of view to obtain the reconstructed image combined with the depth information.Results and conclusion According to Monte Carlo simulation and radiation source imaging experiment results,this method can effectively improve the positioning ability of the detector.For the experimental scenario mentioned in the paper,the location accuracy can be improved by up to 1.54°.
