This paper proposed a novel multi-view interactive behavior recognition method based on local self-similarity descriptors and graph shared multi-task learning. First, we proposed the composite interactive feature repr...This paper proposed a novel multi-view interactive behavior recognition method based on local self-similarity descriptors and graph shared multi-task learning. First, we proposed the composite interactive feature representation which encodes both the spatial distribution of local motion of interest points and their contexts. Furthermore, local self-similarity descriptor represented by temporal-pyramid bag of words(BOW) was applied to decreasing the influence of observation angle change on recognition and retaining the temporal information. For the purpose of exploring latent correlation between different interactive behaviors from different views and retaining specific information of each behaviors, graph shared multi-task learning was used to learn the corresponding interactive behavior recognition model. Experiment results showed the effectiveness of the proposed method in comparison with other state-of-the-art methods on the public databases CASIA, i3Dpose dataset and self-built database for interactive behavior recognition.展开更多
Detecting the moving vehicles in jittering traffic scenes is a very difficult problem because of the complex environment.Only by the color features of the pixel or only by the texture features of image cannot establis...Detecting the moving vehicles in jittering traffic scenes is a very difficult problem because of the complex environment.Only by the color features of the pixel or only by the texture features of image cannot establish a suitable background model for the moving vehicles. In order to solve this problem, the Gaussian pyramid layered algorithm is proposed, combining with the advantages of the Codebook algorithm and the Local binary patterns(LBP) algorithm. Firstly, the image pyramid is established to eliminate the noises generated by the camera shake. Then, codebook model and LBP model are constructed on the low-resolution level and the high-resolution level of Gaussian pyramid, respectively. At last, the final test results are obtained through a set of operations according to the spatial relations of pixels. The experimental results show that this algorithm can not only eliminate the noises effectively, but also save the calculating time with high detection sensitivity and high detection accuracy.展开更多
Objective For computer-aided Chinese medical diagnosis and aiming at the problem of insufficient segmentation,a novel multi-level method based on the multi-scale fusion residual neural network(MF2ResU-Net)model is pro...Objective For computer-aided Chinese medical diagnosis and aiming at the problem of insufficient segmentation,a novel multi-level method based on the multi-scale fusion residual neural network(MF2ResU-Net)model is proposed.Methods To obtain refined features of retinal blood vessels,three cascade connected UNet networks are employed.To deal with the problem of difference between the parts of encoder and decoder,in MF2ResU-Net,shortcut connections are used to combine the encoder and decoder layers in the blocks.To refine the feature of segmentation,atrous spatial pyramid pooling(ASPP)is embedded to achieve multi-scale features for the final segmentation networks.Results The MF2ResU-Net was superior to the existing methods on the criteria of sensitivity(Sen),specificity(Spe),accuracy(ACC),and area under curve(AUC),the values of which are 0.8013 and 0.8102,0.9842 and 0.9809,0.9700 and 0.9776,and 0.9797 and 0.9837,respectively for DRIVE and CHASE DB1.The results of experiments demonstrated the effectiveness and robustness of the model in the segmentation of complex curvature and small blood vessels.Conclusion Based on residual connections and multi-feature fusion,the proposed method can obtain accurate segmentation of retinal blood vessels by refining the segmentation features,which can provide another diagnosis method for computer-aided Chinese medical diagnosis.展开更多
How to integrate and disseminate globally distributed multi-source and heterogeneous spatial information is an open problem in integration and sharing service of geographic information. Here we propose a new service a...How to integrate and disseminate globally distributed multi-source and heterogeneous spatial information is an open problem in integration and sharing service of geographic information. Here we propose a new service architecture suitable for integra- tion and sharing of distributed multi-source geographic information. We also propose a global virtual pyramid model, which can be applied in 3D virtual globes. In view of the difficulty of web multi-node geographic information sharing service, we propose a web multi-node service aggregation method, integrated in our autonomously developed virtual globe platform Geo- Globe and introduced in the National Platform for Common GeoSpatial Information Services named ＂T1ANDITU＂. It achieves 2D and 3D integration for geographic information service.展开更多
A novel method for multi-image matching by synthesizing image and object-space information is proposed. Firstly, four levels of image pyramids are generated according to the rule that the next pyramid level is generat...A novel method for multi-image matching by synthesizing image and object-space information is proposed. Firstly, four levels of image pyramids are generated according to the rule that the next pyramid level is generated from the previous level using the average gray values of the 3 by 3 pixels, and the first level of pyramid image is generated from the original image. The initial horizontal parallaxes between the reference image and each searching image are calculated at the highest level of the image pyramid. Secondly, corresponding image points are searched in each stereo image pair from the third level of image pyramid, and the matching results in all stereo pairs are integrated in the object space, by which the mismatched image points can be eliminated and more accurate spatial information can be obtained for the subsequent pyramid image matching. The matching method based on correlation coefficient with geometric constraints and global relaxation matching is introduced in the process of image matching. Finally, the feasibility of the method proposed in this paper is verified by the experiments using a set of digital frame aerial images with big overlap. Compared with the traditional image matching method with two images, the accuracy of the digital surface model (DSM) generated using the proposed method shows that the multiimage matching method can eliminate the mismatched points effectively and can improve the matching success rate significantly.展开更多
基金Project(51678075)supported by the National Natural Science Foundation of ChinaProject(2017GK2271)supported by Hunan Provincial Science and Technology Department,China
文摘This paper proposed a novel multi-view interactive behavior recognition method based on local self-similarity descriptors and graph shared multi-task learning. First, we proposed the composite interactive feature representation which encodes both the spatial distribution of local motion of interest points and their contexts. Furthermore, local self-similarity descriptor represented by temporal-pyramid bag of words(BOW) was applied to decreasing the influence of observation angle change on recognition and retaining the temporal information. For the purpose of exploring latent correlation between different interactive behaviors from different views and retaining specific information of each behaviors, graph shared multi-task learning was used to learn the corresponding interactive behavior recognition model. Experiment results showed the effectiveness of the proposed method in comparison with other state-of-the-art methods on the public databases CASIA, i3Dpose dataset and self-built database for interactive behavior recognition.
基金Project(61172047)supported by the National Natural Science Foundation of China
文摘Detecting the moving vehicles in jittering traffic scenes is a very difficult problem because of the complex environment.Only by the color features of the pixel or only by the texture features of image cannot establish a suitable background model for the moving vehicles. In order to solve this problem, the Gaussian pyramid layered algorithm is proposed, combining with the advantages of the Codebook algorithm and the Local binary patterns(LBP) algorithm. Firstly, the image pyramid is established to eliminate the noises generated by the camera shake. Then, codebook model and LBP model are constructed on the low-resolution level and the high-resolution level of Gaussian pyramid, respectively. At last, the final test results are obtained through a set of operations according to the spatial relations of pixels. The experimental results show that this algorithm can not only eliminate the noises effectively, but also save the calculating time with high detection sensitivity and high detection accuracy.
基金Key R&D Projects in Hebei Province(22370301D)Scientific Research Foundation of Hebei University for Distinguished Young Scholars(521100221081)Scientific Research Foundation of Colleges and Universities in Hebei Province(QN2022107)。
文摘Objective For computer-aided Chinese medical diagnosis and aiming at the problem of insufficient segmentation,a novel multi-level method based on the multi-scale fusion residual neural network(MF2ResU-Net)model is proposed.Methods To obtain refined features of retinal blood vessels,three cascade connected UNet networks are employed.To deal with the problem of difference between the parts of encoder and decoder,in MF2ResU-Net,shortcut connections are used to combine the encoder and decoder layers in the blocks.To refine the feature of segmentation,atrous spatial pyramid pooling(ASPP)is embedded to achieve multi-scale features for the final segmentation networks.Results The MF2ResU-Net was superior to the existing methods on the criteria of sensitivity(Sen),specificity(Spe),accuracy(ACC),and area under curve(AUC),the values of which are 0.8013 and 0.8102,0.9842 and 0.9809,0.9700 and 0.9776,and 0.9797 and 0.9837,respectively for DRIVE and CHASE DB1.The results of experiments demonstrated the effectiveness and robustness of the model in the segmentation of complex curvature and small blood vessels.Conclusion Based on residual connections and multi-feature fusion,the proposed method can obtain accurate segmentation of retinal blood vessels by refining the segmentation features,which can provide another diagnosis method for computer-aided Chinese medical diagnosis.
基金supported by the National Natural Science Foundation of China(Grant No.41023001)National Basic Research Program of China(Grant No.2012CB719906)Innovative Research Groups Supported Project of the National Natural Science Foundation of China(Grant No.41021061)
文摘How to integrate and disseminate globally distributed multi-source and heterogeneous spatial information is an open problem in integration and sharing service of geographic information. Here we propose a new service architecture suitable for integra- tion and sharing of distributed multi-source geographic information. We also propose a global virtual pyramid model, which can be applied in 3D virtual globes. In view of the difficulty of web multi-node geographic information sharing service, we propose a web multi-node service aggregation method, integrated in our autonomously developed virtual globe platform Geo- Globe and introduced in the National Platform for Common GeoSpatial Information Services named ＂T1ANDITU＂. It achieves 2D and 3D integration for geographic information service.
基金Supported by the National Natural Science Foundation of China (Nos. 40771176, 40721001)
文摘A novel method for multi-image matching by synthesizing image and object-space information is proposed. Firstly, four levels of image pyramids are generated according to the rule that the next pyramid level is generated from the previous level using the average gray values of the 3 by 3 pixels, and the first level of pyramid image is generated from the original image. The initial horizontal parallaxes between the reference image and each searching image are calculated at the highest level of the image pyramid. Secondly, corresponding image points are searched in each stereo image pair from the third level of image pyramid, and the matching results in all stereo pairs are integrated in the object space, by which the mismatched image points can be eliminated and more accurate spatial information can be obtained for the subsequent pyramid image matching. The matching method based on correlation coefficient with geometric constraints and global relaxation matching is introduced in the process of image matching. Finally, the feasibility of the method proposed in this paper is verified by the experiments using a set of digital frame aerial images with big overlap. Compared with the traditional image matching method with two images, the accuracy of the digital surface model (DSM) generated using the proposed method shows that the multiimage matching method can eliminate the mismatched points effectively and can improve the matching success rate significantly.
