This paper presents a type of special Dual-Status spring parameter inspection method which is in assembly line. In order to measure contour parameter, this paper designs the measurement course and illustrates method of image processing which carries on object location and contour parameter calculating of Dual-Status spring using Hough Transform. This method is proved to be useful and efficient in practice. This paper is innovative in four facts. First, Hough Transform is never used to measure Dual-Status spring contour parameter. Second, Hough Transform can work well no matter what the spring lies toward. Third, the method does not cause elastic deformation which is from artificial influence. Finally, it can be used to measure multi-kind of parts in the line. This method can be widely used in other similar applications.
We present a conceptually simple framework for 6DoF object pose estimation, especially for autonomous driving scenarios. Our approach can efficiently detect the traffic participants from a monocular RGB image while simultaneously regressing their 3D translation and rotation vectors. The proposed method 6D-VNet, extends the Mask R-CNN by adding customised heads for predicting vehicle's finer class, rotation and translation. It is trained end-to-end compared to previous methods. Furthermore, we show that the inclusion of translational regression in the joint losses is crucial for the 6DoF pose estimation task, where object translation distance along longitudinal axis varies significantly, e.g., in autonomous driving scenarios. Additionally, we incorporate the mutual information between traffic participants via a modified non-local block to capture the spatial dependencies among the detected objects. As opposed to the original non-local block implementation, the proposed weighting modification takes the spatial neighbouring information into consideration whilst counteracting the effect of extreme gradient values. We evaluate our method on the challenging real-world Pascal3D+ dataset and our 6D-VNet reaches the 1st place in ApolloScape challenge 3D Car Instance task (Apolloscape, 2018), (Huang et al., 2018).
Subspace methods have been successfully applied to face recognition tasks. It is well-studied in both unsupervised learning and supervised learning, such as Eigenface and Fisherface. In practice, besides abundant unlabeled examples, domain knowledge in the form of pairwise constraints is commonly available, which specifies whether a pair of instances belong to the same class or different classes. In this study, we propose a face recognition method based on semi-supervised locality preserving learning together with pairwise constraints and unlabeled data, called Semi-supervised Laplacianface (S-Laplacianface). It tries to preserve the local geometric structure of the face manifold as Laplacianface, also requires the subspace to satisfy the pairwise constraints defined by the user. Experimental results on two face databases demonstrate the effectiveness of proposed algorithm.
We present a conceptually simple framework for 6DoF object pose estimation, especially for autonomous driving scenario. Our approach efficiently detects traffic participants in a monocular RGB image while simultaneously regressing their 3D translation and rotation vectors. The method, called 6D-VNet, extends Mask R-CNN by adding customised heads for predicting vehicle's finer class, rotation and translation. The proposed 6D-VNet is trained end-to-end compared to previous methods. Furthermore, we show that the inclusion of translational regression in the joint losses is crucial for the 6DoF pose estimation task, where object translation distance along longitudinal axis varies significantly, e.g., in autonomous driving scenarios. Additionally, we incorporate the mutual information between traffic participants via a modified non-local block. As opposed to the original non-local block implementation, the proposed weighting modification takes the spatial neighbouring information into consideration whilst counteracting the effect of extreme gradient values. Our 6D-VNet reaches the 1 st place in ApolloScape challenge 3D Car Instance task. Code has been made available at: https://github.com/stevenwudi/6DVNET .
A new robust watermarking method, named QIM-NSGA-II, is proposed based on the non-dominated sorting genetic algorithm II (NSGA-II) and quantization index modulation (QIM). The NSGA-II algorithm is utilized to find out the optimal embedding position and adaptive quantization step for embedding watermark into a carrier image in the framework of QIM. In the process of searching an optimal solution, the trade-off between robustness and image fidelity of the watermarked image is represented by the Pareto-Front discovered by NSGA-II. Experiment results show that the proposed scheme has a good robustness against common attacks, such as amplitude scaling, noise, filtering, cropping, JPEG compression.
Abstract A new robust watermarking method, named SFLA-QIM, is proposed based on the shuffled frog leaping algorithm (SFLA) and quantization index modulation (QIM). The shuffled frog leaping algorithm is utilized to find out the optimal embedding position and adaptive quantization step for embedding watermark into a carrier image in the framework of QIM. A carefully chosen fitness function is designed in terms of the Peak Signal to Noise Ratio (PSNR) and the Normalized Correlation (NR) value to achieve high transparency and robustness. The proposed scheme is blind. Compared with other quantization index related watermarking methods, SFLA-QIM exhibits satisfactory robustness against a wide variety of attacks such as amplitude scaling, filtering, noise addition, cropping and JPEG compression.
'/%3e%3cuse xlink:href='%23a' transform='rotate(23.036 .093 25.536)'/%3e%3cuse xlink:href='%23a' transform='rotate(45.87 1.273 16.18)'/%3e%3cuse xlink:href='%23a' transform='rotate(69.945 .996 12.078)'/%3e%3cuse xlink:href='%23a' transform='rotate(20.66 -19.689 31.932)'/%3e%3c/svg%3e)