Search

Due to several complex factors such as the type, size, and shape of target object, vision-assisted robot grasping technology still faces serious challenges. In this research, a deep learning-based robot hand vision grasping algorithm was developed considering semi-structural environmental constraints. The proposed algorithm could build a deep learning network on the basis of the desired object, perform object recognition, category classification and position judgment, and complete robot hand-grasping tasks. The obtained experimental results demonstrated that the proposed algorithm effectively solved the problem of recognizing and classifying multi-category objects in a semi-structured environment, improving recognition rate and grasping rate and reducing collision rate. [ABSTRACT FROM AUTHOR]

In this research, a 3D visual recognition system has been developed based on Wei deep learning algorithm using GPU. The proposed system consisted of a GPU with depth image function library, which performed image data acquisition, depth information operation, coordinate conversion, image contour search, convolutional class neural network model training, etc., and achieved object pinning by TCP/IP communication with motion control system. The obtained experimental results revealed that the recognition rate of the developed algorithm for target objects at different positions was as high as 92%. Experimental target recognition rates for different angles were relatively low, but reached 87%, and experimental accuracy rates of different luminance values also reached 89%. The errors of robot hand clamping targets also fell within 1–4 mm, which were higher than experimental expectation. [ABSTRACT FROM AUTHOR]

We prove various sharp bounds for the anisotropic p -capacity Cap F , p (K) (1 < p < n) of compact sets K in the Euclidean space R n (n ≥ 2). Our results are mainly the anisotropic generalizations of some isotropic ones in [Ludwig, Xiao, Zhang, Math. Ann. 2011], [Xiao, Ann. Henri Poincaré 2016], [Xiao, Adv. Math. 2017] and [Xiao, Adv. Geom. 2017]. Key ingredients in the proofs include the inverse anisotropic mean curvature flow (IAMCF), the anisotropic Hawking mass and its monotonicity property along IAMCF for certain surfaces, and the anisotropic isocapacitary inequality. [ABSTRACT FROM AUTHOR]

We consider an |$n$| -dimensional smooth Riemannian manifold |$M^n=[0,R)\times \mathbb{S}^{n-1}$| endowed with a warped product metric |$g=dr^2+h^2(r)g_{\mathbb{S}^{n-1}}$| and diffeomorphic to a Euclidean ball. Suppose that |$M$| has strictly convex boundary. First, for the classical Steklov eigenvalue problem, we derive an optimal lower (upper, respectively) bound for its eigenvalue gaps in terms of |$h^{\prime}(R)/h(R)$| when |$n\geq 2$| and |$Ric_g\geq 0$| (⁠|$\leq 0$|⁠ , respectively). Second, in the same spirit, for two 4th-order Steklov eigenvalue problems studied by Kuttler and Sigillito in 1968, we deduce an optimal lower bound for their eigenvalue gaps in terms of either |$h^{\prime}(R)/h^3(R)$| or |$h^{\prime}(R)/h(R)$| when |$n=2$| and the Gaussian curvature is nonnegative. We also consider optimal estimates on the eigenvalue ratios for these eigenvalue problems. [ABSTRACT FROM AUTHOR]

We derive estimates relating the values of a solution at any two points to the distance between the points, for quasilinear isotropic elliptic equations on compact Riemannian manifolds, depending only on dimension and a lower bound for the Ricci curvature. These estimates imply sharp gradient bounds relating the gradient of an arbitrary solution at given height to that of a symmetric solution on a warped product model space. We also discuss the problem on Finsler manifolds with nonnegative weighted Ricci curvature, and on complete manifolds with bounded geometry, including solutions on manifolds with boundary with Dirichlet boundary condition. Particular cases of our results include gradient estimates of Modica type. [ABSTRACT FROM AUTHOR]

Abstract We prove that in Riemannian manifolds the k -th Steklov eigenvalue on a domain and the square root of the k -th Laplacian eigenvalue on its boundary can be mutually controlled in terms of the maximum principal curvature of the boundary under sectional curvature conditions. As an application, we derive a Weyl-type upper bound for Steklov eigenvalues. A Pohozaev-type identity for harmonic functions on the domain and the min–max variational characterization of both eigenvalues are important ingredients. [ABSTRACT FROM AUTHOR]

Let M be an n -dimensional compact connected manifold with boundary, κ > 0 a constant and 1 ≤ q ≤ n − 1 an integer. We prove that M supports a Riemannian metric with the interior q -curvature K q ≥ − q κ 2 and the boundary q -curvature Λ q ≥ q κ , if and only if M has the homotopy type of a CW complex with a finite number of cells with dimension ≤ (q − 1). Moreover, any Riemannian manifold M with sectional curvature K ≥ − κ 2 and boundary principal curvature Λ ≥ κ is diffeomorphic to the standard closed n -ball. [ABSTRACT FROM AUTHOR]

In the first part we derive sharp upper bounds of Reilly type for three kinds of eigenvalues in product manifolds R k × M n + 1 − k for any complete Riemannian manifold M . The eigenvalues include the first Laplacian eigenvalue on mean convex closed hypersurfaces, the first Steklov eigenvalue on domains with mean convex boundary, and the first Hodge Laplacian eigenvalue on closed hypersurfaces with certain convexity condition. In the second part, we prove a comparison result between the first Steklov eigenvalue of a strip domain in space forms and that of the corresponding warped product manifold. [ABSTRACT FROM AUTHOR]

We introduce capillary hypersurfaces and its stability in a manifold with density. We prove that stable -minimal hypersurfaces with free boundary in a geodesic ball in space form with suitable radial density must be totally geodesic. We also prove two criteria for instability of the capillary hypersurfaces in a Euclidean ball with suitable density. At last, we obtain a topological restriction on strongly stable capillary surfaces in a 3-manifold with density under certain conditions. These results generalize those in a manifold with constant density. [ABSTRACT FROM AUTHOR]

In this short note we obtain some gradient estimates for the positive solution to the doubly nonlinear diffusion equation on closed Riemannian manifold with Ricci curvature bounded below by a non-positive constant. As applications, we also derive corresponding Harnack inequalities. [ABSTRACT FROM AUTHOR]

This paper is concerned with the fully nonlinear equation σ 2 ( g ) = a σ 1 ( g ) + b . The first result is to obtain the entire solutions of the equation for conformally flat metric on R n under some additional assumptions, which generalizes the famous result of Chang–Gursky–Yang in [3] . The second one is to classify compact locally conformally flat manifolds with nonnegative Ricci curvature and the metric g satisfying the equation. [ABSTRACT FROM AUTHOR]

Given a smooth positive function F ∈ C ∞ (S n) such that the square of its positive 1-homogeneous extension on R n + 1 ∖ { 0 } is uniformly convex, the Wulff shape W F is a smooth uniformly convex body in the Euclidean space R n + 1 with F being the support function of the boundary ∂ W F . In this paper, we introduce the fully nonlinear locally constrained anisotropic curvature flow ∂ ∂ t X = (1 − E k 1 / k σ F) ν F , k = 2 , ... , n in the Euclidean space, where E k denotes the normalized k th anisotropic mean curvature with respect to the Wulff shape W F , σ F the anisotropic support function and ν F the outward anisotropic unit normal of the evolving hypersurface. We show that starting from a smooth, closed and strictly convex hypersurface in R n + 1 (n ≥ 2), the smooth solution of the flow exists for all positive time and converges smoothly and exponentially to a scaled Wulff shape. A nice feature of this flow is that it improves a certain isoperimetric ratio. Therefore by the smooth convergence of the above flow, we provide a new proof of a class of the Alexandrov–Fenchel inequalities for anisotropic mixed volumes of smooth convex domains in the Euclidean space. [ABSTRACT FROM AUTHOR]

The intelligent machine vision technology based on man-machine interaction mode has the advantages of weak intrusion, low adhesion and no device binding. With the development and progress of science and technology, the intelligent machine vision technology has become one of the most important directions in the field of human–computer interaction. Compared with the traditional interactive mode, the intelligent machine vision interaction technology is quite convenient, and the existence of these problems can also influence the vision of the intelligent machine to a certain extent. And the wide application of the sense interaction. At present, the operation precision is the main basis of the machine vision interaction design. Therefore, this paper studies the precision of the visual interaction of the intelligent machine. In this paper, three point-to-click experiments will be carried out on the basis of the Fitts' Law. The accuracy of the machine vision algorithm is experimentally studied from the operating direction, the mapping scale equation and the machine vision algorithm, and a reasonable suggestion is made for the intelligent machine vision interactive design of the human interaction mode. [ABSTRACT FROM AUTHOR]

It is difficult to adapt to the actual situation of the production and testing of the rivets by examining the defects of low working efficiency and low accuracy. In order to solve this defect, through a series of research and analysis, it can be found that the non-contact automatic inspection method can solve the existing defects. The OSTU operation method is improved and used for the image segmentation of the rivets, which can reduce the error segmentation. In order to eliminate the uncertainty of the rivet position, the method of the least external rectangle method is obtained to determine the main shaft of the rivet. This approach reduces randomness at work. Through the study of rivet contour curvature method to analyze the characteristics of the part of the rivet contour, can better reduce in proportion of noise in the process of operation, and has a lot of improvement for accurate precision. Through experiment that this method of testing with high accuracy, errors generated during inspection situation is less, and less affected when testing can improve the efficiency of detection in industrial production, can well meet the demands of rivet real-time inspection. [ABSTRACT FROM AUTHOR]

In this paper, we consider the closed embedded hypersurface Σ in the warped product manifold equipped with the metric g = dr2 + λ(r)2 gN. We give some characterizations of slice {r} × N by the condition that Σ has constant weighted higher-order mean curvatures (λ′)αpk, or constant weighted higher-order mean curvature ratio (λ′)αpk/p1, which generalize Brendle's [Constant mean curvature surfaces in warped product manifolds, Publ. Math. Inst. Hautes Études Sci. 117 (2013) 247-269] and Brendle-Eichmair's [Isoperimetric and Weingarten surfaces in the Schwarzschild manifold, J. Differential Geom. 94(3) (2013) 387-407] results. In particular, we show that the assumption convex of Brendle-Eichmair's result [Isoperimetric and Weingarten surfaces in the Schwarzschild manifold, J. Differential Geom. 94(3) (2013) 387-407] is unnecessary. Here pk is the kth normalized mean curvature of the hypersurface Σ. As a special case, we also give some characterizations of geodesic spheres in ℝn, ℍn and , which generalize the classical Alexandrov-type results. [ABSTRACT FROM AUTHOR]

Abstract: In this paper, we use the inverse curvature flow to prove a sharp geometric inequality on star-shaped and two-convex hypersurface in hyperbolic space. [Copyright &y& Elsevier]

In the production process of lithium battery, the quality inspection requirements of lithium battery are very high. At present, most of the work is done manually. Aiming at the problem of large manual inspection workload and large error, the robot visual inspection technology is applied to the production of lithium battery. In recent years, with the rapid development and progress of science and technology, the rapid development of visual detection hardware and algorithms, making it possible to screen defective products through visual detection algorithms. This paper takes lithium battery as the research object, and studies its vision detection algorithm. As a common commodity, the quality of lithium battery is the key for users to choose. With the increasing requirements of users for battery quality, how to produce high-quality battery is the key problem to be solved by manufacturers. However, at present, the defects of battery surface are mostly carried out manually. There are low efficiency and low detection rate in the process of manual detection. In this paper, the visual detection algorithm is studied to detect the defects such as pits, rust marks and broken skin on the surface of lithium battery, specifically to design the imaging experimental platform of lithium battery; use different lighting schemes to design different battery positioning and extraction algorithms; use Hough detection method to locate the battery surface, and design the battery defect algorithm for this, and compare the algorithm through experiments. [ABSTRACT FROM AUTHOR]

In the production process of lithium battery, the quality inspection requirements of lithium battery are very high. At present, most of the work is done manually. Aiming at the problem of large manual inspection workload and large error, the robot visual inspection technology is applied to the production of lithium battery. In recent years, with the rapid development and progress of science and technology, the rapid development of visual detection hardware and algorithms, making it possible to screen defective products through visual detection algorithms. This paper takes lithium battery as the research object, and studies its vision detection algorithm. As a common commodity, the quality of lithium battery is the key for users to choose. With the increasing requirements of users for battery quality, how to produce high-quality battery is the key problem to be solved by manufacturers. However, at present, the defects of battery surface are mostly carried out manually. There are low efficiency and low detection rate in the process of manual detection. In this paper, the visual detection algorithm is studied to detect the defects such as pits, rust marks and broken skin on the surface of lithium battery, specifically to design the imaging experimental platform of lithium battery; use different lighting schemes to design different battery positioning and extraction algorithms; use Hough detection method to locate the battery surface, and design the battery defect algorithm for this, and compare the algorithm through experiments. [ABSTRACT FROM AUTHOR]

In recent years, with the aggravation of environmental pollution, relying on the traditional detection of environmental pollution has been unable to meet the current requirements for the environment, the use of advanced technology to detect environmental pollution has become crucial. In order to meet the requirements of today's era, with the rapid development of image recognition technology, it is necessary to study how to apply it to environmental pollution detection. The image recognition technology based on embedded technology has the characteristics of high discrimination, high acceptability and strong touch sense. It is of great significance for environmental monitoring to make full use of image recognition technology. Image recognition technology is to capture the same environment by digital camera, and then store the obtained image by computer. The HSI model is used to quantify the stored photos, and the variance of the gradient function is used to form photos and images with different levels of clarity, so as to analyze the environmental pollution according to the quantified results. In this paper, the ambient air quality is taken as the research object, and HSI model is used to quantify, so as to analyze the correlation of air detection results. [ABSTRACT FROM AUTHOR]

• To detect and identify the commutator surface defect method is proposed. • Initially proposes the deep separable convolutions and residual networks using a separate residual module. • Better to apply in real-time detection and recognition of commutator surface defects. With low accuracy and poor efficiency, the manual and traditional detection of commutator surface defects cannot meet efficiency and timeliness requirements. Thus, a method is proposed to detect and identify commutator surface defects. YOLOv3 target detection is applied to commutator surface defect detection and recognition, and the model size and parameter number are reduced without significantly reducing detection accuracy. First, this paper proposes a separable residual module based on deep separable convolutions and residual networks. A network with shallower layers and fewer channels is designed for quick detection and recognition of commutator surface defects. Finally, the algorithm herein is evaluated on SD_data. The experimental results indicate that while maintaining good accuracy, this method has a smaller model size, fewer parameters and faster running time than the YOLOv3 network. Moreover, accuracy is improved to a certain extent compared to the current commutator surface defect detection methods, so it can be better applied to real-time detection and recognition of commutator surface defects. [ABSTRACT FROM AUTHOR]