Search

The traditional Siamese network based object tracking algorithms suffer from high computational complexity, making them difficult to run on embedded devices. Moreover, when faced with long-term tracking tasks, their success rates significantly decline. To address these issues, we propose a lightweight long-term object tracking algorithm called Meta-Master-based Ghost Fast Tracking (MGTtracker),which based on meta-learning. This algorithm integrates the Ghost mechanism to create a lightweight backbone network called G-ResNet, which accurately extracts target features while operating quickly. We design a tiny adaptive weighted fusion feature pyramid network (TiFPN) to enhance feature information fusion and mitigate interference from similar objects. We introduce a lightweight region regression network, the Ghost Decouple Net (GDNet) for target position prediction. Finally, we propose a meta-learning-based online template correction mechanism called Meta-Master to overcome error accumulation in long-term tracking tasks and the difficulty of reacquiring targets after loss. We evaluate the algorithm on public datasets OTB100, VOT2020, VOT2018LT, and LaSOT and deploy it for performance testing on Jetson Xavier NX. Experimental results demonstrate the effectiveness and superiority of the algorithm. Compared to existing classic object tracking algorithms, our approach achieves a faster running speed of 25 FPS on NX, and real-time correction enhances the algorithm's robustness. Although similar in accuracy and EAO metrics, our algorithm outperforms similar algorithms in speed and effectively addresses the issues of significant cumulative errors and easy target loss during tracking. Code is released at https://github.com/ygh96521/MGTtracker.git. [ABSTRACT FROM AUTHOR]

Acoustic target recognition for two-dimensional (2D) acoustic scatterers is investigated using the singularity expansion method (SEM). Based on the Watson transformation series of the scattering field, the SEM poles can be calculated and their physical interpretation given, along with the exact normal mode for any acoustic scattering problem. Typical oscillatory phenomena appear as a series of damped sinusoidal signals in the time domain and as a standing-wave distribution in the space. These external oscillation modes are associated with the SEM poles. We note that the positions of these poles in the complex frequency plane are uniquely determined by the shape and flexible characteristics of the target regardless of the waveforms and positions of the incident signals. We then infer that SEM poles can be used as the characteristic parameters for target shape recognition. The relationship between the positions of SEM poles and the geometrical characters of 2D scatterers has been established not only for cylinders but also for other general 2D scatterers. The new method and the related calculation results provide an effective way to perform shape recognition using an acoustic scattering field, with potential applications in non-destructive testing and acoustic imaging. [ABSTRACT FROM AUTHOR]

The radar cross section (RCS) is an important parameter that reflects the scattering characteristics of radar targets. Based on the monostatic radar RCS time series' statistical features by sliding window segmentation, a novel sliding window-statistical-gated recurrent unit (SW-S-GRU) method for radar target recognition (RTR) is proposed using a GRU. The sliding window method divides the RCS time series into many segments for obtaining the statistical features as the input of the GRU. The deeper features are extracted from the segmented time series and then classified by the GRU. Under the model of precession motion, simulation results show that the proposed method achieves a great recognition accuracy. Even under the condition of a low SNR, the proposed method can obtain better recognition accuracy. For the precession dataset, the effect of sliding window parameters on RTR is analysed. The simulation results show that the recognition result of the model is better using the longer series overlap length between adjacent times. And when the number of hidden layers is 8 or above 8, the recognition accuracy does not change. Using the publicly available measured drone RCS data, the proposed method can also identify the drone well. [ABSTRACT FROM AUTHOR]

Magnetic soft materials (MSMs) and magnetic shape memory polymers (MSMPs) have been some of the most intensely investigated newly developed material types in the last decade, thanks to the great and versatile potential of their innovative characteristic behaviors such as remote and nearly heatless shape transformation in the case of MSMs. With regard to a number of properties such as shape recovery ratio, manufacturability, cost or programming potential, MSMs and MSMPs may exceed conventional shape memory materials such as shape memory alloys or shape memory polymers. Nevertheless, MSMs and MSMPs have not yet fully touched their scientific-industrial potential, basically due to the lack of detailed knowledge on various aspects of their constitutive response. Therefore, MSMs and MSMPs have been developed slowly but their importance will undoubtedly increase in the near future. This review emphasizes the development of MSMs and MSMPs with a specific focus on the role of the magnetic particles which affect the shape memory recovery and programming behavior of these materials. In addition, the synthesis and application of these materials are addressed. [ABSTRACT FROM AUTHOR]

The classification and retrieval of 3D models have been widely used in the field of multimedia and computer vision. With the rapid development of computer graphics, different algorithms corresponding to different representations of 3D models have achieved the best performance. The advances in deep learning also encourage various deep models for 3D feature representation. For multi-view, point cloud, and PANORAMA-view, different models have shown significant performance on 3D shape classification. However, There's not a way to consider utilizing the fusion information of multi-modal for 3D shape classification. In our opinion, We propose a novel multi-modal information fusion method for 3D shape classification, which can fully utilize the advantage of different modal to predict the label of class. More specifically, the proposed can effectively fuse more modal information. it is easy to utilize in other similar applications. We have evaluated our framework on the popular dataset ModelNet40 for the classification task on 3D shape. Series experimental results and comparisons with state-of-the-art methods demonstrate the validity of our approach. [ABSTRACT FROM AUTHOR]

The existing deraining methods have obtained noteworthy improvements, but it is a challenging problem to extend the methods for complicated rain conditions where rain streaks exhibit different distribution densities, sizes, shapes , etc. The main challenges are the ability to fully explore and utilize the multi-scale context information of rain streaks that maintain both global structure completeness and local detail accurateness. To this end, this paper proposes an E xploring C ontext- G ated N etwork, known as ECG Net. To adequately explore the richer context information, the proposed method consists of two key elements: context-enhanced feature block (CEFB) and multi-scale-gated aggregation block (MGAB). Specifically, the various scale features can be captured by CEFB with the multi-scale operation, to better remove the rain streaks and effectively restore the local detail textures. Subsequently, the captured features from different spaces are sent to MGAB, to aggregate and transmit these different scale features from the encoder to the decoder and reduce the transmission loss of information. Massive experiments on the commonly used benchmarks have demonstrated that the proposed method obtains more appealing performances against other competitive methods. • Capturing multi-scale features and enhancing contextual information, obtaining local modeling and long-range dependency. • Gated aggregation information from different levels, reducing redundant features and loss of informational transmission. • Better rain streaks removal and recovering image details and textures. [ABSTRACT FROM AUTHOR]

• Engagement of octagonal lattice-based triangulated feature characterization, which is the first of its kind. • The inherent congruency of the geometrical arrangement makes the descriptor robust to numerous image transformations. • The nature of the second-order derivatives capture keenly high-frequency information such as edges, corners, and points. • Thorough investigations on benchmark shape datasets demonstrate the contribution's superiority. • Complexity analysis reveals the simplicity of the OLTT model signifying its compatibility with real scenarios. Erstwhile shape description schemes lack primarily in establishing trade-offs with accuracy and computational load. Accordingly, a lightweight shape descriptor offering precise definition and compaction of high-frequency features is contributed in this paper using a simple geometrical shape for localization and shape characterization. Initially, the input image is octagonally tessellated and triangularly decomposed into sub-regions whose side-wise differences are evaluated and subjected to second-order differentiation to produce three high-frequency values representing triangle corners. The resultant is processed by the law of sines to yield localized shape features exhibiting congruence and is reiterated on the residual regions, followed by a novel octal encoding scheme encompassing maximal variations in the localized regions. The resulting features are globally fabricated into shape histograms in a non-overlapping manner representing the shape vector. This scheme validated on widely popular benchmark shape datasets demonstrates superior retrieval and recognition accuracies greater than 93% which is lacking in its competitors. [ABSTRACT FROM AUTHOR]

This paper represents advantages of using Centroid distance function for shape detection in real time traffic sign recognition compared with extracting histogram of oriented gradients (HOG) features and using support vector machine (SVM) classifier. Simulation results of using centroid distance show similar accuracy in compare with HOG SVM while have very low complexity and cost and running with higher speed. [ABSTRACT FROM AUTHOR]

Deep convolutional neural networks (DCNNs) show impressive similarities to the human visual system. Recent research, however, suggests that DCNNs have limitations in recognizing objects by their shape. We tested the hypothesis that DCNNs are sensitive to an object's local contour features but have no access to global shape information that predominates human object recognition. We employed transfer learning to assess local and global shape processing in trained networks. In Experiment 1, we used restricted and unrestricted transfer learning to retrain AlexNet, VGG-19, and ResNet-50 to classify circles and squares. We then probed these networks with stimuli with conflicting global shape and local contour information. We presented networks with overall square shapes comprised of curved elements and circles comprised of corner elements. Networks classified the test stimuli by local contour features rather than global shapes. In Experiment 2, we changed the training data to include circles and squares comprised of different elements so that the local contour features of the object were uninformative. This considerably increased the network's tendency to produce global shape responses, but deeper analyses in Experiment 3 revealed the network still showed no sensitivity to the spatial configuration of local elements. These findings demonstrate that DCNNs' performance is an inversion of human performance with respect to global and local shape processing. Whereas abstract relations of elements predominate in human perception of shape, DCNNs appear to extract only local contour fragments, with no representation of how they spatially relate to each other to form global shapes. [ABSTRACT FROM AUTHOR]

The article provides a detailed description of the 16 building blocks that comprise the total innovation management for excellence (TIME) pyramid. Topics discussed include need an innovation system that transforms the solution into an output, such as the innovation systems cycle; use of building blocks to increase an organization's efficiency, effectiveness and adaptability; and essential for an organizational assessment to collect information related to the needs.

Training tactile sensing for shape recognition is considered to be an effective rehabilitation technique. Previous studies in tactile sensing showed a tendency of recognition ambiguity, thus necessitating tactile sensing rehabilitation. Eleven subjects observed invisible objects using their fingers and were asked to identify the shape of the objects. The relationship between the degree of recognition and shape complexity was investigated. The results showed high self-confidence in recognizing high complexity shapes. The recognition process was confirmed in a second experiment measuring brain activation using near-infrared spectroscopy. Measurement of eight subjects showed the activation of verbal and visual processing regions, indicating that the act of handling the shape was translated to verbal expression and visual imaging. These results potentially quantify tactile sensing and contribute to the realization of personalized rehabilitation. [ABSTRACT FROM AUTHOR]

We present a novel method for real-time pose and shape reconstruction of two strongly interacting hands. Our approach is the first two-hand tracking solution that combines an extensive list of favorable properties, namely it is marker-less, uses a single consumer-level depth camera, runs in real time, handles inter- and intra-hand collisions, and automatically adjusts to the user's hand shape. In order to achieve this, we embed a recent parametric hand pose and shape model and a dense correspondence predictor based on a deep neural network into a suitable energy minimization framework. For training the correspondence prediction network, we synthesize a two-hand dataset based on physical simulations that includes both hand pose and shape annotations while at the same time avoiding inter-hand penetrations. To achieve real-time rates, we phrase the model fitting in terms of a nonlinear least-squares problem so that the energy can be optimized based on a highly efficient GPU-based Gauss-Newton optimizer. We show state-of-the-art results in scenes that exceed the complexity level demonstrated by previous work, including tight two-hand grasps, significant inter-hand occlusions, and gesture interaction.1 [ABSTRACT FROM AUTHOR]

Abstract Shape information plays an important role in the human visual system, and how to represent the shape accurately is a very challenging issue in shape recognition. In recent years, many shape description approaches have been proposed. However, most of the existing methods are still facing challenges on accuracy and computational efficiency. Fourier descriptor is regarded as a promising shape description method because it has a solid theoretical foundation and at the same time possesses the strength of appealing invariance properties and high computational efficiency. We introduce a novel multiscale Fourier descriptor based on triangular features which is used to identify shapes. The local and global characteristics of a shape are effectively captured by the proposed shape descriptor. Meanwhile, the proposed shape descriptor has good properties, such as the invariant of the geometric transformation and the starting point of an object. We tested this descriptor on four popular benchmarking datasets, including MPEG-7, Swedish leaf, ETH-80, and Flavia leaf. The results confirm that our method is better than comparable-complexity approaches based on Fourier descriptors and does not perform unfavorably with respect to more complex, state-of-the-art, shape descriptors. In particular, our method is far superior to the complex shape description methods in terms of retrieval efficiency and computational complexity. Highlights • We propose a novel multiscale triangle feature signature for Fourier descriptors. • Our method solves the lack of local shape feature of the Fourier descriptors. • The results show the superiority of our method over state-of-the-art descriptors. [ABSTRACT FROM AUTHOR]

In this paper, we consider a conductivity interface problem to recover the salient features of the inclusion within a body from noisy observation data on the boundary. Based on integral equations, we propose iterative algorithms to detect the location, the size and the shape of the conductivity inclusion. This problem is severely ill-posed and nonlinear, thus we should consider regularization techniques in order to improve the corresponding approximation. We give several examples to show the viability of our proposed reconstruction algorithms. [ABSTRACT FROM AUTHOR]

Autonomous exploration in robotics is a crucial feature to achieve robust and safe systems capable to interact with and recognize their surrounding environment. In this paper, we present a method for object recognition using a three-fingered robotic hand actively exploring interesting object locations to reduce uncertainty. We present a novel probabilistic perception approach with a Bayesian formulation to iteratively accumulate evidence from robot touch. Exploration of better locations for perception is performed by familiarity and novelty exploration behaviors, which intelligently control the robot hand to move toward locations with low and high levels of interestingness, respectively. These are active behaviors that, similar to the exploratory procedures observed in humans, allow robots to autonomously explore locations they believe that contain interesting information for recognition. Active behaviors are validated with object recognition experiments in both offline and real-time modes. Furthermore, the effects of inhibiting the active behaviors are analyzed with a passive exploration strategy. The results from the experiments demonstrate the accuracy of our proposed methods, but also their benefits for active robot control to intelligently explore and interact with the environment. [ABSTRACT FROM AUTHOR]

Our goal is to provide a novel method of representing 2D shapes, where each shape will be assigned a unique fingerprint—a computable approximation to the conformal map of the given shape to a canonical shape in 2D or 3D space (see page 22 for a few examples). In this paper, we make the first significant step in this program where we address the case of simply and doubly connected planar domains. We prove uniform convergence of our approximation scheme to the appropriate conformal mapping. To this end, we affirm a conjecture raised by Ken Stephenson in the 1990s which predicts that the Riemann mapping can be approximated by a sequence of electrical networks. In fact, we first treat a more general case. Consider a planar annulus, i.e., a bounded, 2-connected, Jordan domain, endowed with a sequence of triangulations exhausting it. We construct a corresponding sequence of maps which converge uniformly on compact subsets of the domain, to a conformal homeomorphism onto the interior of a Euclidean annulus bounded by two concentric circles. The resolution of Stephenson’s conjecture then follows by a limiting argument. With more complex topology of the given shape, i.e., when it has higher genus, we will use methods invented by Arabnia (J Parallel Distrib Comput 10:188-192, 1990) and Wani-Arabnia (J Supercomput 25:43-62, 2003). First, to divide the domain into subdomains and thereafter to make the scheme presented in this paper suitable for parallel processing. We will then be able to compare our results for those appearing, for instance, in the work of Arabnia-Oliver (Comput Graph Forum 8:3-11, 1989) that provides algorithms for the translation and scaling of complicated digitalized images. [ABSTRACT FROM AUTHOR]

A Fast Screen and Shape Recognition (FSSR) algorithm is proposed with complexity down to O(n) for the multiple change-point detection problems. The proposed FSSR algorithm includes two steps. First, by dividing the data into several subsegments, FSSR algorithm can quickly lock some small subsegments that are likely to contain change-points. Second, through a point by point search in each selected subsegment, FSSR algorithm determines the precise location of the change-point. The simulation study shows that FSSR has obvious speed and stability advantages. Particularly, the sparser the change-points is, the better result will be achieved from FRRS. Finally, we apply FSSR to two real applications to demonstrate its feasibility and robustness. One is the problem of DNA copy number variations identifying; another is the problem of operation scenarios reduction for renewable integrated electrical distribution network. [ABSTRACT FROM AUTHOR]

Most modern mobile devices are equipped with touchscreens as the main input hardware. Users can write text or draw shapes on the touchscreen to interact with apps. Therefore, accurate recognition of users’ freehand sketches becomes crucial for a device to receive correct instructions from users. This paper proposes a real-time scheme to recognize shapes drawn on the touchscreen. The proposed shape recognition scheme includes preprocessing, feature extraction and shape classification stages. Freehand strokes drawn by users are usually distorted and inaccurate. In preprocessing, this study uses the sampling technique to remove drawing imperfections such as small jagged noise or distorted strokes. In the feature extraction, we use a state machine to extract the length and curvature as the intrinsic features of a shape. In the final shape classification stage, a template-based approach is used to classify the input shape. A fitness score of the input shape to a template is calculated and the template with the highest score is chosen as the most matched shape. Experiment results show that the proposed real-time shape recognition has high accuracy and good performance. [ABSTRACT FROM AUTHOR]

Soft actuators are the components responsible for organs and tissues adsorptive fixation in some surgical operations, but the lack of shape sensing and monitoring of a soft actuator greatly limits their application potential. Consequently, this paper proposes a real-time 3D shape reconstruction method of soft surgical actuator which has an embedded optical fiber with two Fiber Bragg Grating (FBG) sensors. First, the design principle and the sensing of the soft actuator based on FBG sensors are analyzed, and the fabrication process of soft actuator which has an embedded optical fiber with two FBG sensors is described. Next, the calibration of the FBG sensors is conducted. Based on curvatures and curve fitting functions, the strategy of 3D shapes reconstruction of the soft actuator is presented. Finally, some bending experiments of the soft actuator are carried out, and the 3D shapes of the soft actuator at different bending states are reconstructed. This well reconstructed 3D shape of a soft actuator demonstrates the effectiveness of the shape reconstruction method that is proposed in this paper, as well as the potential and increased applications of these structures for real soft surgical actuators. [ABSTRACT FROM AUTHOR]

Abstract: Modular composites with a 3D periodic structure, consisting of a major brittle inorganic phase (building blocks) and a minor viscoelastic organic matrix, offer great potentials for improved fracture toughness and failure probability in polymer‐ceramic composites. Alumina building blocks with dimensions of 1500 μm were assembled by a novel placing system equipped with an automatic optical inspection (AOI) system. The AOI system coupled with shape recognition enables simultaneous dimensional characterization, tolerance sorting, and flexible placing of different shaped building blocks. 3D periodic structures with cubic, monoclinic, and triclinic unit cells were fabricated by high accuracy placing of cubic building blocks enabling near‐net shape manufacturing. The placing precision of the assembled structures was determined by μCT to have a maximum deviation of ±78 μm. The structures were afterward infiltrated with a soft epoxy resin to fabricate epoxy‐alumina composites. The brick‐and‐mortar like building block arrangements of the monoclinic and triclinic structures exhibited improved bending strength, fracture toughness, and failure probability compared to monolithic epoxy, due to crack deflection and pull‐out toughening mechanisms. A maximum bending strength of 35.1 ± 7.5 MPa, a work‐of‐fracture of 814.7 ± 255.1 J/m² and a calculated fracture toughness of 4.8 ± 0.8 MPa m for the triclinic structures was achieved. [ABSTRACT FROM AUTHOR]

Natsumushi is a free image analysis software that offers easy handling and quick measurement, designed especially for entomologists as the main users. The software enables measurement of: (i) color features of a specific region; (ii) area size; (iii) length of simple lines or polylines; and (iv) number of points or their x-y coordinates. Users can specify the region for measurement either manually or automatically by using image thresholding operations. The software is freely available at the website https://staff.aist.go.jp/t-fukatsu/ Natsumushi.html. [ABSTRACT FROM AUTHOR]

Recognition of three-dimensional (3D) shape is a remarkable subject in computer vision systems, because of the lack of excellent shape representations. With the development of 2.5D depth sensors, shape recognition is becoming more important in practical applications. Many methods have been proposed to preprocess 3D shapes, in order to get available input data. A common approach employs convolutional neural networks (CNNs), which have become a powerful tool to solve many problems in the field of computer vision. DeepPano, a variant of CNN, converts each 3D shape into a panoramic view and shows excellent performance. It is worth paying attention to the fact that both serious information loss and redundancy exist in the processing of DeepPano, which limits further improvement of its performance. In this work, we propose a more effective method to preprocess 3D shapes also based on a panoramic view, similar to DeepPano. We introduce a novel method to expand the training set and optimize the architecture of the network. The experimental results show that our approach outperforms DeepPano and can deal with more complex 3D shape recognition problems with a higher diversity of target orientation. [ABSTRACT FROM AUTHOR]

Models designed to explain how shapes are perceived and stored by the nervous system commonly emphasize encoding of contour features, especially orientation, curvature, and linear extent. A number of experiments from my laboratory provide evidence that contours deliver a multitude of location markers, and shapes can be identified when relatively few of the markers are displayed. The emphasis on filtering for orientation and other contour features has directed attention away from full and effective examination of how the location information is registered and used for summarizing shapes. Neural network (connectionist) models try to deal with location information by modifying linkage among neuronal populations through training trials. Connections that are initially diffuse and not useful in achieving recognition get eliminated or changed in strength, resulting in selective response to a given shape. But results from my laboratory, reviewed here, demonstrate that unknown shapes that are displayed only once can be identified using a matching task. These findings show that our visual system can immediately encode shape information with no requirement for training trials. This encoding might be accomplished by neuronal circuits in the retina. [ABSTRACT FROM AUTHOR]

Many mammals use some special tactile hairs, the so-called mystacial macrovibrissae, to acquire information about their environment. In doing so, rats and mice, e.g., are able to detect object distances, shapes, and surface textures. Inspired by the biological paradigm, we present a mechanical model for object contour scanning and shape reconstruction, considering a single vibrissa as a cylindrically shaped Euler-Bernoulli-bending rod, which is pivoted by a bearing. In doing so, we adapt our model for a rotational scanning movement, which is in contrast to many previous modeling approaches. Describing a single rotational quasi-static sweep of the vibrissa along a strict convex contour function using nonlinear Euler-Bernoulli theory, we end up in a boundary-value problem with some unknown parameters. In a first step, we use shooting methods in an algorithm to repeatedly solve this boundary-value problem (changing the vibrissa base angle) and generate the support reactions during a sweep along an object contour. Afterwards, we use these support reactions to reconstruct the object contour solving an initial-value problem. Finally, we extend the scanning process adding a second sweep of the vibrissa in opposite direction in order to enlarge the reconstructable area of the profile. [ABSTRACT FROM AUTHOR]

A combined shape descriptor for object recognition is presented, along with an offline and online learning method. The descriptor is composed of a local edge-based part and global statistical features. We also propose a two-level, nearest neighborhood type multiclass classification method, in which classes are bounded, defining an inherent rejection region. In the first stage, global features are used to filter model instances, in contrast to the second stage, in which the projected edge-based features are compared. Our experimental results show that the combination of independent features leads to increased recognition robustness and speed. The core algorithms map easily to cellular architectures or dedicated VLSI hardware. [ABSTRACT FROM AUTHOR]

Bag of Shape Features (BoSF), such as Bag of Contour Fragments (BoCF) and Bag of Skeleton-associated Contour Parts (BoSCP), derived from the well-known Bag of Features (BoF), is an effective framework for shape representation. The feature pooling in this framework is a critical step, while either max pooling or average pooling is not a learnable process. In this paper, we aim at learning a pooling function which is adaptive to the input shape features instead. Towards this end, we formulate our pooling function as a weighted sum of max pooling and average pooling, where the weight is expressed by an activation function of the input shape features. To automatically learn this weight, the output of the pooling function is fed into a SVM classifier and they are trained jointly to minimize a shape classification loss. Experimental results on several standard shape datasets demonstrate the effectiveness of the proposed learned pooling function, which can achieve considerable improvements compared with both BoCF and BoSCP. [ABSTRACT FROM AUTHOR]

The number of global mechanical equilibria as a shape descriptor (among others, for sedimentary particles) is at the forefront of current geophysical research. Although the technology is already available to provide scanned, 3D images of the particles (appearing as fine spatial discretization of smooth surfaces), nevertheless, the automated identification and measurement of global equilibria on such 3D images has not been solved so far. The main difficulty lies in the algorithmic distinction between local equilibria (associated with the small un-evenness of the pebble's surface) and global equilibria, associated with the overall shape. The former are easily measured, however, only the latter provide meaningful physical information. Here we provide and illustrate an algorithm to detect global equilibrium points on a finely discretized, polyhedral surface provided by 3D scan of sedimentary particles. [ABSTRACT FROM AUTHOR]

Object recognition in 3D scenes is one of the fundamental tasks in computer vision. It is used frequently in robotics or augmented reality applications [1]. In our work we intend to apply 3D shape recognition to create a Tangible Augmented Reality system that is able to pair virtual and real objects in natural indoors scenes. In this paper we present a method for arranging virtual objects in a real-world scene based on primitive shape graphs. For our scheme, we propose a graph node embedding algorithm for graphs with vectorial nodes and edges, and genetic operators designed to improve the quality of the global setup of virtual objects. We show that our methods improve the quality of the arrangement significantly. [ABSTRACT FROM AUTHOR]

Recognition of objects in pictures and movies requires the use of techniques, such as filtering, segmentation and classification. Image filtering is required to remove all artifacts that hinder the unequivocal identification and sharpen interesting objects. Segmentation refers to finding areas of images respected to individual objects. For the selected areas corresponding to objects in the selected picture, the classification of objects finally gives information about the type of object which orientation is made. This paper presents a method for the classification of objects from drawings as a bitmap using the method of fundamental solutions (MFS). The MFS was tested on the selected bitmap depicting simple geometric shapes. The correlations between errors occurring on the boundary for particular shapes are used for the selection of geometric shape figures. Due to this correlation, it is possible to recognize the shape of the image appearing on the drawing by an analysis consisting of the comparison of recognized points describing the shape of contour to a database containing solutions of boundary value problems for the selected shape. In one way, the comparison of the pattern can determine which shape from database it is most similar to in terms of contour. This article appear that this approach is very simple and clearly. In result, this method can be used to recognition of the objects in the systems of real-time processing. [ABSTRACT FROM AUTHOR]

Phase measuring profilometry and moiré methodology have been widely applied to the three-dimensional shape measurement of target objects, because of their high measuring speed and accuracy. However, these methods suffer from inherent limitations called a correspondence problem, or 2p-ambiguity problem. Although a kind of sensing method to combine well-known stereo vision and phase measuring profilometry (PMP) technique simultaneously has been developed to overcome this problem, it still requires definite improvement for sensing speed and measurement accuracy. We propose a dynamic programming-based stereo PMP method to acquire more reliable depth information and in a relatively small time period. The proposed method efficiently fuses information from two stereo sensors in terms of phase and intensity simultaneously based on a newly defined cost function of dynamic programming. In addition, the important parameters are analyzed at the view point of the 2π-ambiguity problem and measurement accuracy. To analyze the influence of important hardware and software parameters related to the measurement performance and to verify its efficiency, accuracy, and sensing speed, a series of experimental tests were performed with various objects and sensor configurations. [ABSTRACT FROM AUTHOR]

Tactile information has been largely exploited for object recognition with robotic hands but very few approaches have used proprioception alone. In those that do, raw values of joint angles or torques are exploited to train learning algorithms. However, these approaches under-exploit the potential of proprioception, such as its usefulness to estimate the object pose and size. Furthermore, they focus on recognizing individual objects, which increases the amount of data needed to train the algorithms. In this paper, we present an approach based only on joint angles of a robotic hand to generate a shape proprioceptive signature that is invariant to the size and position of the object. Instead of recognizing a specific object from a list, object characteristics useful for its manipulation are extracted. This signature is exploited not only for shape recognition but also for pose estimation. To illustrate the scope of this method, tests are performed on primitive shapes. Results show that the signatures are invariant within large ranges of sizes and poses. Experiments on real hand were carried, and results depicted that the method works similarly in both simulated environment and real applications. A comparison between this two results is made and discussed. [ABSTRACT FROM AUTHOR]

For 3D shape analysis, an effective and efficient feature is the key to popularize its applications in 3D domain where the major challenge lies in designing an effective high-level feature. The three-dimensional shape contains various useful information including visual information, geometric relationships, and other type properties. Thus the strategy of exploring these characteristics is the core of extracting effective 3D shape features. In this paper, we propose a novel 3D feature learning framework which combines different modality data effectively to promote the discriminability of uni-modal feature by using deep learning. The geometric information and visual information are extracted by Convolutional Neural Networks (CNNs) and Convolutional Deep Belief Networks (CDBNs), respectively, and then two independent Deep Belief Networks (DBNs) are employed to learn high-level features from geometric and visual features. Finally, a Restricted Boltzmann Machine (RBM) is trained for mining the deep correlations between different modalities. Extensive experiments demonstrate that the proposed framework achieves better performance. [ABSTRACT FROM AUTHOR]

In this paper a novel and generalized circularity measure is proposed based on 3D polar-radius-moment invariant. We proved theoretically and verify experimentally that the proposed measure is invariant to scaling and rotation. Moreover, the proposed measure can be adapted to a fixed range for a suitable value of p according to degree of accuracy and is generalized to satisfy different requirements in actual application. The experimental results show that the proposed measure can accord with human visual perception and consistently performs best in terms of retrieval efficiency in test datasets than other compared methods. [ABSTRACT FROM AUTHOR]

In the field of stereoscopic 3D (S3D) display, it is an interesting as well as meaningful issue to retarget the stereoscopic images to the target resolution, while the existing stereoscopic image retargeting methods do not fully take user’s Quality of Experience (QoE) into account. In this paper, we have presented a QoE-guided warping method for stereoscopic image retargeting, which retarget the stereoscopic image and adapt its depth range to the target display while promoting user’s QoE. Our method takes shape preservation, visual comfort preservation, and depth perception preservation energies into account, and simultaneously optimizes the 2D coordinates and depth information in 3D space. It also considers the specific viewing configuration in the visual comfort and depth perception preservation energy constraints. Experimental results on visually uncomfortable and comfortable stereoscopic images demonstrate that in comparison with the existing stereoscopic image retargeting methods, the proposed method can achieve a reasonable performance optimization among the QoE’s factors of image quality, visual comfort, and depth perception, leading to promising overall S3D experience. [ABSTRACT FROM PUBLISHER]

We propose an efficient and robust method for the recognition of objects exhibiting multiple intra-class modes, where each one is associated with a particular object appearance. The proposed method, called random clustering ferns, combines synergically a single and real-time classifier, based on the boosted assembling of extremely randomized trees (ferns), with an unsupervised and probabilistic approach in order to recognize efficiently object instances in images and discover simultaneously the most prominent appearance modes of the object through tree-structured visual words. In particular, we use boosted random ferns and probabilistic latent semantic analysis to obtain a discriminative and multimodal classifier that automatically clusters the response of its randomized trees in function of the visual object appearance. The proposed method is validated extensively in synthetic and real experiments, showing that the method is capable of detecting objects with diverse and complex appearance distributions in real-time performance. [ABSTRACT FROM AUTHOR]

We propose a novel method for detecting and reconstructing tubular shapes in dense, noisy, occluded and unorganized point clouds. The STEP method (Snakes for Tuboid Extraction from Point clouds) was originally designed to reconstruct woody parts of trees scanned with terrestrial LiDAR in natural forest environments. The STEP method deals with the acquisition artefacts of point clouds from terrestrial LiDAR which include three important constraints: a varying sampling rate, signal occlusion, and the presence of noise. The STEP method uses a combination of an original Hough transform and a new form of growing active contours (also referred to as “snakes”) to overcome these constraints while being able to handle large data sets. The framework proves to be resilient under various conditions as a general shape recognition and reconstruction tool. In the field of forestry, the method was demonstrated to be robust to the previously highlighted limitations (with errors in the range of manual forest measurements, that is 1 cm diameter error). The STEP method has therefore the potential to improve current forest inventories as well as being applied to a wide array of other applications, such as pipeline reconstruction and the assessment of industrial structures. [ABSTRACT FROM AUTHOR]

This paper was made in the context of object recognition, and in particular, in the detection of 3D objects and their free forms by local descriptors of interest points to identify them. However, it remains to solve several problems in this area that is related to a large amount of information and invariant to scale and angle of view. In this context, our purpose is to make the recognition of a 3D object from the detection of their interest points and extract characteristics of the detection of each object to facilitate his research in a database. For this reason, we will propose a new robust detector to noise that includes criteria for extracting interest points of 3D objects by specifying their free forms, this detector, is based on SUSAN detector using differential measures for comparing it with others. [ABSTRACT FROM AUTHOR]

The paper presents a novel three-dimensional shape acquisition and reconstruction method based on the well-known Archimedes equality between fluid displacement and the submerged volume. By repeatedly dipping a shape in liquid in different orientations and measuring its volume displacement, we generate the dip transform: a novel volumetric shape representation that characterizes the object's surface. The key feature of our method is that it employs fluid displacements as the shape sensor. Unlike optical sensors, the liquid has no line-of-sight requirements, it penetrates cavities and hidden parts of the object, as well as transparent and glossy materials, thus bypassing all visibility and optical limitations of conventional scanning devices. Our new scanning approach is implemented using a dipping robot arm and a bath of water, via which it measures the water elevation. We show results of reconstructing complex 3D shapes and evaluate the quality of the reconstruction with respect to the number of dips. [ABSTRACT FROM AUTHOR]

Many computer graphics applications use simpler yet faithful approximations of complex shapes to conduct reliably part of their computations. Some tasks, such as physical simulation, collision detection, occlusion queries or free-form deformation, require the simpler proxy to strictly enclose the input shape. While there are algorithms that can output such bounding proxies on simple input shapes, most of them fail at generating a proper coarse approximant on real-world complex shapes, which may contain multiple components and have a high genus. We advocate that, before reducing the number of primitives to describe a shape, one needs to regularize it while maintaining the strict enclosing property, to avoid any geometric aliasing that makes the decimation unreliable. Depending on the scale of the desired approximation, the topology of the shape itself may indeed have to be first simplified, to let the subsequent geometric optimization be free from topological locks. We propose a new bounding shape approximation algorithm which takes as input an arbitrary surface mesh, with potentially complex multi-component structures, and generates automatically a bounding proxy which is tightened on the input and can match even the coarsest levels of approximation. To sustain the nonlinear approximation process that may eventually abstract both geometry and topology, we propose to use an intermediate regularized representation in the form of a shape closing, computed in real time using a new fast morphological framework designed for efficient parallel execution. Once the desired level of approximation is reached in the shape closing, a coarse, tight and bounding polygonization of the proxy geometry is extracted using an adaptive meshing scheme. Our underlying representation is both geometry- and topology-adaptive and can be optionally controlled accurately by a user, through sizing and orientation fields, yielding an intuitive brush metaphor within an interactive proxy design environment. We provide extensive experiments on various kinds of input meshes and illustrate the potential applications of our method in scenarios that benefit greatly from coarse, tight bounding substitutes to the actual high resolution geometry of the original 3D model, including freeform deformation, physical simulation and level of detail generation for rendering. [ABSTRACT FROM AUTHOR]

We present FlowRep, an algorithm for extracting descriptive compact 3D curve networks from meshes of free-form man-made shapes. We infer the desired compact curve network from complex 3D geometries by using a series of insights derived from perception, computer graphics, and design literature. These sources suggest that visually descriptive networks are cycle-descriptive, i.e their cycles unambiguously describe the geometry of the surface patches they surround. They also indicate that such networks are designed to be projectable, or easy to envision when observed from a static general viewpoint; in other words, 2D projections of the network should be strongly indicative of its 3D geometry. Research suggests that both properties are best achieved by using networks dominated by flowlines, surface curves aligned with principal curvature directions across anisotropic regions and strategically extended across sharp-features and isotropic areas. Our algorithm leverages these observation in the construction of a compact descriptive curve network. Starting with a curvature aligned quad dominant mesh we first extract sequences of mesh edges that form long, well-shaped and reliable flowlines by leveraging directional similarity between nearby meaningful flowline directions We then use a compact subset of the extracted flowlines and the model's sharp-feature, or trim, curves to form a sparse, projectable network which describes the underlying surface. We validate our method by demonstrating a range of networks computed from diverse inputs, using them for surface reconstruction, and showing extensive comparisons with prior work and artist generated networks. [ABSTRACT FROM AUTHOR]

Many approaches to shape comparison and recognition start by establishing a shape correspondence. We "turn the table" and show that quality shape correspondences can be obtained by performing many shape recognition tasks. What is more, the method we develop computes a fine-grained, topology-varying part correspondence between two 3D shapes where the core evaluation mechanism only recognizes shapes globally. This is made possible by casting the part correspondence problem in a deformation-driven framework and relying on a data-driven "deformation energy" which rates visual similarity between deformed shapes and models from a shape repository. Our basic premise is that if a correspondence between two chairs (or airplanes, bicycles, etc.) is correct, then a reasonable deformation between the two chairs anchored on the correspondence ought to produce plausible, "chair-like" in-between shapes. Given two 3D shapes belonging to the same category, we perform a top-down, hierarchical search for part correspondences. For a candidate correspondence at each level of the search hierarchy, we deform one input shape into the other, while respecting the correspondence, and rate the correspondence based on how well the resulting deformed shapes resemble other shapes from ShapeNet belonging to the same category as the inputs. The resemblance, i.e., plausibility, is measured by comparing multi-view depth images over category-specific features learned for the various shape categories. We demonstrate clear improvements over state-of-the-art approaches through tests covering extensive sets of man-made models with rich geometric and topological variations. [ABSTRACT FROM AUTHOR]

How does the visual system recognize images of a novel object after a single observation despite possible variations in the viewpoint of that object relative to the observer? One possibility is comparing the image with a prototype for invariance over a relevant transformation set (e.g., translations and dilations). However, invariance over rotations (i.e., orientation invariance) has proven difficult to analyze, because it applies to some objects but not others. We propose that the invariant transformations of an object are learned by incorporating prior expectations with realworld evidence. We test this proposal by developing an ideal learner model for learning invariance that predicts better learning of orientation dependence when prior expectations about orientation are weak. This prediction was supported in two behavioral experiments, where participants learned the orientation dependence of novel images using feedback from solving arithmetic problems. [ABSTRACT FROM AUTHOR]

A novel approach to estimating the detailed shape of arbitrary extended objects jointly with their kinematics in the absence of a priori information is presented. The proposed shape model represents the tightest enclosing bound of the object projected into the ego motion plane as a polygon with an unknown number of vertices. Probabilistic inference techniques are employed to overcome various sources of uncertainty by rigorously estimating the joint distribution over the object shape and kinematic states, rather than estimating these variables directly. Simulation and experimental results are presented for objects with complex shapes tracked from an autonomous vehicle research platform. In addition to providing a richer set of information for higher level reasoning about extended objects (e.g. about object type, or occupied space), the results demonstrate that detailed shape estimates enable efficient use of sensor information by way of explicit surface-based sensor models; this efficient use of sensor information improves observability of latent object states, thereby improving tracking precision. [ABSTRACT FROM PUBLISHER]

As an increasing number of digital images are generated, a demand for an efficient and effective image retrieval mechanisms grows. In this work, we present a new skeleton-based algorithm for 2D and 3D shape retrieval. The algorithm starts by drawing circles (spheres for 3D) of increasing radius around skeletons. Since each skeleton corresponds to the center of a maximally inscribed circle (sphere), this process results in circles (spheres) that are partially inside the shape. Computing the ratio between pixels that lie within the shape and the total number of pixels allows us to distinguish shapes with similar skeletons. Experimental evaluation of the proposed approach including a comprehensive comparison with the previous techniques demonstrates both effectiveness and robustness of our algorithm for shape retrieval using several 2D and 3D datasets. [ABSTRACT FROM AUTHOR]

Medial surfaces are powerful tools for shape description, but their use has been limited due to the sensibility of existing methods to branching artifacts. Medial branching artifacts are associated to perturbations of the object boundary rather than to geometric features. Such instability is a main obstacle for a confident application in shape recognition and description. Medial branches correspond to singularities of the medial surface and, thus, they are problematic for existing morphological and energy-based algorithms. In this paper, we use algebraic geometry concepts in an energy-based approach to compute a medial surface presenting a stable branching topology. We also present an efficient GPU-CPU implementation using standard image processing tools. We show the method computational efficiency and quality on a custom made synthetic database. Finally, we present some results on a medical imaging application for localization of abdominal pathologies. [ABSTRACT FROM AUTHOR]

Background: Identifying potential drug candidates through Ligand-based virtual screening is often associated with processing of huge amount of data and hence is a computational intensive task. Ultrafast Shape Recognition (USR) algorithm has been reported as a faster alternative for molecular shape comparison which maps the chemical structure of query ligand into its shape moment vector to find novel chemical scaffolds in chemical compound libraries. The USR algorithm however was devoid of the ability to discriminate ligand molecules according to their pharmacokinetic features. Methods: To overcome this discrepancy, a modification in the existing USR algorithm called DUSR (Distributed Ultrafast Shape Recognition) was carried out where chemical compounds were screened on the basis of their drug-likeliness properties prior to the molecular shape comparison followed by shape complementarity momentum measure. The DUSR due to its Hadoop implementation acts as a faster approach than the existing standalone tools, utilizing the MapReduce algorithm supporting the high throughput screening of million conformers in a much reduced time span. We further demonstrated the utility of DUSR on dataset of 2 million ligand molecules by running shape comparison based searching job on standalone and multisystem Hadoop platforms. Results: The result suggested that DUSR completed its job in 1h 15 m 41s, 0 h 23 m 41s and 0h13m 22s sec for 2038924 molecules on Hadoop standalone mode, 3-nodes cluster & 5-nodes cluster of distributed commodity hardware respectively. [ABSTRACT FROM AUTHOR]

• Shape recognition performance was worst with reversed binocular disparity. • Performance was better with null or normal disparity, which did not differ. • Conflicting sources of depth information lead to degraded shape descriptions. • Visual shape perception continuously integrates binocular disparity information. The contribution of stereopsis in human visual shape perception was examined using stimuli with either null, normal, or reversed binocular disparity in an old/new object recognition task. The highest levels of recognition performance were observed with null and normal binocular disparity displays, which did not differ. However, reversed disparity led to significantly worse performance than either of the other display conditions. This indicates that stereopsis provides a continuous input to the mechanisms involved in shape perception. [ABSTRACT FROM AUTHOR]

The visual system processes visual input in a hierarchical manner in order to extract relevant features that can be used in tasks such as invariant object recognition. Although typically investigated in primates, recent work has shown that rats can be trained in a variety of visual object and shape recognition tasks. These studies did not pinpoint the complexity of the features used by these animals. Many tasks might be solved by using a combination of relatively simple features which tend to be correlated. Alternatively, rats might extract complex features or feature combinations which are nonlinear with respect to those simple features. In the present study, we address this question by starting from a small stimulus set for which one stimulus-response mapping involves a simple linear feature to solve the task while another mapping needs a well-defined nonlinear combination of simpler features related to shape symmetry. We verified computationally that the nonlinear task cannot be trivially solved by a simple V1-model. We show how rats are able to solve the linear feature task but are unable to acquire the nonlinear feature. In contrast, humans are able to use the nonlinear feature and are even faster in uncovering this solution as compared to the linear feature. The implications for the computational capabilities of the rat visual system are discussed. [ABSTRACT FROM AUTHOR]

The General Shape Analysis (GSA) is a task similar to the shape recognition and retrieval. However, in GSA an object usually does not belong to a template class, but can only be similar to some of them. Moreover, the number of applied templates is limited. Usually, ten most general shapes are used. Hence, the GSA consists in searching for the most universal information about them. This is useful when some general information has to be concluded, e.g. in coarse classification. In this paper the result of the application of three shape descriptors based on the moment theory to the GSA is presented. For this purpose the Moment Invariants, Contour Sequence Moments, and Zernike Moments were selected. [ABSTRACT FROM AUTHOR]

There are various possible approaches to the task of automatic identification of football players on video sequences. In the paper the numbers on jerseys are analysed and investigated. Firstly, the algorithm for the localisation of sport shirts and consecutively numbers is described. Secondly, the method for the recognition of the extracted numbers is proposed and experimentally investigated. The approach analysed in the paper applies the Generic Fourier Descriptor for the representation of extracted binary shapes of numbers. [ABSTRACT FROM AUTHOR]