With the development of technology, the automation industry has gradually improved, and the application of the visual-inertial system has become increasingly prosperous. Self-driving cars and autonomous mobile robots often use the visual-inertial system as a state estimator, and their image information can be used in the artificial intelligence part to provide more information about the robot. The combination of a monocular camera and an inertial sensor has the characteristics of light weight and low power. Monocular Visual-Inertial SLAM is a system that relies on monocular cameras and inertial sensors to perform localization and mapping. Monocular Visual-Inertial SLAM restores its vector to scale with the help of known extrinsic parameter information. However, compared with other methods, it is necessary to be careful in estimating the gyroscope bias of the inertial sensor. The bias and noise of the inertial sensor will directly affect the results of pre-integration, as well as the accuracy of the visual-inertial scale recovery. This phenomenon is called scale uncertainty, which results in feature points with uncertain scale or depth, rapidly reducing the accuracy of pose estimation. This paper proposes an architecture of visual-inertial based on Structure-Scale Adaptivity. In this study, the tightly coupled residual between the structure scale and the pose is designed to provide adaptivity according to the feature conditions, providing system structure and scale constraints, and thus suppressing the problem of scale uncertainty. This study is compared with state-of-the-art algorithms and succeeds in scenarios where other algorithms have failed. It also obtains the best accuracy results in the overall test. Finally, we evaluate our proposed method on VCU-RVI and KITTI datasets, demonstrating the proposed algorithm's effectiveness and feasibility for monocular visual-inertial SLAM.

The development of monocular visual simultaneous localization and mapping (VSLAM) has slowly begun in recent years. At present, the sensors used for VSLAM include monocular, binocular, or depth. For visual mapping, two problems will be encountered and the mapping cannot be performed. One is when there are not enough feature points, the camera's pose at the next moment cannot be estimated, such as a wall. The other is the VSLAM of dynamic environment changes may not be recognized as the same object because the feature matching needs to be coded through its surrounding environment, so it is easy to lose track when encountering changes in light. Compared with binocular and depth, monocular vision lacks depth information, but because it is cheap and easy to install, it needs to be used by multiple people. The current research proposes adding other information, including the camera height, the scene of the reference object and depth estimation by learning methods. The study uses the OpenVSLAM architecture to estimate the camera height scale, and proposes the mechanism be based on the change in the average scale of the first five key frames, with the average scale being updated at the same time to correct the current scale. Through this method, the drastic changes in scale are corrected, and the accuracy of trajectory positioning is improved. We also evaluate our proposed method on a real KITTI Dataset and demonstrate the proposed algorithm is effective and feasible for monocular visual SLAM.

Self-driving vehicle systems have become mainstream as major international research and development companies compete for road detection and mapping projects such as localization. The latter plays an important role in self-driving systems because an accurate determination of the vehicle's position improves trajectory and offset results. And with a good localization function, a high-precision map can be established. This paper proposes using pole maps to enhance vehicle localization while correcting previous vehicle localization trajectory offsets. We have established a pole feature map with pole-shaped characteristic point clouds along the road that are marked with spatial coordinate information. We use three-dimensional light detection and ranging (3D Lidar) as a sensor for environmental scanning, dynamic segment thresholds, and point cloud projections to the image to extract poles, which avoids identification errors typically caused by the scattering effect of 3D Lidar. The resulting pole map uses the occupancy grid map to filter out noise. In terms of localization, we continue to detect pole features while the vehicle is moving, and compare these with the map. When the results match, we update the current localized information. The localization point corrects the information of the trajectory of the undetected pole, which improves vehicle localization accuracy.

Robots are widely used as unmanned vehicles in smart factories. In order to operate the robot in a known environment, the robot must be able to plan the path. The planned path must enable the robot to reach a destination from the starting point and the robot must avoid all obstacles during movement. This study uses a four-parameter logic curve path planning method that uses a closed formula solution and a curve with minimal design parameters to quickly generate an ideal path. The characteristics of the curve are used to derive the S and half-S curves as the solution path. The shortest path is used as the selection reference target to select parameters B and C for the four-parameter logic curve. For the S path, the best solution is chosen. The half -S curve is limited by the elastic end-point heading angle, which gives a unique set of parameter solutions. The generated path does not allow the robot to completely avoid obstacles so a hierarchical half-S curve path planning mechanism is used. A via point is generated at the collision point using the gradient vector for the edge of the obstacle. The planner continues to perform half-S path planning until the path planning ends.

Generating a realistic human class image from a sketch is a unique and challenging problem considering that the human body has a complex structure that must be preserved. Additionally, input sketches often lack important details that are crucial in the generation process, hence making the problem more complicated. In this article, we present an effective method for synthesizing realistic images from human sketches. Our framework incorporates human poses corresponding to locations of key semantic components (e.g., arm, eyes, nose), seeing that its a strong prior for generating human class images. Our sketch-image synthesis framework consists of three stages: semantic keypoint extraction, coarse image generation, and image refinement. First, we extract the semantic keypoints using Part Affinity Fields (PAFs) and a convolutional autoencoder. Then, we integrate the sketch with semantic keypoints to generate a coarse image of a human. Finally, in the image refinement stage, the coarse image is enhanced by a Generative Adversarial Network (GAN) that adopts an architecture carefully designed to avoid checkerboard artifacts and to generate photo-realistic results. We evaluate our method on 6,300 sketch-image pairs and show that our proposed method generates realistic images and compares favorably against state-of-the-art image synthesis methods.

This paper presents a self-driving technology that relies on a built-in sensing system to detect traffic objects. The use of three-dimensional (3D) light detection and ranging (Lidar) to assist measurement and perception is feasible. As Lidar provides high-precision positioning and is not influenced by light intensity, it can be used in bad weather and effectively minimizes the number of accidents caused by self-driving vehicles. One of the intuitive clustering methods used by the modern 3D Lidar, is known as density-based spatial clustering of applications with noise (DBSCAN). DBSCAN uses a single distance threshold to classify the entire point cloud. However, due to the non-uniform scattering characteristics of 3D Lidar, the single threshold cannot meet the current clustering accuracy requirements. Moreover, the method is very time consuming. This study proposed a fast multiresolution clustering method to improve the accuracy and reduce the computations based on the DBSCAN algorithm. We used the 360 sweeping scanning pattern of 3D Lidar to search for the angular area near the point cloud and then used variable thresholds to cluster objects with different range zones. The experimental results demonstrated that the proposed method can effectively improve the accuracy and reduce the computation time required for 3D point cloud clustering.

Sensor fusion, especially in 2D cameras and 3D laser scanners, is crucial for robot and autonomous driving. Calibration is a major aspect of sensor fusion. Most of the calibration is conducted offline by using checkerboards to determine the sensor pose. However, problems arise when robots or vehicles have irregular vibrations during movement. This leads to sensors having a different position from the initial pose. Therefore, online calibration, which allows robots to be calibrated at any time during their movement, is required. This study focused on calibrating a 2D camera and 3D lidar scanner by using their resembling features. For lidar calibration, we transformed the 3D point cloud into a 2D range image and removed the edge points. For calibrating the camera, we applied an edge filter to the image. Then, the inverse distance transform was used to identify the alignment of the edges. The sensor pose relative to the camera and lidar system was determined from their corresponding images.

Visual sensors are widely used in automatic parking systems, so this paper proposes an algorithm for the visual detection of available parking slots. The proposed system consists of two stages: parking slot recognition and slot occupancy classification. The parking slot recognition stage generates parking slots using the corner features of parking slot markings. The slot occupancy classification stage verifies the availability of the parking slot using the features of detected slots. The experimental results demonstrate that the proposed method effectively detects available parking slots in AVM images.

The RGB camera and LIDAR have been applied in object identification for robots. However, Kinect has changed this situation. Because of the wide use of three-dimensional (3D) processing, the point cloud library (PCL) now enables people to easily use in a 3D environment. Iterative closest point (ICP) is an ideal method for identifying a target, but it involves first reconstructing an object. Therefore, this paper presents an alternative method using geometry of surface for identifying the features of an object and differentiating it from other objects.

In this paper, we present a proposed method for analyzing Raman spectra of Functionalized multiwall carbon nano-tubes (MWCNTs) by using empirical model decomposition (EMD). Then, Hilbert-Huang transform (HHT) is adopted to analyze Raman spectra of functionalized MWCNTs. we demonstrate the performance of HHT compare with fast short time Fourier transform (STFT) and enhanced Morlet transform (EMT). The experimental results show that the proposed method performs a good decomposition for identifying D band and G band pattern in MWCNTs.

The primary objective of privacy preservation is to protect an individual's confidential information in released data sets. In recent years, several simulation-based approaches for privacy preservation have been proposed. The idea is to generate a synthetic data set with the constraint that the probability distribution is as close as possible to that of the original set. In this paper, we propose two frameworks for simulation-based privacy preservation of multivariate numerical data. The first framework, called PRIMP (PRivacy preserving by Independent coMPonents), is based on independent component analysis (ICA). It is shown empirically that PRIMP outperforms other simulation-based approaches in terms of Spearman's rank correlation and Kendall's tau correlation. The second approach proposed is a hybrid method that combines PRIMP and Cholesky's decomposition technique. It is shown empirically that the hybrid method preserves the covariance matrix of the original data exactly. The method also resolves the problem of generating good seeds for the Cholesky-based approach. Although the empirical results show that the hybrid approach is not always better than the PRIMP in terms of Spearman's rank correlation and Kendall's tau correlation, in theory, the risk of information leakage under the hybrid approach is much less than that under PRIMP.

Microwave Plasma Chemical Vapor Deposition (MPCVD) method can be used to grow various kinds of diamond films and carbon nanotubes at various temperatures. Manufacturing parameters, such as gas flow rate, input microwave power, working distance, deposition time, chamber pressure and substrate temperature, were all fixed to grow multiwalled carbon nanotubes (MWCNTs). To grow MWCNTs of better quality with a self-assembled MPCVD system, the quality indexes of MWCNTs, which are the aspect ratio of MWCNTs and the ID/IG intensity ratio of the Raman spectrum of MWCNTs, were analyzed. In this paper, we present a proposed method for analyzing Raman spectra of Functionalized MWCNTs by using Empirical Model Decomposition (EMD). The performances of the method are compared with those provided with the Gaussian/Lorentz fitting method. The results show that the proposed method performs a good decomposition for identifying D band and G band pattern in MWCNTs.

In order to improve the reproducibility of mutiwalled carbon nano-tubes (MWCNTs) process, this study integrates the remote monitoring and fuzzy logic control into microwave plasma chemical vapor deposition (MPCVD) system with the reflected microwave power as the main feedback signal. An automatic fuzzy logic controller is used to drive the E-H tuner and adjust the electromagnetic field distribution and plasma density of the MPCVD system. The specific micro-structure ratio of MWCNTs is a fuzzy singleton which input into fuzzy logic algorithm. An E-H tuner position adjustment of (X, Y) = (19.3 cm, 10 cm) is found to have the lowest average reflected power. At this position, the MWCNTs with averaged films thickness is 15.44 µm, the averaged tube diameter is 42 nm, and the ID/IGratio is 1.12 for as-grown carbon nanotubes (CNTs) film.

Effective distance functions in high dimensional data space are very important in solutions for many data mining problems. Recent research has shown that if the Pearson variation of the distance distribution converges to zero with increasing dimensionality, the distance function will become unstable (or meaningless) in high dimensional space, even with the commonly used Lpmetric in the Euclidean space. This result has spawned many studies the along the same lines. However, the necessary condition for unstability of a distance function, which is required for function design, remains unknown. In this paper, we shall prove that several important conditions are in fact equivalent to unstability. Based on these theoretical results, we employ some effective and valid indices for testing the stability of a distance function. In addition, this theoretical analysis inspires us that unstable phenomena are rooted in variation of the distance distribution. To demonstrate the theoretical results, we design a meaningful distance function, called the shrinkage-divergence proximity (SDP), based on a given distance function. It is shown empirically that the SDP significantly outperforms other measures in terms of stability in high dimensional data space, and is thus more suitable for distance-based clustering applications.

PageRank is one of the most important ranking techniques used in search engines nowadays. Since billions of pages already existed in Web, many PageRank acceleration techniques were explored by many researchers. However, in the real Web, just like the existence of pages without out-links, there are many pages without in-links. (In this paper, a Web page without in-links is called a reverse-dangling page.) Given the state of the art, we propose a new reordered PageRank algorithm, called two-way reordered PageRank algorithm, which exploits both dangling nodes and reverse-dangling nodes to reduce the computational complexity of the PageRank vector.

The Microwave Plasma Chemical Vapor Deposition (MPCVD) method has been widely used in several industry applications. The plasma modeling and control issues play an important role in MPCVD systems. One of crucial factors in controlling plasma shape and position is the tunable reflected microwave power of the MPCVD system. However, modeling the tunable reflected power of microwave plasma is highly complex and remains as a poorly understandable information. In this paper, the reflected power distribution corresponding to the adjustable electromagnetic field can be reduced as a 2-D scattered plot by using 2-D histogram projection and then be modeled in a mathematical expression through the 2-D Gaussian Mixture Modeling (GMM). The estimated results of calculation show that microwave power data can be simplified to be a linear combination of some Gaussian functions that provides a predictable and controlled basis for tuning manufacturing parameters and plasma sharp in a real-time control.

Microwave Plasma Chemical Vapor Deposition (MPCVD) method can be used to grow various kinds of diamond films and carbon nanotubes at various temperatures. However, it is usually only the hand-on experience that can be relied on to obtain the nearly satisfactory plasma in the MPCVD system. Therefore, this study set up the reflected power sensor as a reference parameter and used a CCD (Charge Coupled Device) to observe the plasma image. Manufacturing parameters, such as gas flow rate, input microwave power, working distance, deposition time, chamber pressure and substrate temperature, were all fixed to grow MWCNTs. The controlled adjustments, as the independent variables, are the positions of E-H tuner along x-axis and y-axis which directly affect the conditions of the plasma. In order to grow multiwalled carbon nanotubes (MWCNTs) of better quality with a self-assembled MPCVD system, the quality indexes of MWCNTs, which are the aspect ratio of MWCNTs and the ID/IG intensity ratio of the Raman spectrum of MWCNTs, were analyzed. With the established database, it is found that there exist the optimized positions of E-H tuner along x-axis and y-axis for growing MWCNTs of high quality. Moreover, we used PCA (Principle Component Analysis) method to analysis these data, and a relationship between manufacturing parameters was found.

The use of effective distance functions has been explored for many data mining problems including clustering, nearest neighbor search, and indexing. Recent research results show that if the Pearson variation of the distance distribution converges to zero with increasing dimensionality, the distance function will become unstable (or meaningless) in high dimensional space even with the commonly used Lp metric on the Euclidean space. This result has spawned many subsequent studies. We first comment that although the prior work provided the sufficient condition for the unstability of a distance function, the corresponding proof has some defects. Also, the necessary condition for unstability (i.e., the negation of the sufficient condition for the stability) of a distance function, which is required for function design, remains unknown. Consequently, we first provide in this paper a general proof for the sufficient condition of unstability. More importantly, we go further to prove that the rapid degradation of Pearson variation for a distance distribution is in fact a necessary condition of the resulting unstability. With the result, we will then have the necessary and the sufficient conditions for unstability, which in turn imply the sufficient and necessary conditions for stability. This theoretical result derived leads to a powerful means to design a meaningful distance function. Explicitly, in light of our results, we design in this paper a meaningful distance function, called Shrinkage-Divergence Proximity (abbreviated as SDP), based on a given distance function. It is empirically shown that the SDP significantly outperforms prior measures for its being stable in high dimensional data space and robust to noise, and is thus deemed more suitable for distance-based clustering applications than the priorly used metric.

A microwave plasma jet chemical vapor deposition (MPJCVD) method, which utilizes antenna to guide microwaves, is a technology that hasn' t successfully applied to grow diamond films. This study overcame difficulties in system design and grew sub-micron diamond films using a self-assembled MPJCVD system. The advantageous high-density plasma of such microwave plasma jet can largely improve the uniformity of plasma density which is usually a problem in the traditional microwave plasma system. The MPJCVD of this study can provide a plasma jet with a cross-section of about 1 cm and possesses a moveable seat to grow a large area of diamond films. This study pretreated silicon substrates with ultrasonic-energized diamond powders. In an atmosphere of 0.25% methane-to-hydrogen ratio, a diamond film with its grains of nearly 0.5 um can be successfully synthesized using a high temperature plasma jet under microwave powers of 600 W, 800 W, and 1000 W. The field emission scanning electron microscopy (FESEM), Raman spectrometer, X-ray diffractometer (XRD), and X-ray photoelectron spectrometer (XPS) are used to characterize the as-grown diamond films. The results show such sub-micron diamond films possess perfect crystals and grains of averaged 0.5 mum.