Symbiotic radio (SR) is a promising technology to achieve ultra-low-power transmission for the next generation wireless network. However, its enabling technique, ambient backscatter transmission, suffers from double fading and path loss that severely restricts its service range. In this work, the reconfigurable holographic surface (RHS) is introduced at the transmitter to tackle this problem. Unlike the widely studied reconfigurable intelligent surface (RIS), the RHS that uses amplitude control can offer higher integration and lower power consumption. Seeing that the treatment of the direct-link interference in the received signal is the key problem for the receiver of the backscatter devices to achieve successful signal detection, we propose two strategies. InStrategy I, the ambient data symbol is detected for canceling the direct-link interference, while inStrategy II, we design the data stream sent by the ambient transmitter and its transmission frame in collaboration with zero-forcing beamforming to alleviate the interference among all ambient users and backscatter devices. Based on the two strategies, respectively, problems are formulated to jointly optimize the transmit power, the digital beamforming, and the holographic beamforming of the RHS such that the energy efficiency of the SR network (SRN) is maximized. For each of the two problems, we develop specific hybrid beamforming algorithm that decomposes the original problem into three sub-problems. These sub-problems respectively optimize the transmit power, the digital beamforming, and the holographic beamforming that are solved in an alternative manner. Simulation results verify that the proposed strategies can well exploit the potential of the RHS in enhancing the transmission performance of the SRN.

Symbiotic radio is an energy- and spectrum-efficient transmission technology to achieve seamless connection in the next generation wireless network. To tackle the transmission distance limitation of the backscatter devices (BD) in the symbiotic radio network (SRN), in this work, reconfigurable holographic surface (RHS) is introduced to accommodate the multiple BDs by assisting their concurrent transmission. Compared to the traditional reconfigurable intelligent surface, RHS has the advantages of higher energy efficiency and integration with lower hardware cost. An optimization problem is formulated to jointly optimize the digital beamforming of the radio-frequency chains and the holographic pattern of the RHS such that the achievable sum rate of the received signal at the sink node (SN) which is used to collect the information of all the BDs is maximized under the achievable-rate constraint of the ambient mobile user. This challenging non-convex problem is transformed into semi-definite programming by successive convex approximation and sequential parametric convex approximation, which are solved in an alternating way. The effectiveness of using the RHS to assist the concurrent transmission of the multiple BDs in the SRN has been validated by the numerical results.

Distributed big data and digital healthcare technologies have great potential to promote medical services, but challenges arise when it comes to learning predictive model from diverse and complex e-health datasets. Federated Learning (FL), as a collaborative machine learning technique, aims to address the challenges by learning a joint predictive model across multi-site clients, especially for distributed medical institutions or hospitals. However, most existing FL methods assume that clients possess fully labeled data for training, which is often not the case in e-health datasets due to high labeling costs or expertise requirement. Therefore, this work proposes a novel and feasible approach to learn a Federated Semi-Supervised Learning (FSSL) model from distributed medical image domains, where a federated pseudo-labeling strategy for unlabeled clients is developed based on the embedded knowledge learned from labeled clients. This greatly mitigates the annotation deficiency at unlabeled clients and leads to a cost-effective and efficient medical image analysis tool. We demonstrated the effectiveness of our method by achieving significant improvements compared to the state-of-the-art in both fundus image and prostate MRI segmentation tasks, resulting in the highest Dice scores of 89.23% and 91.95% respectively even with only a few labeled clients participating in model training. This reveals the superiority of our method for practical deployment, ultimately facilitating the wider use of FL in healthcare and leading to better patient outcomes.

Automatic welding of complex joints relies on scanning and inspection of the actual joint geometry, which is important for welding path planning and welding parameter setting. A robotic vision inspection system is presented in this paper to assess the geometry of complex joints before welding. The system can scan the joint with high accuracy and high resolutions via accurate system calibration and fast data synchronization. The scanned joint geometry is inspected to assess the quality of critical dimensions. Critical features are extracted for path planning, and the joint surface is segmented into different regions for assigning different welding parameters. Experimental results based on straight-joint and Y-joint are presented to show how the proposed system works.

Visual inspection involves dimensional inspection and surface inspection. Dimensional inspection is usually achieved via comparing the scanned model of the inspection target with the CAD model to detect dimensional defects such as bending and missing material. Surface inspection is usually based on textures via image processing and analysis to detect defects such as pitting, crack, scratch, and corrosion. Existing systems used fixed predefined viewpoints to capture geometry and texture from the object. However, defects may appear at different locations, distinguishable defect features may not be captured by the fixed viewpoints. Thus, dynamical planning of the viewpoints is desired to provide better sensing parameters adaptive to actual local geometry, appearance and lighting conditions. This paper proposes a new robotic sensing framework for adaptive visual inspection. Viewpoints are planned based on individual object adaptive to different defect locations. Sensor parameters at each viewpoints are adaptive to the surface conditions for optimized geometry/image quality. Data from all viewpoints are fused together to provide an adaptive model.

In this paper, we proposed an automatic crack detection method based on deep convolutional neural network -U-Net [4]. Unlike existing machine learning based crack detection methods, we can process an image as a whole without patchifying, thanks to the encoder-decoder structure of U-Net. The segmentation result is output from the network as a whole, instead of aggregation from neighborhood patches. In addition, a new cost function based on distance transform is introduced to assign pixel-level weight according to the minimal distance to the ground truth segmentation. In experiments, we test the proposed method on two datasets of road crack images. The pixel-level segmentation accuracy is above 92% which outperforms other state-of-the-art methods significantly.

In a 3-D scanning task, a robot-sensor system controls a robotic arm to move a laser sensor. In order to align the coordinate system of the robotic arm and laser sensor, prior calibration is required to derive the transformation between both coordinate systems. This paper proposes a new calibration method in three steps: manual data collection, sensing data calculation, and transformation solution. First, at least four data are required to be collected by the user. The sensing data are then calculated from the collected data and adopted to provide the desired transformation. The proposed algorithm has two features: arbitrary placement of planar disk and noise tolerant. Using a planar disk, the algorithm will automatically derive the angular relationship between the disk and the sensor plane, enabling arbitrary orientation placement. Noise tolerant is guaranteed by fitting ellipses during the sensing data calculation and using a single set of sensing data in transformation solution. Experiments and comparisons are given to demonstrate the efficiency of the proposed calibration algorithm.Note to Practitioners—This paper was motivated by the problem of calibrating a laser sensor and a positioning device (robot arm, CMM, etc.) in a robust and fast manner. Specifically, the calibration is to derive the transformation by aligning the sensors coordinate system to the positioning devices coordinate system. The proposed calibration procedure consists of two parts: manual data collection and automatic transformation calculation. During manual data collection, users only need to select four different data; whereby each data contains of two positions with the same orientation. Then, the desired transformation will be derived automatically. The calibration is designed in an efficient and robust way whereby: 1) data collection is done using a simple planar disk placed in arbitrary orientations; 2) minimum human interaction required; 3) tolerant to noise in the sensor data; and 4) easy implementation by following a proven and standard protocol.

This paper concerns multiphase piecewise smooth image segmentation with intensity inhomogeneities. Traditional methods based on the Mumford-Shah (MS) model require solving complicated diffusion equations evolving in irregular subdomains, leading to significant difficulties in efficient and accurate segmentation, especially in multiphase scenarios. In this paper, we propose a general framework to modify the MS model by using smoothing operators that can avoid the complicated implementation and inaccurate segmentation of traditional approaches. A detailed analysis connecting the smoothing operators and the diffusion equations is given to justify the modification. In addition, we present an efficient algorithm based on the direct augmented Lagrangian method, which requires fewer parameters than the commonly used augmented Lagrangian method. Typically, the smoothing operator in the general model is chosen to be Gaussian kernel, the bilateral kernel, and the directional diffusion kernel, respectively. Ample numerical results are provided to demonstrate the efficiency and accuracy of the modified model and the proposed minimization algorithm through various comparisons with existing approaches.

We propose a cascaded and a contrario hole crack detection (CHORD) method for defect inspection in digital images of turbine blade surfaces. This is the first time an automatic image processing-based method is proposed for such a task. It consists of two major steps: first, the appearance of holes is approximated by ellipses and cascaded pose regression is used to estimate the position and orientation of the holes; Second, we define hole cracks as geometrical structures and a contrario method is used to assess the meaningfulness of each crack. The model-based CHORD method fully considers the features of hole cracks including the characteristics of brightness, length, and orientation, and therefore can accurately detect cracks in the images. The threshold on the strength of cracks is determined automatically and the computational time is about five seconds for each image.

Laser stripe extraction is essential to 3D reconstructions of objects by triangulation laser scanning. Industrial applications require robustness against the spurious points due to multiple reflections among reflective and uneven surfaces. Our approach is a three-stage algorithm, which first detects the potential laser stripe regions, then ranks the regions on their corrected scene irradiance densities, and finally conducts the column-wise peak detection using the region ranking. The proposed method is evaluated in terms of speed, accuracy and robustness on both simulations and a real application for steel groove inspection.

Variational image segmentation based on the Mumford-Shah model requires to solve the heat diffusion equations in evolving irregular subdomains. It brings about significant difficulties in efficient and accurate segmentation, especially, in multi-phase scenarios. In this paper, we propose a new Mumford-Shah type model involving a smoothing operator, acting a similar role as the diffusion process and avoiding complicated computation. We introduce two simplified numerical models based on the Gaussian operator and the bilateral operator respectively, and provide efficient numerical algorithms to solve both segmentation problems. Numerical validation experiments on various images show better accuracy and robustness over existing methods.

Image segmentation is to separate the image domain into sub-domains according to some optimization rule. Variational level-set image segmentation based on the Mumford-Shah model, together with level set formulation, leads to complicate implementation and expensive computational time. To overcome the difficulty in solving the complex coupled level set functions and handle any number of phases in the image, we improve the region-base active contour model in this paper. We formulate the image segmentation as a new multiphase minimization problem to handle images containing any integer phases of intensities. We also propose efficient numerical algorithms to solve such optimization problem without extra steps of convex relaxation. Numerical validation experiments on various images show better accuracy and robustness over existing methods.

Image segmentation is to separate the image domain into local regions. Implicit active contour models via the level-set method can provide smooth and closed contours. The major category is based on the Mumford-Shah image component decomposition model. Approximating the image domain by a set of homogeneous regions, segmentation based on the piecewise constant (PC) models fail in intensity inhomogeneous images. Requiring intensity smoothness in local regions, segmentation based on the piecewise smooth (PS) models can perform better for intensity inhomogeneity than those PC based. Existing PS-based techniques are inefficient and not robust to complicate intensity scenarios with noise. Here we introduce a new functional model by decomposing an image into three parts: PS components, PC components and noise components. We convexify the decomposition model by incorporating with relaxation techniques and optimize the PS components over the whole image domain. New numerical algorithms are also proposed to implement the above approaches efficiently. Numerical validation experiments show that the proposed approaches can achieve much faster, more robust and more accurate image segmentation than existing arts.

Computer-based boundary detection in Echocardiographic Images is a challenging problem, due to the large amount of noise and the poor contrast presented. In this paper, a Markovian level set method is proposed for boundary detection in long-axis echocardiographic images. It combines MRF model which makes use of local statistics with level set method which handles topological changes, to ensure that the resulting boundary is continuous and smooth. Experimental results show that high accuracy is achieved with the proposed method.

Owing to the large amount of speckle noise and ill-defined edges present in echocardiographic images, computer-based boundary detection of the left ventricle (LV) has proved to be a challenging problem. In this paper, a Markovian level set method for boundary detection in long-axis echocardiographic images is proposed. It combines MRF model which makes use of local statistics with level set method which handles topological changes, to detect a continuous and smooth LV boundary. Experimental results show that high accuracy is achieved with the proposed method. The experimental results are also compared with two related MRF-based methods to demonstrate its superiority.

Snakes, or active contour models, have been widely used in image segmentation. However, most present snake models do not discern between positive and negative step edges. In this paper, a new type of dynamic external force for snakes named dynamic directional gradient vector flow (DDGVF) is proposed that uses this information for better performance. It makes use of the gradients in both x and y directions and deals with the external force field for the two directions separately. In snake deformation, the DDGVF field is utilized dynamically according to the orientation of snake in each iteration. Experimental results demonstrate that the DDGVF snake provides a much better segmentation than GVF snake in situations when edges of different directions are present which pose confusion for segmentation.

In this paper, an automated method of boundary detection of the left ventricle (LV) is proposed. The method uses a watershed transform and morphological operation to locate the region containing the LV, then performs snake deformation with a multiscale directional edge map for the detection of the endocardial boundary of the LV.