Industrial Internet of Things (IIoT) provides significant support for observing and controlling industrial machinery. In this paper, a novel hierarchical feature enhancement network (HFEN) is proposed by combining signal processing and representation learning. The signal processing is based on frequency and time frequency analysis, which extracts features with definite physical significance, whereas representation learning improves the representability of the physical features by connecting stacked denoising autoencoders and squeeze-and-excitation networks. A novel two-stream architecture is designed for HFEN to fuse two types of features. Consequently, HFEN can extract features that can be analyzed for physical significance and that are also representative in terms of recognizable patterns. The experimental results prove that the performance of HFEN is satisfactory in terms of accuracy and efficiency when compared to other methods. Finally, this study also aims to demonstrate the potential of a new pairing that fuses the model- and data-driven strategies for IIoT.

6D pose estimation of arbitrary objects is a crucial topic for intelligent transportation infrastructure measurement. However, some external environmental factors and the characteristics of the object itself impact the accuracy of the object’s pose estimation in practical applications. In this paper, we propose a new multi-class dataset ICD-4 (Industrial car Components Dataset) for 6D object pose estimation, which mainly includes four component categories, and every category takes 20,000 different scenarios. ICD-4 dataset delivers quite a few research challenges involving the range of object pose transformations and has significant research value for small-scale pose estimation tasks. We also propose an innovative method PoseMLP, a pose estimation network that uses residual MLP (multilayer perceptron) modules to predict the 6D pose estimation directly. Simultaneously, the experimental results demonstrate the effectiveness and reliability of the proposed method.

In the process of transportation, the handling and loading methods of rigid objects are becoming more and more perfect. However, whether in today's transportation system or in daily life, such as packing objects or sorting cables before transportation, the manipulation of deformable objects has been always inevitable and has attracted more and more attention. Due to the super degrees of freedom and the unpredictable physical state of deformed objects. It is difficult for robots to complete tasks under the environment of the deformable object. Therefore, we present a method based on imitation learning. In the generated expert demonstration, the agent is offered to learn the state sequence, and then imitate the expert's trajectory sequence which avoid the above-mentioned difficulties. In addition, compared with the baseline method, our proposed DN-Transporter Networks are more competitive in a simulation environment involving cloth, ropes or bags.

Optical coherence tomography (OCT) is being widely applied in clinical studies to investigate insight into the retina under the retinal pigment epithelium. Optical coherence tomography angiography (OCTA) is one of the functional extensions of OCT, for visualizing retinal circulation. Due to obstruction of light propagation, such as vitreous floaters or pupil boundaries, OCTA remains challenged by shadow artifacts that can disrupt volumetric data. Detecting and removing these shadow artifacts are crucial when quantifying indicators of retinal disease progression. We simplified an optical attenuation model of shadow formation in OCTA to a linear illumination transformation. And learn its parameters using an adversarial neural network. Our framework also consists of a sub-network for shadows automatic detection. We experimented our method on 28 OCTA images of normal eyes and compared the non-perfusion area (NPA), an index to measure retinal vascularity. The results showed that the NPA adjusted to a reasonable range after image processing using our method. Furthermore, we tested 150 OCTA images of synthesis artifacts, and the mean absolute error(MAE) values reached 0.83 after shadow removal.

Estimating dimensional measurements of the choroid provides diagnostic values which can be used to assess choroidal health. In this paper we describe a methodology of calculating measurements from choroid segmentations automatically generated using convolutional neural network (CNN). We use a three-dimensional (3D) U-Net architecture built from residual units to segment the choroid. A surface fitting phase is jointed to the main process to compensate segmented defects at the area of Optic Nerve Hypoplasia (ONH). Consequently, we process these segmentations to estimate the mean choroidal thickness(MCT). The model is evaluated on volumetric scans from 183 subjects, approximately half of which are thyroid eyes. In the choroidal layer segmentation experiment, the accuracy of the automatic segmentation algorithm proposed in this paper was 98.25% when comparing the manual segmentation results masked by doctors. It showed that the MCT in thyroid eyes were higher than those in normal eyes.

The temporal subtraction technique is a useful tool for computer aided diagnosis (CAD) in visual screening. The technique subtracts the previous image set from the current one for the same subject to emphasize temporal changes and/or new abnormalities. However, it is difficult to obtain a clear subtraction image without subtraction image artifacts. VoxelMorph in deep learning is a useful method, as preparing large training datasets is difficult for medical image analysis, and the possibilities of incorrect learning, gradient loss, and overlearning are concerns. To overcome this problem, we propose a new method for generating temporal subtraction images of thoracic multi-detector row computed tomography (MDCT) images based on ResidualVoxelMorph, which introduces a residual block to VoxelMorph to enable flexible positioning at a low computational cost. Its high learning efficiency can be expected even with a limited training set by introducing residual blocks to VoxelMorph. We performed our method on 84 clinical images and evaluated based on three-fold cross-validation. The results showed that the proposed method reduced subtraction image artifacts on root mean square error (RMSE) by 11.3% (p < 0.01), and its effectiveness was verified. That is, the proposed temporal subtraction method for thoracic MDCT improves the observer’s performance.