Deep Recyclable Trash Sorting Using Integrated Parallel Attention.

Sorting recyclable trash is critical to reducing energy consumption and mitigating environmental pollution. Currently, trash sorting heavily relies on manpower. Computer vision technology enables automated trash sorting.

TFDet: Target-Aware Fusion for RGB-T Pedestrian Detection.

Pedestrian detection plays a critical role in computer vision as it contributes to ensuring traffic safety. Existing methods that rely solely on RGB images suffer from performance degradation under low-light conditions due to the lack of useful information. To address this issue, recent multispectral detection approaches have combined thermal images to provide complementary information and have obtained enhanced performances.

Broadband lens and graphene/silicon photodiode for wide spectral imaging.

We designed a broadband lens along with a graphene/silicon photodiode for wide spectral imaging ranging from ultraviolet to near-infrared wavelengths. By using five spherical glass lenses, the broadband lens, with the modulation transfer function of 0.38 at 100 lp/mm, corrects aberrations ranging from 340 to 1700 nm.

Guided Colorization Using Mono-Color Image Pairs.

Compared to color images captured by conventional RGB cameras, monochrome (mono) images usually have higher signal-to-noise ratios (SNR) and richer textures due to the lack of color filter arrays in mono cameras. Therefore, using a mono-color stereo dual-camera system, we can integrate the lightness information of target monochrome images with the color information of guidance RGB images to accomplish image enhancement in a colorization manner. In this work, based on two assumptions, we introduce a novel probabilistic-concept guided colorization framework.

Induction of lncRNA MALAT1 by hypoxia promotes bone formation by regulating the miR-22-3p/CEBPD axis.

Adaptation to hypoxia promotes fracture healing. However, the underlying molecular mechanism remains unknown. Increasing evidence has indicated that long non-coding RNAs (lncRNAs) play crucial roles in several diseases, including fracture healing.

COMIRE: A Consistence-Based Mislabeled Instances Removal Method.

Training neural network classifiers (NNCs) usually requires all instances to be correctly labeled, which is difficult and/or expensive to satisfy in some practical applications. When label noise is present, mislabeled data will severely mislead the training of NNCs, resulting in poor generalization performance. In this work, we address the label noise issue by removing mislabeled instances from the training data.

Robustness improvement for cyber physical system based on an optimization model of interdependent constraints.

With the rapid development of information technology, traditional infrastructure networks have evolved into cyber physical systems (CPSs). However, this evolution has brought along with it cyber failures, in addition to physical failures, which can affect the safe and stable operation of the whole system. In light of this, in this paper, we propose an interdependence-constrained optimization model to improve the robustness of the cyber physical system.

Wavefront reconstruction based on deep transfer learning for microscopy.

The application of machine learning in wavefront reconstruction has brought great benefits to real-time, non-invasive, deep tissue imaging in biomedical research. However, due to the diversity and heterogeneity of biological tissues, it is difficult to train the dataset with a unified model. In general, the utilization of some unified models will result in the specific sample falling outside the training set, leading to low accuracy of the machine learning model in some real applications.

An asymmetric interdependent networks model for cyber-physical systems.

Cyber-physical systems (CPSs) are integrations of information technology and physical systems, which are more and more significant in society. As a typical example of CPSs, smart grids integrate many advanced devices and information technologies to form a safer and more efficient power system. However, interconnection with the cyber network makes the system more complex, so that the robustness assessment of CPSs becomes more difficult.

Lighting Deviation Correction for Integrating-Sphere Multispectral Imaging Systems.

In an integrating sphere multispectral imaging system, measurement inconsistency can arise when acquiring the spectral reflectances of samples. This is because the lighting condition can be changed by the measured samples, due to the multiple light reflections inside the integrating sphere. Besides, owing to non-uniform light transmission of the lens and narrow-band filters, the measured reflectance is spatially dependent.

Equivalent Continuous Formulation of General Hashing Problem.

Hashing-based approximate nearest neighbors search has attracted broad research interest, due to its low computational cost and fast retrieval speed. The hashing technique maps the data points into binary codes and, meanwhile, preserves the similarity in the original space. Generally, we need to solve a discrete optimization problem to learn the binary codes and hash functions, which is NP-hard.

Multispectral Image Super-Resolution via RGB Image Fusion and Radiometric Calibration.

Multispectral imaging is of wide application for its capability in acquiring the spectral information of scenes. Due to hardware limitation, multispectral imaging device usually cannot achieve high-spatial resolution. To address the issue, this paper proposes a multispectral image super-resolution algorithm, referred as SRIF, by fusing the low-resolution multispectral image and the high-resolution (HR) RGB image.

Machine learning guided rapid focusing with sensor-less aberration corrections.

Non-invasive, real-time imaging and deep focus into tissue are in high demand in biomedical research. However, the aberration that is introduced by the refractive index inhomogeneity of biological tissue hinders the way forward. A rapid focusing with sensor-less aberration corrections, based on machine learning, is demonstrated in this paper.

Distributed Graph Hashing.

Recently, hashing-based approximate nearest neighbors search has attracted considerable attention, especially in big data applications, due to its low computation cost and fast retrieval speed. In the literature, most of the existing hashing algorithms are centralized. However, in many large-scale applications, the data are often stored or collected in a distributed manner.

Dual inhibition of HY023016 based on binding properties of platelet membrane receptor subunit glycoprotein Ibα and thrombin exosites.

Thrombin has long been suggested as a desirable antithrombotic target, but anti-thrombin therapy without anti-platelet thereby has never achieved the ideal effect. HY023016 is a novel compound, in our previous study, it exerted better anti-thrombotic than dabigatran etexilate. The present study aims to illustrate the excess anti-thrombotic molecular mechanisms of HY023016 through thrombin anion exosites and the platelet membrane receptor subunit glycoprotein Ibα (GPIbα).

Bidirectional texture function image super-resolution using singular value decomposition.

The bidirectional texture function (BTF) is widely employed to achieve realistic digital reproduction of real-world material appearance. In practice, a BTF measurement device usually does not use high-resolution (HR) cameras in data collection, considering the high equipment cost and huge data space required. The limited image resolution consequently leads to the loss of texture details in BTF data.

Spectral bidirectional texture function reconstruction by fusing multiple-color and spectral images.

Spectral bidirectional texture function (BTF) is essential for accurate reproduction of material appearance due to its nature of conveying both spatial and spectral information. A practical issue is that the acquisition of raw spectral BTFs is time-consuming. To resolve the limitation, this paper proposes a novel framework for efficient spectral BTF acquisition and reconstruction.

Fast Multispectral Imaging by Spatial Pixel-Binning and Spectral Unmixing.

Multispectral imaging system is of wide application in relevant fields for its capability in acquiring spectral information of scenes. Its limitation is that, due to the large number of spectral channels, the imaging process can be quite time-consuming when capturing high-resolution (HR) multispectral images. To resolve this limitation, this paper proposes a fast multispectral imaging framework based on the image sensor pixel-binning and spectral unmixing techniques.

Empirical model for matching spectrophotometric reflectance of yarn windings and multispectral imaging reflectance of single strands of yarns.

The state-of-the-art multispectral imaging system can directly acquire the reflectance of a single strand of yarn that is impossible for traditional spectrophotometers. Instead, the spectrophotometric reflectance of a yarn winding, which is constituted by yarns wound on a background card, is regarded as the yarn reflectance in textile. While multispectral imaging systems and spectrophotometers can be separately used to acquire the reflectance of a single strand of yarn and corresponding yarn winding, the quantitative relationship between them is not yet known.

Photometric Stereo for General BRDFs via Reflection Sparsity Modeling.

This paper proposes a pixelwise photometric stereo method for object surfaces with general bidirectional reflectance distribution functions (BRDFs) via appropriate reflection modeling. The modeling is based on three general characteristics of reflection components, i.e.

Multispectral Image Out-of-Focus Deblurring Using Interchannel Correlation.

Out-of-focus blur occurs frequently in multispectral imaging systems when the camera is well focused at a specific (reference) imaging channel. As the effective focal lengths of the lens are wavelength dependent, the blurriness levels of the images at individual channels are different. This paper proposes a multispectral image deblurring framework to restore out-of-focus spectral images based on the characteristic of interchannel correlation (ICC).

Channel selection for multispectral color imaging using binary differential evolution.

In multispectral color imaging, there is a demand to select a reduced number of optimal imaging channels to simultaneously speed up the image acquisition process and keep reflectance reconstruction accuracy. In this paper, the channel selection problem is cast as the binary optimization problem, and is consequently solved using a novel binary differential evolution (DE) algorithm. In the proposed algorithm, we define the mutation operation using a differential table of swapping pairs, and deduce the trial solutions using neighboring self-crossover.

[Risk factors for delirium of elderly patients undergoing hip fracture operation].

Objective: To explore the causes for delirium of elderly patients after hip fracture operation.

Methods: A total of 68 cases of delirium were selected from 458 patients aged over 65 years undergoing hip fracture operation via spinal anesthesia from 2009 to 2011. There were 26 males and 42 females with an average age of 72.

Immediate reduction under general anesthesia and single-staged anteroposterior spinal reconstruction for fracture-dislocation of lower cervical spine.

Fracture-dislocation of the lower cervical spine is a severe traumatic lesion, most frequently resulting in tetraplegia. Treatment is usually painful and time consuming. This retrospective study evaluated the clinical curative effect of immediate reduction under general anesthesia and single-staged anteroposterior spinal reconstruction for fracture-dislocation of the lower cervical spine.