The application of power over Ethernet (PoE)-enabled lighting has emerged as a groundbreaking technology with the potential to achieve cooperative control and create an energy-saving lighting network. However, fine-gr...
详细信息
We propose a design of a bandpass-filter-integrated metalens for the gas sensing. A device with both filtering and focusing functions is designed, by integrating a one-dimensional photonic crystal and a metalens. It h...
详细信息
Automatic acne detection can help people more quickly detect acne disease. At present, most of the researches are based on two-stage detectors, and the researches based on single-stage detectors are very few. However,...
Automatic acne detection can help people more quickly detect acne disease. At present, most of the researches are based on two-stage detectors, and the researches based on single-stage detectors are very few. However, smaller and faster models are required in practical applications. In this paper, we build a faster and more accurate acne detection model based on YOLOX. First, we propose an Attention Enhanced Feature Pyramid network (AEFPN) to improve the efficiency and quality of feature fusion. It works by controlling the delivery of feature information and using attention. Then, we propose a stronger data augmentation strategy named MixAug, which uses Copy-Paste and Mixup by turning with a certain probability to make the model converging faster and the training curve smoother. In addition, to assign higher quality samples for small objects, we use Normalized Wasserstein Distance to improve the label assignment strategy called Simplified Optimal Transport Assignment (SimOTA). Finally, we conducted a number of experiments on the AcneSCU dataset. The results demonstrate the proposed method could improve the performance of YOLOX in acne detection, allowing YOLOX to increase 2.62% average precision (AP). At the same time, it can effectively improve the convergence speed of the model. Our model is superior to the current research in model size, detection speed and accuracy.
In this paper,we present an edge detection scheme based on ghost imaging(GI)with a holistically-nested neural *** so-called holistically-nested edge detection(HED)network is adopted to combine the fully convolutional ...
详细信息
In this paper,we present an edge detection scheme based on ghost imaging(GI)with a holistically-nested neural *** so-called holistically-nested edge detection(HED)network is adopted to combine the fully convolutional neural network(CNN)with deep supervision to learn image edges *** data are used to train the HED network,and the unknown object’s edge information is reconstructed from the experimental *** experiment results show that,when the compression ratio(CR)is 12.5%,this scheme can obtain a high-quality edge information with a sub-Nyquist sampling ratio and has a better performance than those using speckle-shifting GI(SSGI),compressed ghost edge imaging(CGEI)and subpixel-shifted GI(SPSGI).Indeed,the proposed scheme can have a good signal-to-noise ratio performance even if the sub-Nyquist sampling ratio is greater than 5.45%.Since the HED network is trained by numerical simulations before the experiment,this proposed method provides a promising way for achieving edge detection with small measurement times and low time cost.
Robots equipped with multi-modal sensing capabilities play an important role in the Internet of Robotic Things (IoRT), especially in emergency rescue. However, existing rescue robots pose challenges for human operator...
详细信息
Coverage enhancement is one of the hot research topics in wireless multimedia sensornetworks. A novel Coverage-enhancing algorithm based on three-dimensional Directional perception and co-evolution (DPCCA) is propose...
详细信息
Coverage enhancement is one of the hot research topics in wireless multimedia sensornetworks. A novel Coverage-enhancing algorithm based on three-dimensional Directional perception and co-evolution (DPCCA) is proposed in multimedia sensornetworks on the basis of the model whose pitch angle and deviation angle can be adjusted. Based on the proposed elliptical cone sensing model, we can derive the coverage area of the node and calculate the optimal pitch angle according the information of monitoring area and the nodes, and then the deviation angle is optimized based on co-evolution algorithm, which eliminate the overlapped and blind sensing area effectively. A set of simulations demonstrate the effectiveness of our algorithm in coverage ratio.
There are many methods and principles of satellite interference source location, but no matter which method is chosen, the positioning equation is nonlinear. Therefore, it is very important to solve the nonlinear equa...
详细信息
In this study, a viable platform for atom traps using a dielectric-loaded surface-plasmon-polariton waveguide is proposed. A trap depth of 0.239 mK can be achieved above a SiO2 waveguide on an Au-SiO2 substrate, with ...
详细信息
In this study, a viable platform for atom traps using a dielectric-loaded surface-plasmon-polariton waveguide is proposed. A trap depth of 0.239 mK can be achieved above a SiO2 waveguide on an Au-SiO2 substrate, with mode powers of 0.5mW for the blue-detuned TM0 mode, 0.1mW for the TM1 mode, and 0.55mW for the red-detuned TM0 mode. The trap center is about 180 nm above the waveguide surface, and the corresponding cooperativity parameter for coupling the Rb87 atom with a guided photon is about 0.137. By controlling the phase difference between counterpropagating red-detuned TM0 modes, atoms can be delivered along the waveguide by an optical conveyor belt. Compared to the dielectric waveguide without the enhancement of surface plasmon polaritons, our scheme has the advantage of forming a trap depth with low-power requirements and stronger atom-photon interactions, which makes it highly suitable for applications in photonic-atomic chips.
Measurement-device-independent quantum key distribution(MDI-QKD)provides us a powerful approach to resist all attacks at detection *** the unconditional security,people also seek for high key generation rate,but MDI-Q...
详细信息
Measurement-device-independent quantum key distribution(MDI-QKD)provides us a powerful approach to resist all attacks at detection *** the unconditional security,people also seek for high key generation rate,but MDI-QKD has relatively low key generation *** this paper,we provide an efficient approach to increase the key generation rate of MDI-QKD by adopting multiple degrees of freedom(DOFs)of single photons to generate *** with other high-dimension MDI-QKD protocols encoding in one DOF,our protocol is more flexible,for our protocol generating keys in independent subsystems and the detection failure or error in a DOF not affecting the information encoding in other *** on above features,our MDI-QKD protocol may have potential application in future quantum comniunication field.
LoRa is one of the most prominent Low-Power Wide-Area network (LPWAN) technologies, to accommodate pervasive Internet-of-Things (IoT) connectivities. However, its service capacity and scalability are limited due to th...
详细信息
暂无评论