Abstract: A calibration method for fringe projection systems based on plane mirrors. Firstly, two mirrors are placed behind the tested object. Through the reflection of mirrors, the camera can image the measured object from the front and other two perspectives, so as to obtain 360-degree two-dimensional information of the measured object. The projector projects three sets of phase-shifting fringe patterns with frequencies of 1, 8, and 64. The camera captures the fringe image to obtain an absolute phase map with a frequency of 64 by using the phase-shifting method and the temporal phase unwrapping algorithm. By using the calibration parameters between the projector and the camera, the absolute phase map can be converted into three-dimensional information of the measured object. Then, the mirror calibration is realized by capturing a set of 3D feature point pairs, so that the 3D information from different perspectives is transformed into a unified world coordinate system.

Abstract: The present invention discloses an electrocatalytic Fenton oxidation-electrochemical oxidation coupling process and apparatus for efficient treatment of chemical wastewater, and belongs to the field of sewage treatment. The process includes an electrocatalytic Fenton oxidation step, an electrochemical oxidation step, and a pH adjustment step. A spacing between a cathode and an anode in the electrocatalytic Fenton oxidation step is controlled, so that oxygen produced at the anode reacts at the cathode to produce H2O2. The treatment requirements can be met without external aeration or external addition of H2O2, and meanwhile, the efficiency of COD removal by electro-Fenton oxidation is effectively improved. Further, by connecting a pH adjusting tank with the electrocatalytic Fenton oxidation-electrochemical oxidation coupling apparatus in series, a coupling treatment process with near-zero production of iron sludge is realized.

Abstract: A driver fatigue detection method based on combining a pseudo-three-dimensional (P3D) convolutional neural network (CNN) and an attention mechanism includes: 1) extracting a frame sequence from a video of a driver and processing the frame sequence; 2) performing spatiotemporal feature learning through a P3D convolution module; 3) constructing a P3D-Attention module, and applying attention on channels and a feature map through the attention mechanism; and 4) replacing a 3D global average pooling layer with a 2D global average pooling layer to obtain more expressive features, and performing a classification through a Softmax classification layer. By analyzing the yawning behavior, blinking and head characteristic movements, the yawning behavior is well distinguished from the talking behavior, and it is possible to effectively distinguish between the three states of alert state, low vigilant state and drowsy state, thus improving the predictive performance of fatigue driving behaviors.

Abstract: The present invention discloses a three-dimensional diffraction tomography microscopy imaging method based on LED array coded illumination. Firstly, acquiring the raw intensity images, three sets of intensity image stacks are acquired at different out-of-focus positions by moving the stage or using electrically tunable lens. And then, after acquiring the intensity image stacks of the object to be measured at different out-of-focus positions, the three-dimensional phase transfer function of the microscopy imaging system with arbitrary shape illumination is derived. Further, the three-dimensional phase transfer function of the microscopic system under circular and annular illumination with different coherence coefficients is obtained as well, and the three-dimensional quantitative refractive index is reconstructed by inverse Fourier transform of the three-dimensional scattering potential function. The scattering potential function is converted into the refractive index distribution.

Abstract: The present invention provides an information traceability method and system based on a blockchain. The method includes: receiving a traceability request, where the traceability request includes a type label, a time label, and a content label; accessing information path data pre-stored in the blockchain based on the type label to obtain target path data, where the target path data is single-source path data or multi-source path data; determining a corresponding primary data set based on the time label, where the target path data includes a plurality of primary data sets; determining a corresponding secondary data set based on the content label, where the primary data set includes at least one secondary data set; and extracting path information from the secondary data set, and obtaining at least one information source based on the path information.

Abstract: The disclosure is a three-dimensional towered checkerboard for multi-sensor calibration, and a LiDAR and camera joint calibration method based on the checkerboard.

Abstract: The present disclosure relates to a weakly supervised video activity detection method and system based on iterative learning. The method includes: extracting spatial-temporal features of a video that contains actions; constructing a neural network model group; training a first neural network model according to the class label of the video, a class activation sequence output by the first neural network model, and a video feature output by the first neural network model; training the next neural network model according to the class label of the video, a pseudo temporal label output by the current neural network model, a class activation sequence output by the next neural network model, and a video feature output by the next neural network model; and performing action detection on the test video according to the neural network model corresponding to the highest detection accuracy value.

Abstract: A driver fatigue detection method based on combining a pseudo-three-dimensional (P3D) convolutional neural network (CNN) and an attention mechanism includes: 1) extracting a frame sequence from a video of a driver and processing the frame sequence; 2) performing spatiotemporal feature learning through a P3D convolution module; 3) constructing a P3D-Attention module, and applying attention on channels and a feature map through the attention mechanism; and 4) replacing a 3D global average pooling layer with a 2D global average pooling layer to obtain more expressive features, and performing a classification through a Softmax classification layer. By analyzing the yawning behavior, blinking and head characteristic movements, the yawning behavior is well distinguished from the talking behavior, and it is possible to effectively distinguish between the three states of alert state, low vigilant state and drowsy state, thus improving the predictive performance of fatigue driving behaviors.

Abstract: A microscopic imaging method of phase contrast (PC) and differential interference contrast (DIC) based on the transport of intensity equation (TIE) includes capturing three intensity images along the optical axis; solving the TIE by deconvolution to obtain the quantitative phase; obtaining the intensity image under the DIC imaging mode according to the DIC imaging principle; and obtaining the corresponding phase image of PC imaging mode according to the PC imaging principle. The method can endow the bright-field microscope with the ability to realize PC and DIC imaging without complex modification of the traditional bright-field microscope. In addition, it has the same imaging performance as the phase contrast microscope and differential interference contrast microscope, which are expensive, complex-structure, and has strict environmental conditions.

Abstract: Disclosed are methods for the pre-treatment of lignocellulose by adding an alkali or acid reagent(s) during the densification thereof, and for the biotransformation thereof. In the method, an alkali reagent(s) or acid reagent(s) is added to a lignocellulosic raw material for a densification pre-treatment to form an alkali- or acid-containing densified lignocellulose with a compressed compact shape, thereby achieving the pre-treatment. The acid or alkali in the pre-treated lignocellulose can further pre-treat the lignocellulosic raw material in a mild manner during the subsequent transportation and storage processes. If a subsequent pre-treatment is needed, then the severity thereof is reduced substantially; in addition, the uniform mixing of the acid or alkali with the lignocellulose and a large density of the raw material promote a high efficiency and a high loading capacity of the subsequent pre-treatment of the densified lignocellulose. The method is simple and efficient.

Abstract: The invention discloses a single-frame fringe pattern analysis method based on multi-scale generative adversarial network. A multi-scale generative adversarial neural network model is constructed and a comprehensive loss function is applied. Next, training data are collected to train the multi-scale generative adversarial network. During the prediction, a fringe pattern is fed into the trained multi-scale network where the generator outputs the sine term, cosine term, and the modulation image of the input pattern. Finally, the arctangent function is applied to compute the phase. When the network is trained, the parameters of the network do not need to manually tune during the calculation. Since the input of the neural network is only a single fringe pattern, the invention provides an efficient and high-precision phase calculation method for moving objects.

Abstract: The invention discloses a programmable annular LED illumination-based high efficiency quantitative phase microscopy imaging method, the proposed method comprising the following steps: the derivation of system optical transfer function in a partially coherent illumination imaging system; the derivation of phase transfer function with the weak object approximation under the illumination of tilted axially symmetric coherent point illumination source; the extension of illumination from an axially symmetric coherence point source to a discrete annular point source, and the optical transfer function can be treated as an incoherent superposition of each pair of tilted axially symmetric coherent point sources. The acquisition of raw intensity dataset; the implementation of deconvolution for quantitative phase reconstruction.

Abstract: Provided is a method for preparing copper azide and cuprous azide encapsulated by conductive metal-organic framework. The method uses a conductive copper-containing metal-organic framework material as a precursor, and completes the azidation of the precursor by means of a liquid-solid electrochemical azidation reaction. Copper azide and cuprous azide nanocrystals are highly uniformly embedded within a conductive framework, which may effectively avoid the agglomeration of copper azide and cuprous azide, and reduce static charge generated by friction, displacement, and the like. Meanwhile, the conductive framework may promote the effective transfer of charge, avoid the accumulation of static charge, and improve the electrostatic safety.

Abstract: A single-shot differential phase contrast quantitative phase imaging method based on color multiplexing illumination. A color multiplexing illumination solution is used to realize single-shot differential phase contrast quantitative phase imaging. In the single-shot color multiplexing illumination solution, three illumination wavelengths of red, green, and blue are used to simultaneously illuminate a sample, and the information of the sample in multiple directions is converted into intensity information on different channels of a color image. By performing channel separation on this color image, the information about the sample at different spatial frequencies can be obtained.

Abstract: An intrusion detection method and system for Internet of Vehicles based on Spark and combined deep learning are provided. The method includes the following steps: S1: setting up Spark distributed cluster; S2: initializing the Spark distributed cluster, constructing a convolutional neural network (CNN) and long short-term memory (LSTM) combined deep learning algorithm model, initializing parameters, and uploading collected data to a Hadoop distributed file system (HDFS); S3: reading the data from the HDFS for processing, and inputting the data to the CNN-LSTM combined deep learning algorithm model, for recognizing the data; and S4: dividing the data into multiple resilient distributed datasets (RDDs) for batch training with a preset number of iterations.

Abstract: The patent discloses a differential phase contrast (DPC) quantitative phase microscopy method based on the optimal illumination pattern design. Firstly, the optimal illumination pattern corresponding to the isotropic phase transfer function of DPC quantitative phase imaging is derived, which is determined as a semi-annular illumination pattern with the illumination numerical aperture NAill equal to the numerical aperture NAobj of the objective lens. The illumination intensity distribution varies with the cosine of the illumination angle, and it can be expressed as S(?)=cos(?). This patent effectively compensates for the frequency loss of phase transfer, not only the high-frequency responses of PTF are enhanced, but also the transfer responses of low-frequency phase information is significantly improved.

Abstract: A calibration method for fringe projection systems based on plane mirrors. Firstly, two mirrors are placed behind the tested object. Through the reflection of mirrors, the camera can image the measured object from the front and other two perspectives, so as to obtain 360-degree two-dimensional information of the measured object. The projector projects three sets of phase-shifting fringe patterns with frequencies of 1, 8, and 64. The camera captures the fringe image to obtain an absolute phase map with a frequency of 64 by using the phase-shifting method and the temporal phase unwrapping algorithm. By using the calibration parameters between the projector and the camera, the absolute phase map can be converted into three-dimensional information of the measured object. Then, the mirror calibration is realized by capturing a set of 3D feature point pairs, so that the 3D information from different perspectives is transformed into a unified world coordinate system.

Abstract: A method for vehicle detection based on single-axis geomagnetic sensor is disclosed. The method includes the following: arranging two geomagnetic sensors in tandem at a fixed distance in the same lane, and acquiring, by the two geomagnetic sensors, data when a vehicle passes by; performing data cleansing and denoising on the data acquired by the geomagnetic sensors; detecting, by the geomagnetic sensors, the vehicle by using an state machine algorithm based on a fixed threshold, and extracting moments when the vehicle enters and leaves detection ranges of the sensors; and collecting statistics on traffic flow in a predetermined period of time, and calculating the velocity and length of the vehicle. The presently disclosed method and apparatus can be independently used to obtain vehicle parameters at important traffic sections or intersections, or can be used in combination with other traffic detection devices to obtain more comprehensive traffic information.

Abstract: The invention claims a microscopic imaging method of phase contrast (PC) and differential interference contrast (DIC) based on the transport of intensity equation (TIE). Firstly, three intensity images are captured along the optical axis; secondly, TIE is solved by deconvolution to obtain the quantitative phase; then, the intensity image under the DIC imaging mode is obtained according to the DIC imaging principle; finally, the corresponding phase image of PC imaging mode is obtained according to the PC imaging principle. The proposed approach can endow the bright-field microscope with the ability to realize PC and DIC imaging without complex modification of the traditional bright-field microscope. In other words, this method only needs to use the traditional bright-field microscope without adding any complex hardware. Through the PC and DIC algorithms, this method has the advantages of quantitative, high-speed, low-cost, simple structure, and less external interference.

Abstract: The present invention discloses a three-dimensional diffraction tomography microscopy imaging method based on LED array coded illumination. Firstly, acquiring the raw intensity images, three sets of intensity image stacks are acquired at different out-of-focus positions by moving the stage or using electrically tunable lens. And then, after acquiring the intensity image stacks of the object to be measured at different out-of-focus positions, the three-dimensional phase transfer function of the microscopy imaging system with arbitrary shape illumination is derived. Further, the three-dimensional phase transfer function of the microscopic system under circular and annular illumination with different coherence coefficients is obtained as well, and the three-dimensional quantitative refractive index is reconstructed by inverse Fourier transform of the three-dimensional scattering potential function. The scattering potential function is converted into the refractive index distribution.