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: Disclosed is a high-precision dynamic real-time 360-degree omnidirectional point cloud acquisition method based on fringe projection. The method comprises: firstly, by means of the fringe projection technology based on a stereoscopic phase unwrapping method, and with the assistance of an adaptive dynamic depth constraint mechanism, acquiring high-precision three-dimensional (3D) data of an object in real time without any additional auxiliary fringe pattern; and then, after a two-dimensional (2D) matching points optimized by the means of corresponding 3D information is rapidly acquired, by means of a two-thread parallel mechanism, carrying out coarse registration based on Simultaneous Localization and Mapping (SLAM) technology and fine registration based on Iterative Closest Point (ICP) technology.

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 invention discloses a deep learning-based temporal phase unwrapping method for fringe projection profilometry. First, four sets of three-step phase-shifting fringe patterns with different frequencies (including 1, 8, 32, and 64) are projected to the tested objects. The three-step phase-shifting fringe images acquired by the camera are processed to obtain the wrapped phase map using a three-step phase-shifting algorithm. Then, a multi-frequency temporal phase unwrapping (MF-TPU) algorithm is used to unwrap the wrapped phase map to obtain a fringe order map of the high-frequency phase with 64 periods. A residual convolutional neural network is built, and its input data are set to be the wrapped phase maps with frequencies of 1 and 64, and the output data are set to be the fringe order map of the high-frequency phase with 64 periods. Finally, the training dataset and the validation dataset are built to train and validate the network.

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: Disclosed is a high-precision dynamic real-time 360-degree omnidirectional point cloud acquisition method based on fringe projection. The method comprises: firstly, by means of the fringe projection technology based on a stereoscopic phase unwrapping method, and with the assistance of an adaptive dynamic depth constraint mechanism, acquiring high-precision three-dimensional (3D) data of an object in real time without any additional auxiliary fringe pattern; and then, after a two-dimensional (2D) matching points optimized by the means of corresponding 3D information is rapidly acquired, by means of a two-thread parallel mechanism, carrying out coarse registration based on Simultaneous Localization and Mapping (SLAM) technology and fine registration based on Iterative Closest Point (ICP) technology.

Abstract: A flat-plate water-heating photovoltaic/thermal module and a production process thereof are disclosed. The flat-plate water-heating photovoltaic/thermal module includes a frame. The lower surface of the frame is provided with a heat preservation back plate. The upper surface of the frame is sequentially laminated with a glass cover plate, a first photovoltaic cell laminating adhesive, a photovoltaic cell slice, a second photovoltaic cell laminating adhesive, a transparent back plate, a third photovoltaic cell laminating adhesive and a heat absorbing component from top to bottom. A heat preservation cavity is formed between the heat preservation back plate and the heat absorption part.

Abstract: The invention discloses a three-dimensional (3D) measurement method based on end-to-end deep learning for speckle projection. First, the speckle pattern was projected by the projector and collected simultaneously by the stereo camera. The speckle images after stereo rectification are fed into the stereo matching network. A feature extraction sub-network based on shared weights processes the speckle images to obtain a series of low-resolution 3D feature tensors, The feature tensor is fed into the saliency object detection sub-network to detect foreground information in the speckle images, producing a full-resolution valid mask map. A 4D matching cost volume is generated using the feature tensor of both views based on the candidate disparity range, filtered by a series of 3D convolutional layers to achieve cost aggregation, so that the initial disparity map is obtained by disparity regression.

Abstract: This invention proposes a single-vector-based finite control set model predictive control for two parallel power converters, which adopts a centralized control structure to achieve accurate control of overall performance. It establishes predictive models for line currents and three phase-circulating currents and constructs a novel cost function that uses these currents as performance indices to implement the predictive control algorithm based on the proposed predictive models. The invention proposes dynamic weighting coefficients and adjustment principles to improve system control performance. A finite set output signal matrix containing important characteristic information of all alternative vectors is constructed to avoid redundant calculations in each control horizon, reducing computation time during practical implementation.

Abstract: The invention discloses a miniaturized, low-cost, multi-contrast label-free microscopic imaging system. The imaging system is based on an inverted microscopic structure, a highly integrated optical system is designed by adopting a micro lens having a fixed focal length, and a complex optical system of a traditional microscope system is replaced, such that the whole microscope is highly integrated. The system uses a programmable LED array as an illumination light source the LED array is controlled by a computer to display different illumination modes, six imaging functions of a bright field, a dark field a rainbow dark field, Rheinberg optical dyeing, differential phase contrast, and quantitative phase imaging are achieved; and diversified unmarked imaging methods are provided for biological applications.

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.