Abstract: A cultivated land recognition method in a satellite image includes: segmenting a satellite image of the Earth into a plurality of standard images; and recognizing cultivated land area in each of the standard images using a cultivated land recognition model to obtain a plurality of first images. Edges of ground level entities in each of the standard images are detected using an edge detection model to obtain a plurality of second images. Each of the first images and a corresponding one of the second images is merged to obtain a plurality of third images; and cultivated land images is obtained by segmenting each of the third images using a watershed segmentation algorithm. Not only can a result of recognizing cultivated land in satellite images of the Earth be improved, but an efficiency of recognizing the cultivated land also be improved. A computing device employing the method is also disclosed.

Abstract: A device providing intelligent assistance in mobility for disabled people and others includes a mobility device and a lifting device detachably mounted on the mobility device. The lifting device includes a base frame, a retractable bracket structure, several wheels, a sitting pad, and a backrest. The wheels are mounted on a lower surface of the base frame and drive the lifting device to move. The retractable bracket structure is mounted on an upper surface of the base frame. The sitting pad is detachably mounted on the retractable bracket structure, and the backrest is rotatably mounted on the retractable bracket structure.

Abstract: In a crop identification method, multi-temporal sample remote sensing images labeled with first planting blocks of a specific crop are acquired. NDVI data of the sample remote sensing images are calculated. Noise of the NDVI data is reduced. A first multivariate Gaussian model is fitted based on de-noised NDVI data of the sample remote sensing image. Multi-temporal target remote sensing images are acquired. An NDVI time series of each pixel in the target remote sensing image is constructed. The NDVI time series is input to the first multivariate Gaussian model to obtain a likelihood value of each pixel displaying the specific crop in the remote sensing images. Second planting blocks of the specific crop in the target remote sensing images are determined accordingly. An accurate and robust identification result is thereby achieved.

Abstract: In a face swap method carried out by an electronic device, a first head image is segmented from a destination image. First facial landmarks and a first hair mask are obtained according to the first head image. A second head image is segmented from a source image. Second facial landmarks and a second hair mask are obtained according to the second head image. If at least one eye landmark in the second facial landmarks is covered by hair, the second head image and the second hair mask are processed and repaired so as to obtain a swapped-face image with eyes not covered by hair.

Abstract: A method for generating a model for facial sculpture based on a generative adversarial network (GAN) includes training a predetermined GAN based on a three dimensional (3D) face dataset of multiple 3D face images to obtain an initial sculpture generation model. A curvature conversion on each of the multiple 3D face images is performed to obtain a distribution map of curvature value and the distribution map of curvature value of each of the multiple 3D face images is added as attention information to the initial sculpture generation model, to train and generate a face sculpture generation model. A target 3D face data and predetermined face curvature parameters are received, and the target 3D face data and the predetermined face curvature parameters are inputted into the face sculpture generation model to generate a face sculpture model. A computing device using the method is also provided.

Abstract: In a method for training an image generation model, a first generator generates a first sample matrix, a first converter generates a sample contour image, a first discriminator optimizes the first generator and the first converter, a second generator generates a second sample matrix according to the first sample matrix, a second converter generates a first sample grayscale image, a second discriminator optimizes the second generator and the second converter, a third generator generates a third sample matrix according to the second sample matrix, a third converter generates a second sample grayscale image, a third discriminator optimizes the third generator and the third converter, a fourth generator generates a fourth sample matrix according to the third sample matrix, a fourth converter generates a sample color image, and a fourth discriminator optimizes the fourth generator and the fourth converter. The image generation model can be trained easily.

Abstract: In a method for training an image generation model, a first generator generates a first sample matrix, a first converter generates a sample contour image, a first discriminator optimizes the first generator and the first converter, a second generator generates a second sample matrix according to the first sample matrix, a second converter generates a first sample grayscale image, a second discriminator optimizes the second generator and the second converter, a third generator generates a third sample matrix according to the second sample matrix, a third converter generates a second sample grayscale image, a third discriminator optimizes the third generator and the third converter, a fourth generator generates a fourth sample matrix according to the third sample matrix, a fourth converter generates a sample color image, and a fourth discriminator optimizes the fourth generator and the fourth converter. The image generation model can be trained easily.

Abstract: A vehicle damage detection method based on image analysis, an electronic device, and a storage medium are provided. In the vehicle damage detection method, query images are obtained by filtering received images through a pre-trained Single Shot MultiBox Detector (SSD) object detection model, and a feature vector of each of the query images is obtained by inputting each of the query images into a residual network. Target output data is obtained using a Transformer model, similar images of the query images are obtained by processing the target output data using a pre-trained similarity judgment model. Loss of a current vehicle damage assessment case is evaluated based on similar cases, and evaluated loss is outputted. By utilizing the vehicle damage detection method, effectiveness of the vehicle damage detection is improved, and automatic evaluation of a loss is achieved.

Abstract: An image generation method and a computing device using the method, includes creating an image database with a plurality of original images, and obtaining a plurality of first outline images of an object by detecting an outline of the object in each of the original images. Numerous first feature matrixes are obtained by calculating a feature matrix of each of the first outline images. A second feature matrix of a second outline image input by a user is calculated. A target feature matrix is selected from the plurality of first feature matrixes, the target feature matrix has a minimum difference as the second feature matrix. A target image corresponding to the target feature matrix is matched and displayed from the image database. The method and device allow detection of an object outline in an image input by users and the generation of an image with the detected outline.

Abstract: An image generation method and a computing device employing the method includes: acquiring a plurality of original images; and processing the plurality of original images to obtain a training data set. An anti-neural network model is trained according to the training data set. A candidate image is generated through the trained anti-neural network model. The candidate image is complemented through a detail completion network model to obtain a target image according to a comparison image. Thereby, a style of the generated image is the same as that of the comparison image. A more realistic image can be randomly generated saving the time and energy of artificially creating an image.

Abstract: The present disclosure provides a primary frequency modulation method for a wind turbine, which may include: detecting a current frequency of a power grid; determining an instruction value of a power change amount for a primary frequency modulation by a first determining process when the current frequency of the power grid is less than a standard frequency of the power grid, wherein the first determining process may include: determining a reference value of the power change amount for the primary frequency modulation based on the current frequency; and when it is determined that currently there is an active power headroom for the wind turbine, comparing the reference value with a current active power headroom value of the wind turbine and determining the instruction value of the power change amount for the primary frequency modulation; and performing the primary frequency modulation based on the instruction value of the power change amount.

Abstract: A method for generating a model for facial sculpture based on a generative adversarial network (GAN) includes training a predetermined GAN based on a three-dimensional (3D) face dataset of multiple 3D face images to obtain a curvature map generation model and training a predetermined image translation model based on dataset of multiple image pairs to obtain a height map generation model. Target 3D face data is received, and the target 3D face data is inputted into the curvature map generation model to generate a target curvature map, and the target curvature map is inputted to the height map generation model to generate a target height map. The target height map is performed a 3D reconstruction to obtain a facial sculpture model corresponding to the target 3D face data. A computing device using the method is also provided.

Abstract: In an embodiment, a semiconductor apparatus comprises: a semiconductor chip, a substrate, and a bonding layer located between the semiconductor chip and the substrate that bonds the semiconductor chip and the substrate, wherein the bonding layer comprises sintered metal that comprises a plurality of voids, and wherein at least a portion of the plurality of voids are filled with a specific material having fluidity at a temperature higher than a preset temperature and is curable after being heated and melted.

Abstract: A liquid crystal display device and a backlight module are provided. The backlight module includes a frame, a light source, and a light guide plate. The light guide plate includes a light incident surface, a bottom portion and a top portion. The frame includes a lateral plate disposed opposite to the light incident surface. The light source includes a flexible printed circuit and a LED, and the flexible printed circuit includes a vertical portion and a first horizontal portion, wherein the vertical portion is disposed between the lateral plate and the light incident surface, the LED is disposed on a surface of the vertical portion facing the light guide plate, and the first horizontal portion is a part of the vertical portion bending toward the light guide plate. By practice of the disclosure, the narrow border design of the liquid crystal display device could be achieved.

Abstract: The present disclosure provides a liquid crystal display and a backlight module which includes a reflective sheet, a light guide plate disposed on the reflective sheet, an optical assembly and a light source assembly, the light guide plate including a light guide portion and a support portion disposed to surround the light guide portion, and the optical assembly being located on a top of the light guide portion; and the light source assembly including a plurality of LEDs which are disposed between the support portion and the light guide portion and disposed to be opposite to an incident surface of the light guide portion. The light guide plate according to the present disclosure includes a light guide portion and a support portion disposed to surround the light guide portion, wherein the support portion is used to support the display module and fix the backlight module, thereby omitting a rubber frame.

Abstract: The present disclosure relates to an end effector instrument. The end effector instrument may include an end effector device. The end effector device may include a clip and a resilient portion including a connecting hole and a limiting convex. The end effector instrument may further include a delivery device including a sheath and a shaft. The sheath may include a passage that accommodates the shaft. A distal end of the shaft may include a connecting end. The sheath may include a limiting concave. The connecting end may extend into or exit from the connecting hole when the sheath is set outside the resilient portion: when the connecting end extends into the connecting hole, the resilient portion may expand outward, and the limiting convex may extend into the limiting concave; when the connecting end exits from the connecting hole, the resilient portion may rebound, and the limiting convex may exit from the limiting concave.

Abstract: A liquid crystal display device and a backlight module are provided. The backlight module includes a frame, a light source, and a light guide plate. The light guide plate includes a light incident surface, a bottom portion and a top portion. The frame includes a lateral plate disposed opposite to the light incident surface. The light source includes a flexible printed circuit and a LED, and the flexible printed circuit includes a vertical portion and a first horizontal portion, wherein the vertical portion is disposed between the lateral plate and the light incident surface, the LED is disposed on a surface of the vertical portion facing the light guide plate, and the first horizontal portion is a part of the vertical portion bending toward the light guide plate. By practice of the disclosure, the narrow border design of the liquid crystal display device could be achieved.

Abstract: A display module and a display device are provided. The display module comprises a liquid crystal display panel, a backlight module, a single-sided adhesive layer, the liquid crystal display panel is positioned on the backlight module, the backlight module comprising a top side and a bottom side opposite positioned on the top side, and four lateral sides located between the top side and the bottom side, the single-sided adhesive layer is adhesive and covering surface of the bottom side and surface of the four lateral sides. Using the display module could narrow the frame of display module, and achieves to full screen. It also could let thickness of the display module become thinner and lighter.

Abstract: The present disclosure provides a backlight module, which includes: a transparent light guiding body having a light incidence side surface and a sealed accommodating cavity; a plurality of quantum dots accommodated in the accommodating cavity; and a light source disposed adjacent to the light incidence side surface. The present disclosure also provides a liquid crystal display having the backlight module. The present disclosure prevent the quantum dot material from being affected by moisture and oxygen by sealing the quantum dot materials using glass flat plates, thereby facilitating the display of the liquid crystal display.

Abstract: The present disclosure provides a primary frequency modulation method for a wind turbine, which may include: detecting a current frequency of a power grid; determining an instruction value of a power change amount for a primary frequency modulation by a first determining process when the current frequency of the power grid is less than a standard frequency of the power grid, wherein the first determining process may include: determining a reference value of the power change amount for the primary frequency modulation based on the current frequency; and when it is determined that currently there is an active power headroom for the wind turbine, comparing the reference value with a current active power headroom value of the wind turbine and determining the instruction value of the power change amount for the primary frequency modulation; and performing the primary frequency modulation based on the instruction value of the power change amount.