Abstract: A method of grouping certain cell densities to establish the number and volume of cells appearing in an image input the image into a self-encoder having a preset number of a density grouping models to obtain a preset number of reconstructed images. The image and each reconstructed image are input into a twin network model of the density grouping model corresponding to each reconstructed image, and a first error value is calculated between the image and each reconstructed image. A minimum first error value in the first error value set is determined, and a density range corresponding to the density grouping model corresponding to minimum first error value is taken as the density range. An electronic device and a non-volatile storage medium performing the above-described method are also disclosed.

Abstract: A method for optimizing the conversion of a deep learning model to process other data, applied in a device, includes converting a first deep learning model to obtain a second deep learning model, obtaining a weighting arrangement of the two models according to their deep learning frameworks and performing a quantization on the two models. A similarity in weighting between the two models is analyzed to produce a weighting analysis based on the first and second weighting arrangement and the first and second model quantization result weighting. The two models are tested to establish a model performance analysis. One or more suggestions for optimization are obtained based on the weighting analysis and the model performance analysis, and are applied to optimize the second deep learning model, an optimized second deep learning model being employed to process the other data.

Abstract: A method for training a depth estimation model is provided. The method includes obtaining a first left image and a first right image. A disparity map is obtained by inputting the first left image into a depth estimation model. A second right image is obtained by adding the first left image to the disparity map. The first left image is converted into a third right image. A mask image is obtained by performing a binarization processing on a pixel value of each of pixel points of the third right image. Once a loss value of the depth estimation model is obtained by calculating a mean square error of pixel values of all corresponding pixel points of the first right image, the second right image, and the mask image, a depth estimation model is iteratively trained according to the loss value.

Abstract: The present application provides a method for uploading vehicle driving data and an electronic device. The method includes: obtaining vehicle driving data of a target vehicle; predicting a vehicle accident occurrence probability of the target vehicle according to the vehicle driving data and a preset analysis model; when determining that the vehicle accident occurrence probability meets preset conditions, obtaining historical driving data of the target vehicle within a preset time period before a current time, and uploading the historical driving data to a cloud server. The above method can avoid a situation that the vehicle driving data for a period of time before the accident has not been uploaded, after the vehicle system fails due to a vehicle accident. By promptly uploading the historical driving data, therefore providing data support and improve accuracy for subsequent accident cause analysis.

Abstract: A method for detecting defects in products from images thereof and an electronic device applying the method inputs a defect image repair data set into an autoencoder to train the autoencoder, and generates a reconstructed image, calculates a reference error value between the sample image and the reconstructed image by a preset error function, and set a threshold value based on the reference error value. The electronic device inputs an image possibly revealing a defect into the autoencoder and generates the reconstructed image corresponding to the image to be detected, and uses the preset error function to calculate the reconstruction error between the image and the reconstructed image, thereby determining whether the image being analyzed does reveal defects. When the reconstruction error is greater than the threshold value, a determination is made that a defect is revealed.

Abstract: A method for detecting three-dimensional (3D) objects in relation to autonomous driving is applied in an electronic device. The device obtains detection images and depth images, =inputs the detection images into a trained object detection model to determine categories of objects in the detection images and two-dimensional (2D) bounding boxes of the objects. The device determines object models of the objects and 3D bounding boxes of the object models according to the object categories, and calculates point cloud data of the objects selected and distances from the depth camera to the object models. The device determines angles of rotation of the object models of the objects according to the object models of the objects and the point cloud data, and can determine respective positions of the objects in 3D space according to the distance from the depth camera to the object models, the rotation angles, and the 3D bounding boxes.

Abstract: A method for obtaining depth images for improved driving safety applied in an electronic device processes first and immediately-following second images which have been captured and processes each to obtain two sets of predicted depth maps. The electronic device determines a transformation matrix of a camera between first and second images and converts the first predicted depth maps into first point cloud maps, and second predicted depth maps into second point cloud maps. The first point cloud maps are converted into third point cloud maps, and the second point cloud maps into fourth point cloud maps. First and fourth point cloud maps are matched and first and second error values are calculated, thereby obtaining a target deep learning network model. Images to be detected are input into the target deep learning network model and depth images are obtained.

Abstract: A method for assisting safer riving applied in a vehicle-mounted electronic device obtains RGB images of a scene in front of a vehicle when engine is running, processes the RGB images by a trained depth estimation model, obtains depth images and converts the depth images to three-dimensional (3D) point cloud maps. A curvature of the driving path of the vehicle is calculated, and 3D regions of interest of the vehicle are extracted from the 3D point cloud maps according to a size of the vehicle and the curvature or deviation from straight ahead. The 3D regions of interest are analyzed for presence of obstacles. When no obstacles are present, the vehicle is controlled to continue driving, when presence of at least one obstacle is determined, an alarm is issued.

Abstract: A method for detection of three-dimensional (3D) objects on or around a roadway by machine learning, applied in an electronic device, obtains images of road, inputs the images into a trained object detection model, and determines categories of objects in the images, two-dimensional (2D) bounding boxes of the objects, and parallax (rotation) angles of the objects. The electronic device determines object models and 3D bounding boxes of the object models and determines distance from the camera to the object models according to size of the 2D bounding boxes, image information of the detection images, and focal length of the camera. The positions of the object models in a 3D space can be determined according to the rotation angles, the distance, and the 3D bounding boxes, and the positions of the object models are taken as the position of the objects in the 3D space.

Abstract: A method for measuring a growth height of a plant, an electronic device, and a storage medium are provided. The method controls a camera device to obtain a color image and a depth image of a plant to be detected. The color image is detected by a detection model which is pre-trained, and a plurality of detection boxes which includes a plurality of plants to be detected is obtained. The color image and the depth image are aligned to create an alignment image. A plurality of target boxes is acquired from the alignment image, and depth values of the plurality of target boxes are determined. The quantity of the target boxes and a height of one or more plants to be detected are determined, no manual operations are required.

Abstract: A method for neural network model encryption and decryption includes a first apparatus stores a neural network model and obtains hardware configuration information of the first apparatus, and obtains an encryption key accordingly; encrypts the neural network model by a predetermined encryption algorithm; a second apparatus obtains the encrypted neural network model from the first apparatus, transmits a decryption request to the first apparatus, obtains the hardware configuration information from the first apparatus, obtains a decryption key based on the hardware configuration information; and decrypts the encrypted neural network model by a predetermined decryption algorithm.

Abstract: A method for determining a growth height of a plant, an electronic device, and storage medium are provided. The method includes controlling a camera device to capture a plant to be detected, and obtaining a color image and a depth image of the plant to be detected. The color image and the depth image are aligned and an alignment image is obtained. The color image is detected using a pre-trained mobilenet-ssd network, and a detection box including the plant to be detected is obtained. A depth value of each of pixel points in the detection box is determined, and target depth values are obtained. A mean value and a standard deviation of the target depth values are determined, and a height of the plant to be detected is determined. According to the method, accuracy of the height of the plant can be improved.

Abstract: A defect detection method applied to an electronic device includes determining, pixel difference values based a test sample image and positive sample images. A color difference threshold is determined according to positive sample images. Feature connected regions of the test sample image are generated according to the color difference threshold and pixel difference values. A first threshold is generated according to image noises of positive sample images. A target region is determined from the feature connected regions according to a number of pixel points in each feature connected region and the first threshold. Once a second threshold is determined according to defective pixel points of negative sample images, a detection result of a test sample is determined according to an area of the target region and the second threshold.

Abstract: A method of optimizing the detection of abnormalities in images of products generates a first image similar to training images and a second image similar to testing images with normal images and the images showing abnormalities inputted into a generative adversarial network (GAN). The GAN determines a first similarity ratio between the first image and the training image and generates a parameter based on the first similarity ratio for adjusting the GAN. A second similarity ratio between the second image and the testing image is determined. The testing image is deemed a normal image when the second similarity ratio is larger than the specified threshold value, and deemed to be an image revealing abnormalities when the second similarity ratio is less than or equal to the specified threshold value. A terminal device and a computer readable storage medium applying the method are also provided.

Abstract: An image defect detection method applied to an electronic device is provided. The method includes dividing a detecting image into a plurality of detecting areas, generating a detection accuracy value for each detecting area based on a defective image and a non-defective image, and obtaining a plurality of detection accuracy values. An autoencoder is selected for each detection accuracy value. A model corresponding to each detecting area is obtained by training the autoencoder based on the non-defective image. A plurality of reconstructed image blocks is obtained by inputting each of a plurality of detecting blocks into the corresponding model, and a reconstruction error value between each reconstructed image block and the corresponding detecting block is obtained. A detection result of a product contained in the image to be detected is obtained based on the reconstruction error value corresponding to each detecting block.

Abstract: A method of detecting product defects obtains an image of a product and sets a region of interest (ROI) of the image. A first contour of a first target object is detected in the region of interest. The image is detected according to the first contour to obtain a corrected image. A position difference between the first contour and a second target object in the region of interest is obtained. A second contour of the second target object is detected in the corrected image according to the position difference. A first image area corresponding to the first contour and a second image area corresponding to the second contour are segmented and input into an autoencoder. According to outputs of the autoencoder, whether the product is defective is determined. A detection result of the product is output. The method can detect defects on products quickly and accurately.

Abstract: A method for calculating a density of stem cells in a cell image and an electronic device are provided. A plurality of preset ratios and a plurality of density calculation models can be used to perform hierarchical density calculations on the cell image. Starting from the largest preset ratio (the first preset ratio) reduction of the cell image to no reduction, the density calculation is performed on the cell image using a model starting with a highest density calculation (the first density calculation model) to a model with the smallest density calculation (the third density calculation model), which can quickly detect densities of various stem cells. Using different preset ratios and corresponding density calculation models for calculation, it is not necessary to calculate the number of stem cells to obtain the density of stem cells, which improves a calculation efficiency of the density of stem cells.

Abstract: A method of determining a distribution of stem cells in a cell image, an electronic device and a storage medium are disclosed. The method acquires a cell image and segments the cell image and obtaining a plurality of sub-images. The plurality of sub-images is inputted into a stem cell detection model to detect to obtain a number of stem cells in each sub-image. A position of each sub-image in the cell image is determined. A distribution of the stem cells in the cell image is output, according to the number of stem cells in each sub-image and the position of each sub-image in the cell image. The present disclosure an accuracy of the distribution of stem cells in the cell image.

Abstract: A virtual scene generation method applied to an electronic device is provided. The electronic device identifies object prediction information of each real object in each of real scene images. A first virtual image corresponding to each real scene image is obtained according to the object prediction information of each real object. A second virtual image and a texture difference image corresponding to each real scene image are generated. A target image corresponding to each real scene image is generated according to the second virtual image and the texture difference image corresponding to each real scene image. Once a virtual scene generation model is generated based on the real scene images, the first virtual image, the second virtual image, the target image corresponding to each real scene image, a virtual scene corresponding to an image is obtained using the virtual scene generation model and the virtual scene simulator.

Abstract: A method for generating defective image of products applied in an electronic device includes generating first input data according to flawless sample images and a first noise vector, using an autoencoder as a generator of a Generative Adversarial Network (GAN), inputting the first input data to the generator, and generating images for training in defects. The method further includes calculating a first loss value between the flawless sample images and the defect training images, inputting the defect training images into a discriminator of the GAN, and calculating a second loss value. The method further includes obtaining an optimized GAN and taking the optimized GAN as a defective image adversarial network, obtaining flawless testing images, inputting the flawless testing images and a second noise into a generator of the defective image adversarial network, and generating images of defects by processing the flawless testing images and the second noise.