Abstract: A method for determining a plant growth curve includes obtaining color images and depth images of a plant to be detected at different time points, performing alignment processing on each color image and each depth image to obtain an alignment image, detecting the color image through a pre-trained target detection model to obtain a target bounding box, calculating an area ratio of the target bounding box in the color image, determining a depth value of all pixel points in the target boundary frame according to the aligned image, performing denoising processing on each depth value to obtain a target depth value, generating a first growth curve of the plant to be detected according to the target depth values and corresponding time points, and generating a second growth curve of the plant to be detected according to the area ratios and the corresponding time points.

Abstract: A method for determining a height of a plant, an electronic device, and a storage medium are disclosed. In the method, a target image is obtained by mapping an obtained color image with an obtained depth image. The electronic device processes the color image by using a pre-trained mobilenet-ssd network, obtains a detection box appearance of the plant, and extracts target contours of the plant to be detected from the detection box. The electronic device determines a depth value of each of pixel points in the target contour according to the target image. Target depth values are obtained by performing a de-noising on depth values of the pixel points, and a height of the plant to be detected is determined according to the target depth value. The method improves accuracy of height determination of a plant.

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 obtaining depth images implemented in an electronic device includes obtaining a first image and a second image; obtaining a predicted depth map of the first image, and calculating a first error value of the predicted depth map; determining a first transformation matrix between the first image and the second image; obtaining an instance segmentation image and obtaining a first mask image and a second mask image; obtaining a target transformation matrix; converting the predicted depth map into a first point cloud image, converting the first point cloud image into a second point cloud image, and converting the second point cloud image into a third image; calculating a second error value between the second image and the third image; obtaining a target deep learning network model; and inputting at least one image into the target deep learning network model, and obtaining at least one depth image.

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: 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 acquires a first image and a second image of a target object being inputted into the depth estimation network for outputting a depth image. A pixel posture conversion relationship between the first image and the second image is obtained. The pixel posture conversion relationship includes a position relationship between each first pixel in the first image and a second pixel in the second image, which correspond to a same part of the target object. A restored image is generated based on the depth image, the pixel posture conversion relationship, and pre-obtained camera parameters. A loss of the depth estimation network is determined based on a difference between the first image, the depth image, the restored image, and the second image for adjusting the parameters of the depth estimation network. A training apparatus, and an electronic device applying the method are also disclosed.

Abstract: A method for training an autoencoder implemented in an electronic device includes obtaining a stereoscopic image as the vehicle is in motion, the stereoscopic image includes a left image and a right image; generating a stereo disparity map according to the left image; generating a predicted right image according to the left image and the stereo disparity map; and calculating a first mean square error between the predicted right image and the right image.

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 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 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 and system for generating depth in monocular images acquires multiple sets of binocular images to build a dataset containing instance segmentation labels as to content; training an work using the dataset with instance segmentation labels to obtain a trained autoencoder network; acquiring monocular image, the monocular image is input into the trained autoencoder network to obtain a first disparity map and the first disparity map is converted to obtain depth image corresponding to the monocular image. The method combines binocular images with instance segmentation images as training data for training an autoencoder network, monocular images can simply be input into the autoencoder network to output the disparity map. Depth estimation for monocular images is achieved by converting the disparity map to a depth image corresponding to the monocular image. An electronic device and a non-transitory storage are also disclosed.

Abstract: A method for processing images implemented in an electronic device includes obtaining images during moving of a vehicle; obtaining instance segmentation images by segmenting the images; obtaining a predicted disparity map by reconstructing the left images based on a pre-established autoencoder; generating a first error value of the autoencoder for the images according to the left image, the predicted disparity map, and the right image, generating a second error value of the autoencoder for the instance segmentation image according to the left image of instance segmentation, the predicted disparity map, and the right image of instance segmentation; establishing an autoencoder model by adjusting the autoencoder according to the first error value and the second error value; obtaining a test image as the vehicle is moving, and obtaining a target disparity map; and obtaining a depth image corresponding to the test image by converting the target disparity map.

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: 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 detecting cells in images using an autoencoder, a computer device, and a storage medium extracts a first feature vector from each of a plurality of sample medical images. The first feature vector is inputted into an autoencoder, and a first latent feature of each of the plurality of sample medical images is extracted. A first predicted value of a number of cells in each of the plurality of sample medical images is generated based on the first latent feature. The first latent feature is inputted into the autoencoder, and a plurality of reconstructed images are obtained. The autoencoder is optimized based on the plurality of reconstructed images and the first predicted value. This method can be run in the computer device to improve efficiency of detection from images.

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 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 discovering defects in products by detecting abnormalities in images, an electronic device, and a storage medium are provided. The method includes training an autoencoder model using images of flawless products, inputting such an image into the autoencoder model, and determining whether a reconstructed image can be generated based on the image. The image is determined to be showing abnormality in respond that no reconstructed image is generated. In respond that the reconstructed image is generated, the reconstructed image corresponding to the image to be detected is obtained, and the presence of abnormality in the reconstructed image is determined according to a defect judgment criterion. This method running in the electronic device improves efficiency and accuracy of abnormality detection.