Abstract: A depth estimation method and apparatus are provided. The depth estimation method includes obtaining an image from an image sensor comprising upper pixels, each comprising N sub-pixels, obtaining N sub-images respectively corresponding to the N sub-pixels from the image, obtaining a viewpoint difference between the N sub-images using a first neural network, and obtaining a depth map of the image based on the viewpoint difference using a second neural network.

Abstract: Embodiments of the invention provides a cutting tool. The cutting tool includes a housing; a motor, accommodated in the housing; a transmission mechanism, connected to the motor and used for driving a saw blade, having a saw blade plane; and base plates, connected to the housing and comprising a first base plate provided with a first bottom surface and a second base plate provided with a second bottom surface, wherein at least one of the first base plate and the second base plate is provided with an abutting surface coplanar with the saw blade plane; the abutting surface is used for being matched with a guide surface, and the first base plate and the second base plate are movable to expose the abutting surface.

Abstract: Provided is a liveness verification method and device. A liveness verification device acquires a first image and a second image, and select one or more liveness models based on respective analyses of the first image and the second image, including analyses based on an object part being detected in the first image and/or the second image, and to verify, using the selected one or more liveness models, a liveness of the object based on the first image and/or the second image. The first image may be a color image and the second image may be an Infrared image.

Abstract: An image processing method implemented by a processor includes receiving an image, acquiring a target image that includes an object from the image, calculating an evaluation score by evaluating a quality of the target image, and detecting the object from the target image based on the evaluation score.

Abstract: An image segmentation method and device, a computer device and a non-volatile storage medium are provided. The image segmentation method includes: performing super-pixel segmentation on an image to be segmented to obtain a super-pixel image, and binarizing the image to be segmented to obtain a binary image; combining the super-pixel image and the binary image to obtain a binary super-pixel image; performing distance transformation on the binary super-pixel image, to obtain a grayscale super-pixel image; marking seed points in the grayscale super-pixel image, to obtain a seed point super-pixel image in which grayscale values of the seed points are greater than a first value, and grayscale values of pixel blocks other than the seed points in target regions are the first value; and marking and filling the pixel blocks, grayscale values of which are the first value in the seed point super-pixel image, to obtain a segmented image.

Abstract: An image processing apparatus, includes an image classifier configured to determine whether an input image is a low-quality image or a high-quality image; and an image evaluator configured to determine a first predetermined number of clearest images from a plurality of low-quality images determined by the image classifier.

Abstract: A processor implemented method of processing a facial expression image, the method includes controlling a camera to capture a first facial expression image and a second facial expression image, acquiring a first expression feature of the first facial expression image, acquiring a second expression feature of the second facial expression image, generating a new expression feature dependent on differences between the acquired first expression feature and the acquired second expression feature, and adjusting a target facial expression image based on the new expression feature.

Abstract: The present disclosure relates to a positioning method, a positioning server, and a positioning system. The positioning method includes: receiving a wireless positioning coordinate of a moving object; determining a visual sub-map to be matched in a visual map database based on the wireless positioning coordinate; and obtaining a visual positioning coordinates corresponding to a current image of the moving object captured at time of wireless positioning as a positioning result, based on the determined visual sub-map to be matched.

Abstract: An image-to-image search method includes: receiving an image to be searched and at least one category of similarity search sent by a terminal; extracting a feature code of the image by using a trained hash model that uniquely corresponds to the at least one category of similarity search according to the received image and the at least one category of similarity search; obtaining target images that are similar to the image according to the feature code of the image in a feature code library that uniquely corresponds to the at least one category of similarity search; and sending the target images to the terminal.

Abstract: A processor implemented image processing method includes acquiring a facial image by performing a face detection on an image, performing a quality assessment on the facial image using a preset facial image regression model, and determining a quality level of the facial image based on the quality assessment.

Abstract: This disclosure provides an image recommendation method, a client, a server, a computer system and a medium. The method includes acquiring an image, sending the acquired image to a server, such that the server extracts a scale invariant feature of the acquired image and performs retrieval of identical images according to the scale invariant feature of the acquired image, and such that the server extracts a multi-scale feature of the acquired image and performs retrieval of similar images according to the multi-scale feature of the acquired image, and receiving at least one recommended image. The at least one recommended image is based on result of the identical image retrieval and result of the similar image retrieval.

Abstract: This disclosure describes a power tool comprising a housing, a motor received in the housing and an output shaft driven by the motor and used for mounting a cutting tool. The housing comprises a first head housing and a second head housing. The first head housing is used for receiving part of the output shaft. A maximal length of the first head housing along an axial direction of the output shaft is L. A plane where the axis of the output shaft is positioned is defined as a middle plane. N vibration damping elements are disposed between the first head housing and the second head housing and, on at least one side of the middle plane, each vibration damping element comprises a vibration damping part contacting with the first head housing and the second head housing. A sum of the lengths of the N vibration damping parts along the axial direction of the output shaft is larger than or equal to 0.2L and smaller than or equal to L.

Abstract: A processor implemented method of processing a facial expression image, the method includes acquiring an expression feature of each of at least two reference facial expression images; generating a new expression feature based on an interpolation value of the expression feature; and adjusting a target facial expression image based on the new expression feature and creating a new facial expression image.

Abstract: The embodiments of the present disclosure provide a positioning method, a positioning device. The method may include: acquiring an image from a camera; obtaining a first coordinate of the camera in a world coordinate system from the image based on a deep learning model; obtaining an initial coordinate of the camera in the world coordinate system based on the first coordinate; and determining a real-time coordinate of the camera in the world coordinate system through inter-frame matching based on the initial coordinate of the camera in the world coordinate system.

Abstract: Disclosed are an image retrieval method, an image retrieval apparatus, an image retrieval device and a computer-readable storage medium, wherein the image retrieval method including: extracting global features of an input image and obtaining a global feature code based on the global features; extracting content features of the input image and obtaining a content feature code based on the content features; splicing the global feature code with the content feature code to obtain a composite feature code of the input image; comparing the composite feature code with alternative feature codes in a feature code library to obtain an image retrieval result. By comprehensively considering the global features and the content features of the input image in the image retrieval process, the accuracy and retrieval efficiency of the retrieval results can be improved.

Abstract: The present invention discloses a speed changing tool, comprising: a housing; a motor, disposed in the housing and outputting rotary power; a trigger switch, used for starting and stopping the motor; an output shaft; a gear transmission, which is disposed between the motor and the output shaft to transmit rotation of the motor to the output shaft, and comprises at least one group of gear system, a gear ring meshed with the gear system and a moving member, wherein the moving member can be moved between a first position and a second position and when in the first position and the second position, the moving member has different states relative to the housing, such that the gear transmission outputs a rotary speed of the motor with different speed reduction ratios; the variable speed tool further comprises a drive mechanism for driving the moving member to move between two positions, when a load of the output shaft reaches or exceeds a preset value, the drive mechanism can drive the moving member to move to the

Abstract: Disclosed is a liveness test method and apparatus. A liveness test apparatus determines a pre-liveness score based on a plurality of sub-images acquired from an input image, determines a post-liveness score based on a recognition model for recognizing an object included in the input image, and determines a liveness of the object based on any one or any combination of the pre-liveness score and the post-liveness score.

Abstract: A method of detecting a target includes generating an image pyramid based on an image on which a detection is to be performed; classifying candidate areas in the image pyramid using a cascade neural network; and determining a target area corresponding to a target included in the image based on the plurality of candidate areas, wherein the cascade neural network includes a plurality of neural networks, and at least one neural network among the neural networks includes parallel sub-neural networks.

Abstract: A method of detecting a target includes determining a quality type of a target image captured using a camera, determining a convolutional neural network of a quality type corresponding to the quality type of the target image in a database comprising convolutional neural networks, determining a detection value of the target image based on the convolutional neural network of the corresponding quality type, and determining whether a target in the target image is a true target based on the detection value of the target image.

Abstract: A method for positioning a supermarket shopping cart, a system for positioning a supermarket shopping cart and a supermarket shopping cart. A method for positioning a supermarket shopping cart provided by the present disclosure includes: acquiring a first reference image of a supermarket, and processing a first reference image to obtain a partition in which a shopping cart is located as a positioning partition, in which the supermarket comprises a plurality of partitions; receiving distance information sent by at least one signal transmitter provided in the positioning partition, in which each partition is provided with at least one signal transmitter; and obtaining a first positioning position of the shopping cart, according to distance information sent by at least one signal transmitter corresponding to the positioning partition, and determining an actual position of the shopping cart based on the first positioning position of the shopping cart.