The present application is applicable to the technical field of image processing, and provides a target object tracking method and an apparatus, and a terminal device. The target object tracking method includes: obtaining an image sequence including a target object, wherein the image sequence includes a plurality of image; analyzing the plurality of image, and determining a motion vector and a motion vector residual of the target object in a current image; and inputting the motion vector, the motion vector residual , and a known target region of the target object in a previous image into a first target detection network, and determining a predicted target region of the target object in the current image. The present application can reduce the calculation amount and thus improve the operation speed of target object tracking.

According to the present invention, proposed is a method for inspecting a labeling operation, the method comprising, when a deep learning model for inspecting a labeling operation for a bounding box corresponding to an object included in an image is present and a computing apparatus uses the deep learning model, the steps of: performing, by the computing apparatus, first training on the deep learning model on the basis of a training image; obtaining, by the computing apparatus, an operation image and a bounding box labeling value therefor; calculating, by the computing apparatus, a score for inspection by performing a calculation while passing the operation image and the bounding box labeling value through the deep learning model; and determining, by the computing apparatus, whether the bounding box labeling value for the operation image is accurate on the basis of the score for inspection and performing any one of a pass process, a fail process, and a re-inspection process.

A wound-size measuring method for use in a portable electronic device is provided. The method includes the following steps: obtaining an input image via a camera device of the portable electronic device; using a CNN (convolutional neural network) model to recognize the input image, and selecting a part of the input image with the highest probability of containing a wound as an output wound image; and calculating an actual height and an actual width of the output wound image according to a lens-focal-length parameter reported by an operating system running on the portable electronic device, a plurality of reference calibration parameters corresponding to a pitch angle of the portable electronic device, and a pixel-height ratio and a pixel-width ratio of the output wound image.

A method of object identification includes: capturing an image of an object having a material presenting surface artifacts; detecting a boundary within the captured image; selecting a portion of the image depicting the surface material within the boundary; based on the selected portion of the image, determining attributes of the surface artifacts; generating, based on the determined attributes of the surface artifacts, a physical identifier corresponding to the object; and storing the generated physical identifier.

A discriminative mode generation unit generates a discriminative model that discriminates a target object included in an image using a target object image, which includes the target object and to which a label of the target object is applied, and a non-target object image, which includes a non-target object. An interest area detection unit inputs the target object image to the discriminative model, and detects an interest area which is an area that is predicted to include the target object. A rectangle generation unit generates a rectangle circumscribing the target object based on the interest area. A learning data output unit outputs learning data including a label of the target object and the rectangle.

A remote communication support system includes a transmission device and a receiving device. The receiving device is connected to the transmission device via a network. The transmission device includes an imaging portion, a control portion, and a communication portion. The imaging portion images an image. The control portion processes the image imaged by the imaging portion in accordance with a rule corresponding to a mask-release level for a communication counterparty. The communication portion transmits the image processed by the control portion to the receiving device of the communication counterparty.

A relative position calculator calculates relative position and attitude of a vehicle based on images captured by an image capturing apparatus on the vehicle. An absolute position calculator extracts a marker from a captured image by, and calculates absolute position and attitude of the vehicle based on position and attitude of the one extracted marker. A reliability calculator calculates reliabilities of the relative position and attitude, and reliabilities of the absolute position and attitude. A position and attitude determiner determines the relative position and attitude as position and attitude of the vehicle when the reliabilities of the relative position and attitude are equal to or larger than the reliabilities of the absolute position and attitude, and otherwise, determines the absolute position and attitude as the position and attitude of the vehicle.

Natural language processing systems and methods are disclosed herein. In some embodiments, digital document information comprising text is received. The digital document information may be processed through word and character encoding operations to generate word and character vectors while retaining document location information for the words and characters. The data may be then be processed by a series of convolution and maximum pooling operations to obtain maximum valued elements from the data. The document location information as well as the maximum values element data may be further processed for semantic classification of the data using a semantic classifier and bounding box regression.

For the automated loading of a load by a crane system, a camera system of the crane system generates at least one image data stream. The at least one image data stream is analyzed by a computer unit with the assistance of an artificial neural network. On the basis of the analysis, a first marker and a second marker are recognized by the computer unit in respective single images of the at least one image data stream. Positions of the markers are determined, and the load is loaded automatically by a lifting device of the crane system dependent upon the positions of the markers.

The present invention provides a comprehensive detection device and method for a cancerous region, and belongs to the technical field of deep learning. In the present invention, a cancerous region detection network is trained for preprocessed and annotated CT image data to predict bounding box coordinates of a cancerous region and a corresponding cancer confidence score; a clinical analysis network is trained for preprocessed clinical data with a cancer risk level to predict a cancer probability value of a corresponding patient; and a predicted cancer probability value is weighted to a predicted cancer confidence score to realize a comprehensive determination of the cancerous region. The present invention can detect a cancerous region with high accuracy and high performance.