In order to provide a learning data generating apparatus that is able to efficiently restrain erroneous detections, the learning data generating apparatus includes a data acquisition unit configured to acquire learning data including teacher data, and a generation unit configured to generate generated learning data based on the learning data and a generating condition, wherein the generation unit converts teacher data of a positive instance into teacher data of a negative instance according to a preset rule when generating the generated learning data.

An activity recognition system may comprise a local device and a server. The local device may be configured to: obtain a video; determine whether at least one human is present in one or more frames of the video; in response to determining the at least one human present in the video, determine if the at least one human in each of the frames corresponds to the same person; in response to determining that the at least one human in each of the frames corresponds to the same person, determine if the person is a stranger; and in response to determining that the person is not a stranger, transmit at least a portion of the video to the server. The server may be configured to: predict an activity class associated with the person; and trigger an alarm based on the activity class.

An image recognition method and system based on deep learning are provided. The image recognition system includes a first recognizing engine, at least one second recognizing engine and a processing circuit. The second recognizing engine is activated to recognize a testing image when the first recognizing engine is recognizing the testing image. The processing circuit determines whether to interrupt the first recognizing engine recognizing the testing image according to a result outputted by the second recognizing engine after the second recognizing engine completes recognition of the testing image.

A method of determining, one or more damage states of one or more auxiliary parts of a damaged vehicle, the vehicle comprising a plurality of normalized parts and at least some of the normalized parts further comprising one or more auxiliary parts. The method includes receiving one or more images of the vehicle, using a plurality of classifiers, each determining at least one classification of damage to the vehicle, each said classification being determined for each of a plurality of normalized parts of the vehicle, determining one or more classifications for the plurality of auxiliary parts using one or more trained models, wherein each classification comprises at least one indication of damage to at least one auxiliary part and outputting the determined damage states of the one or more auxiliary parts.

The present disclosure uses automated, computer-driven analysis of video feeds to extract raw motion metadata, identify moving objects and assess whether or not the moving objects are compliant with certain predefined rules. The motion can be visually plotted on a background in the form of motion trails, and a chronological plot of the motion may be provided as a menu to find anomalies through visual screening. The motion metadata may be filtered through annotations. A highlighted portion of the video feed relating to a specific topic of interest may be replayed.

An image recognition method and system based on deep learning are provided. The image recognition system includes a first recognizing engine, at least one second recognizing engine and a processing circuit. The second recognizing engine is activated to recognize a testing image when the first recognizing engine is recognizing the testing image. The processing circuit determines whether to interrupt the first recognizing engine recognizing the testing image according to a result outputted by the second recognizing engine after the second recognizing engine completes recognition of the testing image.

Disclosed is a method for training a neural network to quantify the vessel calibre of retina fundus images. The method involves receiving a plurality of fundus images; pre-processing the fundus images to normalise images features of the fundus images; and training a multi-layer neural network, the neural network comprising of a convolutional unit, multiple dense blocks alternating with transition units for down-sampling image features determined by the neural network, and a fully-connected unit, wherein each dense block comprises a series of cAdd units packed with multiple convolutions, and each transition layer comprises a convolution with pooling.

Disclosed is a method and system for classifying elements of a product. The method comprises identifying elements of the product. Thereupon, features of the one or more elements are determined, using a feature recognition technique. The features correspond to manufacturing operations required for manufacturing the elements, and include sheet metal operations, turn operations, injection moulding operations, and machining operations. The manufacturing operations are determined in a priority order with the sheet metal operation having a highest priority and the machining operation having a least priority.

An automatic target recognizer system including: a database that stores target recognition data including multiple reference features associated with each of multiple reference targets; a pre-selector that selects a portion of the target recognition data based on a reference gating feature of the multiple reference features; a preprocessor that processes an image received from an image acquisition system which is associated with an acquired target and determines an acquired gating feature of the acquired target; a feature extractor and processor that discriminates the acquired gating feature with the reference gating feature and, if there is a match, extracts multiple segments of the image and detects the presence, absence, probability or likelihood of one of multiple features of each of the multiple reference targets; a classifier that generates a classification decision report based on a determined classification of the acquired target; and a user interface that displays the classification decision report.

In some embodiments, a computer-implemented method is disclosed. The method comprises receiving a plant image from a user device and applying a first digital model to first regions within the image for classifying each of the first regions into a class of a first set of classes corresponding to a first plurality of plant diseases, a healthy condition, or a combination of a second plurality of plant diseases. The method also includes applying a second digital model to one or more second regions within the image for classifying each of the one or more second regions into a class of a second set of classes corresponding to the second plurality of plant diseases. The method then includes transmitting classification data related to the classes of the first set of classes and the classes of the second set of classes to the user device into which the regions are classified.