Disclosed is an object-detection system configured to utilize multiple object-detection models that generate respective sets of object-detection conclusions to detect objects of interest within images of scenes. The object-detection system is configured to implement a series of functions to reconcile any discrepancies that exist in its multiple sets of object-detection conclusions in order to generate one set of conclusions for each perceived object of interest within a given image.

The present invention integrates a low power and high compression pixel-wise coded exposure (PCE) camera with advanced object detection, tracking, and classification algorithms into a real-time system. A PCE camera can control exposure time of every pixel in the camera and at the same time can compress multiple frames into a compressed frame. Consequently, it can significantly improve the dynamic range as well as reduce data storage and transmission bandwidth usage. Conventional approaches utilize PCE camera for object detection, tracking and classification, require the compressed frames to be reconstructed. These approaches are extremely time consuming and hence makes the PCE cameras unsuitable for real-time applications. The present invention presents an integrated solution that incorporates advanced algorithms into the PCE camera, saving reconstruction time and making it feasible to work in real-time applications.

A method includes screening, by a video-clip screening module in a video description model, a plurality of video proposal clips acquired from a video to be analyzed, to acquire a plurality of video clips suitable for description. The plural video proposal clips acquired from the video to be analyzed may be screened by the video-clip screening module to acquire the plural video clips suitable for description; and then, each video clip is described by a video-clip describing module, thus avoiding description of all the video proposal clips, only describing the screened video clips which have strong correlation with the video and are suitable for description, removing the interference of the description of the video clips which are not suitable for description in the description of the video, guaranteeing the accuracy of the final descriptions of the video clips, and improving the quality of the descriptions of the video clips.

A method and a system for model training are provided. The method can include training a first classifier, a second classifier, and a third classifier with subsets of a labeled dataset. The method can also include predicting a pseudo labeled dataset from an unlabeled dataset using the first classifier, the second classifier, and the third classifier. The method further includes assigning a role to the first classifier, to the second classifier, and to the third classifier. The method can further include selecting a teaching sample dataset from the pseudo labeled dataset based on the role assigned to the third classifier, wherein the third classifier is assigned a role of a student. The method can also include retraining the third classifier with the teaching sample dataset in conjunction with a subset of the labeled dataset.

A system for recognizing gestures generates a skeletal model from video data of a subject. A defined subset of attributes of the skeletal model are mapped to defined positions of a vector. A gesture is recognized by evaluating a neural network using the vector as input. The neural network, trained using training vectors generated according to the definitions of skeletal model attributes and vector positions, classifies a gesture based on the input vector.

Embodiments for implementing enhanced ensemble model diversity and learning by a processor. One or more data sets may be created by combining one or more clusters of data points of a minority class with selected data points of a majority class. One or more ensemble models may be created from the one or more data sets using a supervised machine learning operation. An occurrence of an event may be predicted using the one or more ensemble models.

A method for determining a property of a geological formation based on an optical image of rock samples taken from the formation is presented therein. The image comprises a plurality of pixels and the method comprises defining windows in the image, each window comprising predetermined number of pixels and being of a predetermined shape. The method also includes, for each window, extracting a rockprint value representative of the window. A rockprint comprises indicators for characterizing a texture of the window. The method also includes classifying the windows into categories of a predetermined set. Each category is representative of one type of rock and the classification is based on a comparison of the rockprint value of each window with rockprint values of images of reference rock samples for each category. Based on the classification, the method then includes determining the at least one property of the geological formation, ie the quantification of each type of rock in the sample.

An apparatus and method are disclosed for user and moving vehicle detection in which sensor data for a portable device is processed to determine whether the portable device is in a moving vehicle. Following a determination the portable device is in a moving vehicle, the sensor data is to characterize an association between the user and the portable device to determine whether the portable device is connected to the user. If the user is connected to the portable device, it is then determined if the portable device is being held in hand. If the portable device is held in hand, it is then determined if the user is operating the moving vehicle. Output from an image sensor of the portable device may be used in determining if the user is the operator.

The present invention integrates a low power and high compression pixel-wise coded exposure (PCE) camera with advanced object detection, tracking, and classification algorithms into a real-time system. A PCE camera can control exposure time of every pixel in the camera and at the same time can compress multiple frames into a compressed frame. Consequently, it can significantly improve the dynamic range as well as reduce data storage and transmission bandwidth usage. Conventional approaches utilize PCE camera for object detection, tracking and classification, require the compressed frames to be reconstructed. These approaches are extremely time consuming and hence makes the PCE cameras unsuitable for real-time applications. The present invention presents an integrated solution that incorporates advanced algorithms into the PCE camera, saving reconstruction time and making it feasible to work in real-time applications.

In some examples, image content moderation may include classifying, based on a learning model, an object displayed in an image into a category. Further, image content moderation may include detecting, based on another learning model, the object, refining the detected object based on a label, and determining, based on the another learning model, a category for the refined detected object. Further, image content moderation may include identifying, based on the label, a keyword associated with the object, and determining, based on the identified keyword, a category for the object. Further, image content moderation may include categorizing, based on a set of rules, the object into a category, and moderating image content by categorizing, based on aforementioned analysis the object into a category. Yet further, image content moderation may include tagging, based on fusion-based tagging, the object with a category and a color associated with the object.