An apparatus includes a memory and processor. The memory stores document categories, text generated from an image a physical document page, and a machine learning algorithm. The machine learning algorithm is configured to extract features associated with natural language processing and features associated with the text. The machine learning algorithm is also configured to generate a feature vector that includes the first and second pluralities of features, and to generate, based on the feature vector, a set of probabilities, each of which is associated with a document category and indicates a probability that the physical document from which the text was generated belongs to that document category. The processor applies the machine learning algorithm to the text, to generate the set of probabilities, identifies a largest probability, and assigns the image to the associated document category.

An object detection device includes an image data acquiring unit that acquires image data indicating an image captured by a camera, a first feature amount extracting unit that generates a first feature map using the image data, a second feature amount extracting unit that generates a second feature map using the image data, and generates a third feature map by performing addition or multiplication of the second feature map using the first feature map and weighting the second feature map, and the object detection unit that detects an object in the captured image using the third feature map. A first feature amount in the first feature map uses a mid-level feature corresponding to objectness, and a second feature amount in the second feature map uses a high-level feature.

The disclosure relates to a method for pedestrian detection in a processor circuit of a motor vehicle, wherein an image data set describing an image of an environment of the motor vehicle is received from an environment sensor, and a machine learning model (ML model) is used to determine bounding boxes with potential images of pedestrians using the image data set, and from image data of the image data set the at least one ML model extracts feature data of image features and a detection of a completely or partially depicted pedestrian is carried out within a bounding box using the image features contained therein by way of a classifier of the at least one ML model, and the bounding box depicting the pedestrian is identified by a detection signal as the result of the detection.

One variation of a method includes: accessing a boundary of a stand of trees; defining an array of scan zones within the boundary; accessing a first sequence of images representing treetops in a first scan zone; accessing a second sequence of images representing bases of trees in the first scan zone; accessing a third sequence of images representing bases of trees in a second scan zone; accessing a fourth sequence of images representing treetops in the second scan zone; interpolating canopy characteristics of trees between the first scan zone and the second scan zone based on the first and fourth sequences of images; interpolating lower tree characteristics of trees between the first scan zone and the second scan zone based on the second and third sequences of images; and compiling canopy and lower tree characteristics into a virtual representation of tree characteristics across the stand of trees.

This document describes systems and techniques related to deep association for sensor fusion. For example, a model trained using deep machine learning techniques, may be used to generate an association score matrix that includes probabilities that tracks from different types of sensors are related to the same objects. This model may be trained using a convolutional recurrent neural network and include constraints not included in other training techniques. Focal loss can be used during training to compensate for imbalanced data samples and address difficult cases, and data expansion techniques can be used to increase the multi-sensor data space. Simple thresholding techniques can be applied to the association score matrix to generate an assignment matrix that indicates whether tracks from one sensor and tracks from another sensor match. In this manner, the track association process may be more accurate than current sensor fusion techniques, and vehicle safety may be increased.

A method includes: obtaining a plurality of pieces of detection information from a plurality of sensors, where the detection information includes detection information from different sensors for a same target object; obtaining corresponding formation information based on the plurality of pieces of detection information; determining target formation information based on the plurality of pieces of formation information, where the target formation information indicates detection information detected by different sensors for a same target object set; and fusing, based on formation position information of each target object in the target object set, the detection information that is in the plurality of pieces of formation information and that corresponds to a same target object.

Provided in the present disclosure are a method, an apparatus and a system for determining feature data of image data, and a storage medium. Wherein, the method comprises: acquiring features of image data, the features comprising a first feature and a second feature, wherein, the first feature is extracted from the image data using a first model, the first model being trained in a machine learning manner, and the second feature is extracted from the image data using a second model, the second model being constructed based on a pre-configured data processing algorithm; and determining feature data based on the first feature and the second feature. The present disclosure solves the technical problem that features recognized by the AI may not be consistent with human recognized features.

Image processing methods, apparatuses, and electronic devices include: extracting features of an image to be processed to obtain a first feature map of the image; generating an attention map of the image based on the first feature map; fusing the attention map and the first feature map to obtain a fusion map; and extracting the features of the image again based on the fusion map. The implementation mode introduces an attention mechanism into image processing, and effectively improves the efficiency of acquiring information from an image.

An auxiliary filtering device for face recognition is provided. The auxiliary filtering device is used to exclude an ineligible object to be identified according to the relative relationship between object distances and image sizes, the image variation with time and/or the feature difference between images captured by different cameras to prevent the possibility of cracking the face recognition by using a photo or a video.

A method for camera radar fusion includes receiving, by the processor, radar object detection data for an object and modeling, by a processor, a three dimensional (3D) physical space kinematic model, including updating 3D coordinates of the object, to generate updated 3D coordinates of the object, in response to receiving the radar object detection data for the object. The method also includes transforming, by the processor, the updated 3D coordinates of the object to updated two dimensional (2D) coordinates of the object, based on a 2D-3D calibrated mapping table and modeling, by the processor, a two dimensional (2D) image plane kinematic model, while modeling the 3D physical space kinematic model, where modeling the 2D image plane kinematic model includes updating coordinates of the object based on the updated 2D coordinates of the object.