The described positional awareness techniques employing visual-inertial sensory data gathering and analysis hardware with reference to specific example implementations implement improvements in the use of sensors, techniques and hardware design that can enable specific embodiments to provide positional awareness to machines with improved speed and accuracy.

A detection apparatus to extract features from an image; determine the number of candidate regions of the object in the image based on the extracted features, wherein the determined number of the candidate regions is decided by a position and shape of the candidate regions; and to detect the object from the image based on at least the extracted features and the determined number, position and shape of the candidate regions.

One or more processor can automatically identify, structure and retrieve spatial and/or temporal sequences of digital media content according to semantic specification. Digital media content can be received and information from digital media content can be extracted. Based on the information, a knowledge graph can be constructed or structured to include at least one of spatial and temporal representation of the digital media content. A search query can be received associated with the digital media content. Based on traversing the knowledge graph structure according to at least one of spatial and temporal criterion mapped from the search query, new digital media content can be composed which meets the search query.

A driving assistance apparatus includes a gaze detection portion detecting a gaze distribution of a driver for a vehicle, an image acquisition portion acquiring a captured image from an imaging device that captures an image in surroundings of the vehicle, a driver information acquisition portion acquiring driver information that allows identification of the driver for the vehicle, a generation portion generating a personalized saliency map based on the captured image and the driver information, the personalized saliency map that serves as a saliency map for the captured image and that differs depending on the driver, and a determination portion determining whether or not the driver looks at a visual confirmation target in the surroundings of the vehicle by comparing the gaze distribution detected by the gaze detection portion and the personalized saliency map generated by the generation portion.

A method for detecting a vehicle occupancy by using passenger keypoints based on analyzing an interior image of a vehicle is provided. The method includes steps of: (a) if the interior image is acquired, a vehicle occupancy detecting device (i) inputting the interior image into a feature extractor network, to generate feature tensors by applying convolution operation to the interior image, (ii) inputting the feature tensors into a keypoint heatmap & part affinity field (PAF) extractor, to generate keypoint heatmaps and PAFs, (iii) inputting the keypoint heatmaps and the PAFs into a keypoint detecting device, to extract keypoints from the keypoint heatmaps, and (iv) grouping the keypoints based on the PAFs, to detect keypoints per passengers; and (b) inputting the keypoints into a seat occupation matcher, to match the passengers with seats by referring to the inputted keypoints and preset ROIs for the seats and to detect the vehicle occupancy.

The present disclosure provides an image search method and apparatus, wherein the method includes: acquiring an image to be searched; extracting a multi-scale feature of the image to be searched; determining a hash value of the image to be searched according to the multi-scale feature; and obtaining original images similar to the image to be searched by comparing the multi-scale feature of the image to be searched with a multi-scale feature of each original image corresponding to a hash bucket to which the hash value belongs.

Described is a system for classifying novel objects in imagery. In operation, the system extracts salient patches from a plurality of unannotated images using a multi-layer network. Activations of the multi-layer network are clustered into key attribute, with the key attributes being displayed to a user on a display, thereby prompting the user to annotate the key attributes with class label. An attribute database is then generated based on user prompted annotations of the key attributes. A test image can then be passed through the system, allowing the system to classify at least one object in the test image by identifying an object class in the attribute database. Finally, a device can be caused to operate or maneuver based on the classification of the at least one object in the test image.

An image processing apparatus, an image processing method, and a program, provide accurate collation even when an image contains a number of identical or similar subjects. The image processing apparatus generates, with respect to feature points to be detected from a first image, a first local feature amount group including local feature amounts representing feature amounts of local regions containing the respective feature points, and a first coordinate position information group including coordinate position information. The image processing apparatus clusters the feature points of the first image based on the first coordinate position information group. The image processing apparatus collates, in units of clusters, the first local feature amount group with a second local feature amount group formed from local feature amounts of feature points detected from a second image.

A diagnostic tool for deep learning similarity models and image classifiers provides valuable insight into neural network decision-making. A disclosed solution generates a saliency map by: receiving a test image; determining, with an image classifier, an image classification of the test image; determining, for the test image, a first activation map for at least one model layer using the determined image classification; determining, for the test image, a first gradient map for the at least one model layer using the determined image classification; and generating a first saliency map as an element-wise function of the first activation map and the first gradient map.

Taste and smell classification from multilanguage descriptions can be performed by extracting, by one or more processors using natural language processing, a text including one or more words associated with taste and smell perceptions from an input received from a plurality of users. The input includes multilanguage information regarding at least one of changes in smell and changes in taste perceived by each of the plurality of users. Feature vectors are generated for the text extracted from the input using global vectors, and a distance between the feature vectors and a plurality of reference descriptors associated with taste and smell is calculated for determining a similarity between the text and the reference descriptors and creating a training dataset based on which a classification model is generated for categorizing the plurality of users according to the at least one of changes in smell and changes in taste.