An image processing device according to one aspect of the present disclosure includes: at least one memory storing a set of instructions; and at least one processor configured to execute the set of instructions to: receive a visible image of a face; receive a near-infrared image of the face; adjust brightness of the visible image based on a frequency distribution of pixel values of the visible image and a frequency distribution of pixel values of the near-infrared image; specify a relative position at which the visible image is related to the near-infrared image; invert adjusted brightness of the visible image; detect a region of a pupil from a synthetic image obtained by adding up the visible image the brightness of which is inverted and the near-infrared image based on the relative position; and output information on the detected pupil.

Disclosed is a cross-modality person re-identification method based on local information learning, the method comprising the following steps: acquiring a standard data set and performing data enhancement on the standard data set; dividing the enhanced standard data set into a training set and a test set; constructing a cross-modality person re-identification training network based on a dual-stream ResNet50 convolutional neural network architecture; inputting the training set into the cross-modality person re-identification training network to obtain a cross-modality person re-identification test network through training; randomly selecting an image to be queried from the test set, and inputting the image to be queried and a candidate database from the test set into the cross-modality person re-identification test network to obtain an identification accuracy value corresponding to the image to be queried.

A local computing device receives lidar data and radar data from one or more road side units (RSUs). The local computing device performs ground plane removal based on range to detect targets and perform local sensor fusion. The local computing device may use a global nearest neighbor (GNN) algorithm and a Kalman filter. The local computing device may create an HD map or the data may be brought together with other target data at a central computing device to produce the HD map. Vehicle position and motion are controlled based on the HD map. Detecting and removing a ground plane based on range are illustrated. Fusion, ground plane removal, and delay filtering may be used in various contexts, such as roadways, parking lots and shipping yards.

In some implementations, a device may receive image data identifying images of a space with racks and objects stored on the racks. The device may receive location data identifying location coordinates associated with the images. The device may process the image data and the location data to generate a merged point cloud identifying the racks and the objects in the space. The device may process the image data to generate mask data identifying at least a first mask for the racks and a second mask for the objects. The device may process the location data, the merged point cloud, and the mask data to generate a semantic point cloud identifying the racks and the objects in the space. The device may process the semantic point cloud, with a computer vision model, to calculate utilization metrics for the space.

Techniques for clustering sensor data are discussed herein. Sensors of a vehicle may detect data points in an environment. Clustering techniques can be used in a vehicle safety system to determine connection information between the data points. The connection information can be used by a vehicle computing device that employs clustering and/or segmenting techniques to detect objects in an environment and/or to control operation of a vehicle.

Systems and methods for realizing practical applications of high speed digital image correlation (DIC) for dynamic quantities of interest are provided. In particular, a series of images are captured for a component of interest in which a non-filtered sensor and an analog low-pass filtered sensor are included within the region of interest for the series of images. Displacement signals are obtained for the component of interest, the non-filtered sensor, and the analog low-pass filtered sensor by applying digital image correlation processing to the series of images, which may also be wavelet filtered. Dynamic quantities of interest may be generated and derived from the displacement signals after having been wavelet filtered. Such dynamic quantities of interest based on the wavelet filtered DIC-derived displacement signal may be compared to sensor-derived dynamic quantities of interest to determine if aliasing is or is likely to be present.

System, device, and method of Augmented Reality based mapping of a venue and navigation within a venue. A method includes: performing a crowd-sourced mapping process, that maps a retail store and maps particular products sold within that retail store, based on computer-vision analysis of a plurality of images captured by a plurality of end-user devices of customers within that retail store; and generating a representation of a store map reflecting actual real-time location of particular products within that retail store. Turn-by-turn walking directions are provided, to guide the user from his current in-store location towards a destination product within that retail store. Augmented Reality promotions, advertisements and marketing content elements, route guidance, and other content are generated and displayed on the end-user device.

A security device is disclosed. The security device includes multiple fingerprint sensors. Activating the security device requires users to enter an authentication sequence comprised of different finger-to-fingerprint-sensor combinations. This increases the number of available distinct elements that can be used in an authentication sequence of a given length for a fixed number of buttons. The device also combines two different modes of authentication to improve security. The security device can be integrated into motor vehicles, mobile computing devices or other systems.

System, methods, and other embodiments described herein relate to improving clustering of points within a point cloud. In one embodiment, a method includes grouping the points into cells of a grid. The grid divides an observed region of a surrounding environment associated with the point cloud into the cells. The method includes computing feature vectors for the cells that use cell features to characterize the points in the cells and relationships between the cells. The method includes analyzing the feature vectors according to a clustering model to identify clusters for the cells. The clustering model evaluates the cells to identify which of the cells belong to common entities. The method includes providing the clusters as assignments of the points to the entities depicted in the point cloud.

A method estimates a course of a roadway in a vicinity of a vehicle based on a state function describing the course of the roadway, wherein the state function includes a clothoid spline. The method includes providing ambient measured data describing the course of the roadway at a current position of the vehicle, where the ambient measured data includes a polynomial function. The method also includes transforming the state function and the ambient measured data into a common coordinate system, and checking the ambient measured data for an error. If no error is detected, then the state function is adapted based on the ambient measured data in the common coordinate system. If an error is detected, then the error is stored.