Aspects herein provide a system, methods, and media for applying labels to objects without overlapping or obscuring existing labels or other indicia. In some aspects, an object in motion and labels or indicia on the object are visually identified using near real-time imaging and details of geometric characteristics are determined. An additional label is then generated, printed, and physically applied or attached to the object in motion so that the angle, placement, and orientation of the additional label matches or aligns with the existing labels or indicia, without overlapping or obscuring the existing labels or indicia.

The present disclosure provides a computer-implemented method, a device, and a computer program product for deep lesion tracker. The method includes inputting a search image into a first three-dimensional DenseFPN (feature pyramid network) of an image encoder and inputting a template image into a second three-dimensional DenseFPN of the image encoder to extract image features; encoding anatomy signals of the search image and the template image as Gaussian heatmaps, and inputting the Gaussian heatmap of the template image into a first anatomy signal encoders (ASE) and inputting the Gaussian heatmap of the search image into a second ASE to extract anatomy features; inputting the image features and the anatomy features into a fast cross-correlation layer to generate correspondence maps, and computing a probability map according to the correspondence maps; and performing supervised learning or self-supervised learning to predict a lesion center in the search image.

An approach is provided for detecting and map-coding a tunnel based on probes and image data. The approach involves, for example, identifying a gap in probe data collected from one or more location sensors of a plurality vehicles. The gap represents a probe gap segment along which at least one probe point of the probe data does not occur or occurs below a threshold number. The approach also involves retrieving image data depicting a geographic area based on location coordinate data associated with the gap. The approach further involves processing the image data to identify one or more end points of a road network depicted in the image data. The approach further involves locating a tunnel start point and/or a tunnel end point based on the one or more endpoints. The approach further involves providing the tunnel start point and/or the tunnel end point as a map data output.

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 for determining a semantic free space in an environment of a vehicle comprises capturing a two dimensional visual image from the environment of the vehicle via a camera and determining a limitation of a free space within the visual image. Via a sensor, distance data of objects are captured and assigned to the visual image, and the limitation of the free space is transferred to a bird's-eye view based on the assigned distance data. For objects identified in the visual image a respective bounding box and a respective classification are determined. Objects limiting the free space are selected, and their bounding box is assigned to the limitation of the free space in the bird's-eye view. Finally, segments of the limitation of the free space are classified according to the classification of each bounding box of the selected objects.

A method, an apparatus, a computing device, and a computer-readable storage medium for correcting pedestrian trajectory are disclosed. The method includes obtaining face image frames and body image frames, determining a face identifier for a face area in each of the face image frames, determining an uncorrected face trajectory for the face identifier, determining a body identifier for a body area in each of the body image frames, determining an uncorrected body trajectory for the body identifier, for each of the face image frames and each of the body image frames that are at a same moment, establishing a set of matching relationship between the face identifier and the body identifier, and correcting at least one of the uncorrected face trajectory and the uncorrected body trajectory based on a plurality of sets of matching relationship of a plurality of same moments.

Provided are a device and a method for determining an edge location based on the adaptive weighting of gradients (AWG). The method for determining an edge location according to an embodiment of the present invention includes the steps of determining, based on the edge width of an edge profile in an image, a power factor to be applied to a gradient of the edge profile in order to determine an edge location, calculating a difference value between values of adjacent pixels in the edge profile to generate the gradient, and applying the power factor determined based on the edge width to the gradient to determine the edge location.

A person re-identification device comprises: a feature extracting and dividing unit, that receives images including a person to be re-identified and extracts a feature of each image according to a pre-learned pattern estimation method to acquire a 3-dimensional feature vector, and divides the 3-dimensional feature vector into a pre-designated size unit to acquire local feature vectors; a one-to-many relational reasoning unit, that estimates the relationship between each of the local feature vectors and remaining local feature vectors, and reflects the estimated relationship to acquire local relational features; a global contrastive pooling unit, that acquires a global contrastive feature by performing global contrastive pooling; and a person re-identification unit, that receives the local relational features and the global contrastive feature as a final descriptor of a corresponding image, and compares the final descriptor with a reference descriptor acquired in advance from an image including a person to be searched.

A method is for generating element templates for forming templates when checking value documents of a specified value document type having at least two specified manufacturing elements, which, where applicable, partially overlap each other, and the element templates correspond to the manufacturing elements. Digital training images of training value documents of the specified value document type and a digital reference image of a reference value document of the specified value document type are used, which each have pixels to which pixel data are respectively assigned.

In various examples, sensor data representative of an image of a field of view of a vehicle sensor may be received and the sensor data may be applied to a machine learning model. The machine learning model may compute a segmentation mask representative of portions of the image corresponding to lane markings of the driving surface of the vehicle. Analysis of the segmentation mask may be performed to determine lane marking types, and lane boundaries may be generated by performing curve fitting on the lane markings corresponding to each of the lane marking types. The data representative of the lane boundaries may then be sent to a component of the vehicle for use in navigating the vehicle through the driving surface.