Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for learning template representation libraries. In one aspect, a method includes obtaining an image depicting a physical environment, where the environment includes a given physical object. When possible, a position of the given object in the environment is inferred based on a template representation library using template matching techniques. In response to determining that the position of the given object in the environment cannot be inferred based on the template representation library using template matching techniques, the template representation library is automatically augmented with new template representations.

Ultrasound-based acoustic streaming for deciding whether material is fluid is dependent upon any one or more of a variety of criteria. Examples are displacement, speed (230), temporal or spatial flow variance, progressive decorrelation, slope or straightness of accumulated signal to background comparisons over time, and relative displacement to adjacent soft tissue. Echogenicity-based area identification is combinable with the above movement characteristic detection in the deciding. Fluid pool identification is performable from the area-limited acoustic streaming testing and ultrasound attenuation readings. Candidates from among the areas (210) are screenable based on specific shapes or bodily organs detected. Natural flow can be excluded from streaming detection by identification of blood vessels (206). Processing for each FAST ultrasound view (202), or for the entire procedure, is performable automatically, without need for user intervention or with user intervention to identify suspected areas.

Techniques and systems are described for performing video segmentation using fully connected object proposals. For example, a number of object proposals for a video sequence are generated. A pruning step can be performed to retain high quality proposals that have sufficient discriminative power. A classifier can be used to provide a rough classification and subsampling of the data to reduce the size of the proposal space, while preserving a large pool of candidate proposals. A final labeling of the candidate proposals can then be determined, such as a foreground or background designation for each object proposal, by solving for a posteriori probability of a fully connected conditional random field, over which an energy function can be defined and minimized.

A computer-implemented method for segmenting an object in at least one image acquired by a camera including computing an edge probabilities image based on the image, said edge probabilities image comprising, for each pixel of the image, the probability that said pixel is an edge, computing a segmentation probabilities image based on the image (IM), said segmentation probabilities image comprising, for each pixel of the image (IM), the probability that said pixel belongs to the object (OBJ), and computing a binary mask of the object based on the edge probabilities image and based on the segmentation probabilities image.

A lesion detecting method and a lesion detecting apparatus for breast image in a rotating manner are provided. In the method, a set of breast image in the rotating manner is obtained. The set of breast image in the rotating manner contains sub breast images. The sub breast image is reconstructed, to generate a reconstructed breast image. The reconstructed breast image is compared with the set of breast image in the rotating manner without being reconstructed. Accordingly, at least one lesion position would be confirmed according to the comparing result. Therefore, viewing a three-dimensional breast image would be convenient for medical staff, and false positive of detecting lesion would be reduced.

Global and local alignment energies are used in an image contrast metric. The image contrast metric can be used to find optical targets. Some pixels from a gradient magnitude image and a context range image from an optical image can be used to determine the image contrast metric. A heatmap from the image contrast metrics across part of a wafer can then be used to make a list of targets. Upper and lower confidence values can be applied to rank the available targets.

Systems and methods for determining a breast region in a medical image are provided. The methods may include obtaining a first image relating to the breast region, determining a first region including a first plurality of pixels in the breast region, determining a second region including a second plurality of pixels relating to an edge of the breast region, and determining the breast region by combining the first region and the second region. The second plurality of pixels may include at least a portion of the first plurality of pixels.

Motorized machinery, such as overhead cranes, are widely used in industries all over the world. It is not easy to move crane payloads without oscillation, increasing the likelihood of obstacle collisions and other accidents. One possible solution to such problems could be aiding the operator with a dynamic map of the workspace that shows the current position of obstacles. This method discloses the use of a camera to take images of the workspace, using imaging blurring to smooth the obtained images, and drawing contours to produce an individual, near real-time map of the workspace. In one or more embodiments, known obstacles may be tagged in a manner which is readable by the camera. This image and historical images of the same workspace are layered on top of one another to produce a map of obstacles on the workspace floor. This imaging and layering can produce a near real-time map of obstacles that can be used to guide heavy motorized machinery around a workspace without incident.

Methods, systems, and apparatuses for detecting and describing heterogeneity in a cell sample are disclosed herein. A plurality of fields of view (FOV) are generated for one or more areas of interest (AOI) within an image of the cell sample are generated. Hyperspectral or multispectral data from each FOV is organized into an image stack containing one or more z-layers, with each z-layer containing intensity data for a single marker at each pixel in the FOV. A cluster analysis is applied to the image stacks, wherein the clustering algorithm groups pixels having a similar ratio of detectable marker intensity across layers of the z-axis, thereby generating a plurality of clusters having similar expression patterns.

Methods, devices, and systems for automated cellular analysis of a body fluid sample are disclosed. The methods, devices, and systems apply watershed transform to data, generated by flowing a body fluid sample through a flow cytometer, to determine threshold(s) to be used for analysis of the data.