A system and method are disclosed for solving a supply chain planning problem modeled as a linear programming (LP) problem. Embodiments include receiving a matrix formulation of at least a portion of the LP problem representing a supply chain planning problem for a supply chain network, generating an image based on the matrix formulation to identify connected components, partitioning the matrix formulation based, at least in part, on the connected components constraint into at least two partitions, formulating an LP subproblem from each of the at least two partitions, and solving the LP subproblems to generate a global solution to the supply chain planning problem.

A method for estimating and presenting a passenger flow, a system, and a computer storage medium. The method comprises: performing two-level scene classification on received on-site video data transmitted by a camera; configuring a passenger flow analysis algorithm corresponding to a scene according to a scene classification result; and analyzing a video frame according to the passenger flow analysis algorithm, outputting a passenger flow calculation result, determining, according to the passenger flow calculation result, a crowdedness level of a passenger flow at a location corresponding to the camera, and respectively transmitting the crowdedness level of the passenger flow to a first terminal and a second terminal for display of the crowdedness level of the passenger flow.

Provided is a driving assistance system including a storage device having a program stored therein and a hardware processor, wherein the hardware processor executes the program stored in the storage device, to thereby recognize an object which is present outside of a vehicle on the basis of a detection result of at least one of a radar device and an imaging device which are mounted in the vehicle, perform driving assistance for the vehicle on the basis of a recognition result, and determine a degree of matching between a portion of a contour line of the object and a road partition line and suppress an operation of the driving assistance in a case where the degree of matching is equal to or greater than a threshold.

A method of inspecting patterns to-be-inspected having regular intervals, the same widths and heights by using an image of the patterns to-be-inspected is disclosed. The method includes the steps of: obtaining centroids, widths and heights of the patterns to-be-inspected from an image of the patterns to-be-inspected; obtaining regular intervals, a mean of widths and a mean of heights of the patterns to-be-inspected, as information of design data, from the centroids, the widths and the heights; and inspecting the patterns to-be-inspected by using the information of the design data and edges of the image of the patterns to-be-inspected.

A neural network is configured to process image data captured by a vehicle-mounted camera. The neural network includes common processing layers (a trunk) and separate, parallelizable processing layers (branches). An object detection branch of the neural network is trained to detect objects that may be visible from the vehicle-mounted camera, such as cars, trucks, and traffic signs. A curve determination branch is trained to detect and parameterize salient curves, such as lane boundaries and road boundaries. The curve determination branch itself is configured with a trunk and branch architecture, having both common and separate processing layers. A first branch computes a likelihood that a curve is present in a given location of the image data and a second branch further localizes the curve within the given location if such a curve is present. Training of the different branches of the neural network may be decoupled.

Examples disclosed herein relate to determining the shape of an object representation. In one implementation, a processor determines contours of a silhouette of an object representation above a contour degree threshold, where a contour degree is determined based on the area of the contour with respect to itself. The processor may identify a shape type of the object representation based on a comparison of the determined contours to shape definition information.

Methods and systems for descriptor guided fast marching method based image analysis and associated systems are disclosed. A representative image processing method includes processing an image of a microelectronic device using a fast marching algorithm to obtain arrival time information for the image. The arrival time information is analyzed using a targeted feature descriptor to identify targeted features. The detection of defects is facilitated by segmenting the image. The segmented image can be analyzed to identify targeted features which are then labeled for inspection.

A system and method are disclosed for solving a supply chain planning problem modeled as a linear programming problem. Embodiments include receiving a matrix formulation of at least a portion of the linear programming problem representing a supply chain planning problem for a supply chain network, generating an image based on the matrix formulation to identify connected components, partitioning the matrix formulation based, at least in part, on the connected components constraint into at least two partitions, formulating an linear programming subproblem from each of the at least two partitions, and solving the linear programming subproblems to generate a global solution to the supply chain planning problem.

A system and method for scoring trained probes for use in analyzing one or more candidate poses of a runtime image is provided. A set of probes with location and gradient direction based on a trained model are applied to one or more candidate poses based upon a runtime image. The applied probes each respectively include a discrete set of position offsets with respect to the gradient direction thereof. A match score is computed for each of the probes, which includes estimating a best match position for each of the probes respectively relative to one of the offsets thereof, and generating a set of individual probe scores for each of the probes, respectively at the estimated best match position.

Described is an apparatus for oxygenation and/or CO2 clearance of a patient, comprising: a flow source or a connection for a flow source for providing a gas flow, a gas flow modulator, a controller to control the gas flow, wherein the controller is operable to: receive input relating to heart activity and/or trachea gas flow of the patient, and control the gas flow modulator to provide a varying gas flow with one or more oscillating components with a frequency or frequencies based on the heart activity and/or trachea flow of the patient.