Which stereo matching algorithm is not a global matching algorithm

SSD is not a global matching algorithm, others are.

    The meanings of the four words in the options are as follows:

    A. Dynamic programming: Dynamic programming (DP) is a method used in mathematics, computer science and economics to decompose an original problem into relatively simple A method for solving complex problems in the form of subproblems.

    B. Graph Cut: It is the abbreviation of "Segmentation". In the field of computer vision, image segmentation refers to the process of subdividing a digital image into multiple image sub-regions (collections of pixels) (also known as superpixels). The purpose of image segmentation is to simplify or change the representation of an image so that it is easier to understand and analyze. Image segmentation is often used to locate objects and boundaries (lines, curves, etc.) in an image. More precisely, image segmentation is the process of labeling each pixel in an image such that pixels with the same label share some common visual property. The result of image segmentation is a collection of sub-regions on the image (the entirety of these sub-regions covers the entire image), or a collection of contour lines extracted from the image (eg edge detection). Each pixel in a sub-region is similar under some measure of characteristic or calculated characteristic, such as color, brightness, texture. Adjacent regions are very different under the metric of a certain characteristic.

    C. BP: Backpropagation algorithm (English: Backpropagation algorithm, referred to as: BP algorithm) is a supervised learning algorithm that is often used to train multilayer perceptrons. In 1974, Paul Werbos first showed how to train a learning algorithm for general networks, of which artificial neural networks are only a special case. Unfortunately, the learning algorithm proposed by Paul was unknown in the entire artificial neural network community at the time. It was not until the mid-1980s that the BP algorithm was independently discovered by David Rumelhart, Geoffrey Hinton, Ronald Williams, David Parker and Yann LeCun, and gained widespread attention, causing a second upsurge in the field of artificial neural networks. The BP algorithm is a generalization of the multi-layer forward neural network Delta rule, and it is possible to use the chain rule to iteratively calculate the gradient of each layer. The BP algorithm requires that the excitation function used by each artificial neuron (node) must be differentiable.

    D. SSD: Solid State Disk (Solid State Disk, Solid State Drive, SSD for short) is a computer storage device that uses memory as permanent storage. Although SSD does not use "disk" to store data, but uses NAND Flash, and there is no motor used to drive (Drive) rotation, but people are still called solid-state disk (Solid-State Disk) or solid state according to the naming convention. Drive (Solid-State Drive). It is also translated as "solid storage" (short for "solid state memory").