SSDs are not global matching algorithms, others are.
The 4 words in the options have the following meanings:
A. Dynamic planning: Dynamic Programming (English: Dynamical programming, referred to as DP) is a method of solving complex problems by decomposing the original problem into relatively simple sub-problems in mathematics, computer science, and economics.
B. Figure cut: is the abbreviation for "Image Segmentation" (segmentation). In the field of computer vision, image segmentation refers to the process of subdividing a digital image into multiple image sub-regions (a collection of pixels) (also known as hyper-pixels). The purpose of image segmentation is to simplify or change the representation of images, making images 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 a process of tagging each pixel in an image, a process that allows pixels with the same label to have some common visual characteristics. The result of the image segmentation is a collection of sub-regions on the image (the whole of these sub-regions are covered by the entire image), or a collection of contour lines extracted from the image (such as edge detection). Each pixel in a sub-region is similar to a measure of an attribute or a computed attribute, such as color, brightness, and texture. The adjacency area is very different under the measure of some characteristic.
C. BP: Reverse propagation algorithm (English: backpropagation algorithm, abbreviation: BP algorithm) is a supervised learning algorithm, which is often used to train multilayer perceptron. In 1974, Paul Werbos first gave a learning algorithm for how to train a general network, and the artificial neural network is just one of the exceptions. Unfortunately, no one in the entire artificial neural network community was aware of Paul's proposed learning algorithm. Until the middle of the 80, the BP algorithm was discovered independently by David Rumelhart, Geoffrey Hinton and Ronald Williams, David Parker and Yann LeCun, and gained extensive attention, resulting in the field of artificial neural networks Study of the second craze. The BP algorithm is a generalization of the Delta rules for multilayer feedforward neural networks, and it is possible to iteratively compute the gradient of each layer using chain rules. The BP algorithm requires that the excitation function used by each artificial neuron (node) must be micro-functional.
D. SSD: SSD (solid State disk, SSD) is a computer storage device that takes memory as a permanent memory. Although SSDs are not using "discs" to store data, they use NAND Flash and do not have a motor that drives (drive) rotation, but people are still known as solid state drives (solid-state disk) or solid state drives (solid-state Drive). Also translated as "solid" ("Solid State Memory" abbreviation).
What kind of stereo matching algorithm is not a global matching algorithm