China
Africa
Explore chapters and articles related to this topic
Layout Extraction
Published in Louis Scheffer, Luciano Lavagno, Grant Martin, EDA for IC Implementation, Circuit Design, and Process Technology, 2018
William Kao, Chi-Yuan Lo, Mark Basel, Raminderpal Singh, Peter Spink, Louis Scheffer
The ultimate result of layout extraction will be a circuit description in a form that can be used by a simulator or analysis program. This can be (and originally was) achieved by writing the extracted results out directly as a text file in the simulator language. Today however, it is more likely that the extraction program is part of a larger system. The overall system will enable such features as viewing the extracted circuit on top of the layout; cross-probing the extracted circuit relative to the layout and the logic diagram; and translating the extracted circuit into different text formats for different analysis programs. Each of these functions will require different information from the extraction process stored in the database. What the content and format of this output is will depend on the overall system and database design, but it will probably include physical shapes representing the extracted circuit and devices, in addition to circuit interconnect information to represent the logical extracted circuit.
Overview
Published in Louis Scheffer, Luciano Lavagno, Grant Martin, EDA for IC System Design, Verification, and Testing, 2018
Luciano Lavagno, Grant Martin, Louis Scheffer
Layout extraction is the translation of the topological layout back into the electrical circuit it is intended to represent. This chapter discusses the distinction between designed and parasitic devices, and discusses the three major parts of extraction: designed device extraction, interconnect extraction, and parasitic device extraction.
Indoor scene texturing based on single mobile phone images and 3D model fusion
Published in International Journal of Digital Earth, 2019
Hanjiang Xiong, Wei Ma, Xianwei Zheng, Jianya Gong, Douadi Abdelalim
Single image-based spatial layout extraction is one of the most fundamental tasks in computer vision and image understanding. Recently, machine-learning algorithms have shown outstanding performance in fulfilling this task. In our sense, those approaches can be divided into two major phases. In the first phase, researchers employed only geometry oriented techniques to estimate objects and layout candidates, determining the best matches using Structure Learning. With the advent of deep learning, came the second category of layout extraction approaches that introduced FCN to add features to the process and enhance the extraction results.