Real-time stereo semi-global matching for video processing using previous incremental information

Abstract

This paper presents an incremental stereo algorithm designed to calculate a real-time disparity image. The algorithm is designed for stereo video sequences and uses previous information to reduce computation time and improve disparity image quality. It is based on the semi-global matching stereo algorithm but modified to reuse previous calculation information. Storing and reusing this information not only reduces computation time but improves accuracy in a cost filtering scheme. Some tests are presented to compare the computation time and results of the algorithm, which show that it can achieve better results in terms of quality and time than standard algorithms for some scenarios.

Cell-Based Refinement Processor Utilizing Disparity Characteristics of Road Environment for SGM-Based Stereo Vision Systems

“…In terms of the upper direction, as shown in (8), the seven pixel values from (7, 1) coordinate to (7, 7) coordinate are used for generating inner-window. In terms of the lower direction, as shown in (10), the seven pixel values from (7, 7) coordinate to (7,13) coordinate are used for generating inner-window. As a result, each inner-window must include the center pixel to ensure an odd number of pixels and reflect the center pixel value, as required for our proposed method.…”

“…This crucial information is typically derived from a disparity map, which can be readily converted into a depth map [7], [8]. On embedded platforms, the computation of the disparity map often relies on various traditional stereo matching algorithms, which can be broadly categorized into three main groups: 1) local matching (LM), 2) global matching (GM), and 3) semiglobal matching (SGM) [9], [10], [11].…”

High-Accuracy Measurement of Three-Dimensional Inclinations of Power Transmission Towers Using Reconstruction Model of Stereo Images

“…Step 1: Calculation of matching cost [18][19][20]. The stereo pair is processed by census transformation to obtain a bitstream code as follows: denotes the sort of all the values 0 or 1 in a stream, which forms bitstream codes.…”

“…The stereo pair is processed by census transformation to obtain a bitstream code as follows: denotes the sort of all the values 0 or 1 in a stream, which forms bitstream codes. The matching cost of pixel p with disparity d in each type of stereo pair is calculated using hamming distance as follows: Step 2: Calculation of cost aggregation [18][19][20]. The matching cost C k p m; ð ð nÞ; dÞ is generally ambiguous, and wrong matches can easily have a lower cost than correct ones.…”

“…Therefore, an additional constraint is added that supports smoothness by penalizing changes of neighboring disparities. Cost aggregation is calculated by referring to a semiglobal matching algorithm as follows: [18][19][20]. As for unique constraint, the minimum cost aggregation of pixel p is not close to the other cost aggregations as follows:…”