Literature Survey on Stereo Vision Disparity Map Algorithms

Abstract

This paper presents a literature survey on existing disparity map algorithms. It focuses on four main stages of processing as proposed by Scharstein and Szeliski in a taxonomy and evaluation of dense two-frame stereo correspondence algorithms performed in 2002. To assist future researchers in developing their own stereo matching algorithms, a summary of the existing algorithms developed for every stage of processing is also provided. The survey also notes the implementation of previous software-based and hardware-based algorithms. Generally, the main processing module for a software-based implementation uses only a central processing unit. By contrast, a hardware-based implementation requires one or more additional processors for its processing module, such as graphical processing unit or a field programmable gate array. This literature survey also presents a method of qualitative measurement that is widely used by researchers in the area of stereo vision disparity mappings.

Stereo Matching Algorithm Based on Illumination Control to Improve the Accuracy

“…By means of this survey (Hamzah and Ibrahim, 2016), the crucial part is to develop the preliminary of disparity map which contributes to the overall performance of disparity map accuracy. The preliminary of disparity map is produced at the matching cost computation process (i.e., Step 1).…”

“…The local method applies a small number of pixels around the pixel of interest. These methods are also referred as window-based or area-based methods (Hamzah and Ibrahim, 2016). There are several approaches related to window-based such as fixed window (Yang et al, 2014), multiple window (Hirschmuller et al, 2002) and adaptive window (Lu et al, 2008).…”

High-Speed Low-Complexity Guided Image Filtering-Based Disparity Estimation

“…and meet these constraints for producing a viable embedded stereo matching system. Thorough analysis of the existing literature shows that, despite having low-error rate in the disparity computation, state-of-the-art DSPs can not support global stereo matching algorithms due to intensive computational needs [2], [3]. A viable alternative to this could be GPU-based implementations but at the expense of high cost and power-consumption for real-time designs [4].…”

“…SGM methods are therefore more affordable for dedicated hardware implementations, but still consume significant memory to store the interim cost of different aggregation paths. In contrast, local algorithms use block matching and winner-takes-all optimization to determine the disparity associated with a minimum cost function at each pixel [3]. Hence, they have lower computational complexity and memory requirements compared to global and SGM methods.…”

“…The recently proposed Guided Image Filter (GIF) [19] has been employed in [20]- [22] to reduce the complexity of the cost aggregation step in ADSW methods, leading to a high-quality fast and simple algorithm consisting of the following steps: cost volume construction, cost volume filtering, disparity selection and disparity refinement. Cost Volume Construction (CVC) is a measure of calculating a cost between two pixels, one from the left image and one from the right image, to identify the disparity corresponding to the depth of a point in the scene [3]. The information obtained by matching single pixels is not sufficient for precise matching.…”