Review of Serial and Parallel Min-Cut/Max-Flow Algorithms for Computer Vision

Abstract

Minimum cut/maximum flow (min-cut/max-flow) algorithms solve a variety of problems in computer vision and thus significant effort has been put into developing fast min-cut/max-flow algorithms. As a result, it is difficult to choose an ideal algorithm for a given problem. Furthermore, parallel algorithms have not been thoroughly compared. In this paper, we evaluate the state-of-the-art serial and parallel min-cut/max-flow algorithms on the largest set of computer vision problems yet. We focus on generic algorithms, i.e., for unstructured graphs, but also compare with the specialized GridCut implementation. When applicable, GridCut performs best. Otherwise, the two pseudoflow algorithms, Hochbaum pseudoflow and excesses incremental breadth first search, achieves the overall best performance. The most memory efficient implementation tested is the Boykov-Kolmogorov algorithm. Amongst generic parallel algorithms, we find the bottom-up merging approach by Liu and Sun to be best, but no method is dominant. Of the generic parallel methods, only the parallel preflow push-relabel algorithm is able to efficiently scale with many processors across problem sizes, and no generic parallel method consistently outperforms serial algorithms. Finally, we provide and evaluate strategies for algorithm selection to obtain good expected performance. We make our dataset and implementations publicly available for further research.

Research on intelligent perception of computer vision environment for autonomous driving in complex environment based on cloud computing and improved Bayesian algorithm

“…Finally, the test data set is used to verify the classification accuracy of the model. The results show that the model has higher automation degree, The biggest feature of DeepSORT is to add appearance information, borrow ReID module to extract deep learning features, and reduce the number of ID switches [10].…”

Trajectory Tracking Control Method for Flexible Robot of Construction Machinery Based on Computer Vision

“…However, with the emergence and popularization of computer vision and human interactive platform systems and the continuous enrichment and improvement of relevant theoretical achievements [1][2]. More and more important topics with high-precision motion control algorithms and methods developed in the field of computer vision to solve practical problems have become one of the new trends in recent years, among which the most typical is the research on the application of object-oriented programming technology in robots [3][4].…”