AnyDijkstra, an algorithm to compute shortest paths on images with anytime properties

TL;DR

AnyDijkstra is a novel iterative algorithm for shortest path computation on images that offers anytime results, optimized for memory access and parallel execution, improving efficiency over traditional methods.

Contribution

It introduces an iterative, cache-friendly, and parallelizable version of Dijkstra's algorithm tailored for image graphs, with anytime capabilities.

Findings

Provides faster shortest path computations on images.

Retains anytime properties for incremental results.

Optimized for memory access and parallel processing.

Abstract

Images conveniently capture the result of physical processes, representing rich source of information for data driven medicine, engineering, and science. The modeling of an image as a graph allows the application of graph-based algorithms for content analysis. Amongst these, one of the most used is the Dijkstra Single Source Shortest Path algorithm (DSSSP), which computes the path with minimal cost from one starting node to all the other nodes of the graph. However, the results of DSSSP remains unknown for nodes until they are explored. Moreover, DSSSP execution is associated to frequent jumps between distant locations in the graph, which results in non-optimal memory access, reduced parallelization, and finally increased execution time. Therefore, we propose AnyDijkstra, an iterative implementation of the Dijkstra SSSP algorithm optimized for images, that retains anytime properties while accessing memory following a cache-friendly scheme and maximizing parallelization.