An Empirical Comparison of Real-time Dense Stereo Approaches for use in the Automotive Environment

Abstract

In this work we evaluate the use of several real-time dense stereo algorithms as a passive 3D sensing technology for potential use as part of a driver assistance system or autonomous vehicle guidance. A key limitation in prior work in this area is that although significant comparative work has been done on dense stereo algorithms using de facto laboratory test sets only limited work has been done on evaluation in real world environments such as that found in potential automotive usage. This comparative study aims to provide an empirical comparison using automotive environment video imagery and compare this against dense stereo results drawn on standard test sequences in addition to considering the computational requirement against performance in real-time. We evaluate five chosen algorithms: Block Matching, Semi-Global Matching, No-Maximal Disparity, Cross-Based Local Approach, Adaptive Aggregation with Dynamic Programming. Our comparison shows a contrast between the results obtained on standard test sequences and those for automotive application imagery where a Semi-Global Matching approach gave the best empirical performance. From our study we can conclude that the noise present in automotive applications, can impact the quality of the depth information output from more complex algorithms (No-Maximal Disparity, Cross-Based Local Approach, Adaptive Aggregation with Dynamic Programming) resulting that in practice the disparity maps produced are comparable with those of simpler approaches such as Block Matching and Semi-Global Matching which empirically perform better in the automotive environment test sequences. This empirical result on automotive environment data contradicts the comparative result found on standard dense stereo test sequences using a statistical comparison methodology leading to interesting observations regarding current relative evaulation approaches.