Fast and effective visual place recognition using binary codes and disparity information

Abstract

We present a novel approach for place recognition and loop closure detection based on binary codes and disparity information using stereo images. Our method (ABLE-S) applies the Local Difference Binary (LDB) descriptor in a global framework to obtain a robust global image description, which is initially based on intensity and gradient pairwise comparisons. LDB has a higher descriptiveness power than other popular alternatives such as BRIEF, which only relies on intensity. In addition, we integrate disparity information into the binary descriptor (D-LDB). Disparity provides valuable information which decreases the effect of some typical problems in place recognition such as perceptual aliasing.The KITTI Odometry dataset is mainly used to test our approach due to its varied environments, challenging situations and length. Additionally, a loop closure ground-truth is introduced in this work for the KITTI Odometry benchmark with the aim of standardizing a robust evaluation methodology for comparing different previous algorithms against our method and for future benchmarking of new proposals. Attending to the presented results, our method allows a fast and more effective visual loop closure detection compared to state-of-the-art algorithms such as FAB-MAP, WI-SURF and BRIEF-Gist.

iBoW-LCD: An Appearance-Based Loop-Closure Detection Approach Using Incremental Bags of Binary Words

“…The following public datasets, taken under different visual conditions, have been considered for the evaluation: City Centre [2] (CC), New College [2] (NC), Lip6 Indoor [4] (L6I), Lip6 Outdoor [4] (L6O), KITTI 00 [38] (K00) and KITTI 06 [38] (K06). For benchmarking purposes, we use the ground truth provided by the original authors of each method except for the KITTI sequences, where the files provided by [26] are employed as a reference. This last ground truth was created manually by the authors, labelling as long stops the time intervals where the vehicle was not in motion.…”

Expert video-surveillance system for real-time detection of suspicious behaviors in shopping malls

“…In future works, other type of features apart from the used in our people tracking could be proposed for describing visual appearance in this kind of systems, such as the fast binary descriptors, which have been satisfactorily tested in other computer vision areas related to video-surveillance such as place recognition (Arroyo et al, 2014a(Arroyo et al, ,b, 2015. As other future upgrade to our expert system, the conditions applied in blob fusion method can add a global score for each blob candidate in order to create a hypotheses search space in which to find the highest scoring fusion proposal.…”

Impact Assessment of Image Feature Extractors on the Performance of Slam Systems

“…Recently, a novel stereo feature extractors have been proposed, e.g., [17], which motivates us to con-sider them in S-PTAM. An evaluation of the novel extractors is a subject of our future work.…”