Limits...
Loop Closing Detection in RGB-D SLAM Combining Appearance and Geometric Constraints.

Zhang H, Liu Y, Tan J - Sensors (Basel) (2015)

Bottom Line: The visual feature is encoded with BRAND (binary robust appearance and normals descriptor), which efficiently combines appearance and geometric shape information from RGB-D images.Furthermore, the feature descriptors are stored using the Locality-Sensitive-Hashing (LSH) technique and hierarchical clustering trees are used to search for these binary features.We demonstrate the efficiency of our algorithms by real-time RGB-D SLAM with loop closing detection in indoor image sequences taken with a handheld Kinect camera and comparative experiments using other algorithms in RTAB-Map dealing with a benchmark dataset.

View Article: PubMed Central - PubMed

Affiliation: School of Information Engineering, East China Jiaotong University, Nanchang 330013, China. hzhang69@utk.edu.

ABSTRACT
A kind of multi feature points matching algorithm fusing local geometric constraints is proposed for the purpose of quickly loop closing detection in RGB-D Simultaneous Localization and Mapping (SLAM). The visual feature is encoded with BRAND (binary robust appearance and normals descriptor), which efficiently combines appearance and geometric shape information from RGB-D images. Furthermore, the feature descriptors are stored using the Locality-Sensitive-Hashing (LSH) technique and hierarchical clustering trees are used to search for these binary features. Finally, the algorithm for matching of multi feature points using local geometric constraints is provided, which can effectively reject the possible false closure hypotheses. We demonstrate the efficiency of our algorithms by real-time RGB-D SLAM with loop closing detection in indoor image sequences taken with a handheld Kinect camera and comparative experiments using other algorithms in RTAB-Map dealing with a benchmark dataset.

No MeSH data available.


The schematic diagram of LSH.
© Copyright Policy
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC4507625&req=5

f2-sensors-15-14639: The schematic diagram of LSH.

Mentions: As shown in Figure 2, the idea of LSH is to hash the points in a way that the probability of collision is much higher for points which are close to each other than for those which are far apart. In Figure 2, the point p and q are close in the original space, so they are projected into the same bin. The core of LSH algorithm is to construct a set of hash functions that keep the relativity of distance and use the function to classify the similar data into the same hash bucket. In this work, the similarity measure is the Hamming distance, so the hashing function is a subset of bits of the binary number. Similar features have greater possibility to be fallen into the same bucket. When matching, feature points in the same bucket with matching points are considered as a candidate set. Consequently, a large number of features which are not in the same bucket are excluded.


Loop Closing Detection in RGB-D SLAM Combining Appearance and Geometric Constraints.

Zhang H, Liu Y, Tan J - Sensors (Basel) (2015)

The schematic diagram of LSH.
© Copyright Policy
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC4507625&req=5

f2-sensors-15-14639: The schematic diagram of LSH.
Mentions: As shown in Figure 2, the idea of LSH is to hash the points in a way that the probability of collision is much higher for points which are close to each other than for those which are far apart. In Figure 2, the point p and q are close in the original space, so they are projected into the same bin. The core of LSH algorithm is to construct a set of hash functions that keep the relativity of distance and use the function to classify the similar data into the same hash bucket. In this work, the similarity measure is the Hamming distance, so the hashing function is a subset of bits of the binary number. Similar features have greater possibility to be fallen into the same bucket. When matching, feature points in the same bucket with matching points are considered as a candidate set. Consequently, a large number of features which are not in the same bucket are excluded.

Bottom Line: The visual feature is encoded with BRAND (binary robust appearance and normals descriptor), which efficiently combines appearance and geometric shape information from RGB-D images.Furthermore, the feature descriptors are stored using the Locality-Sensitive-Hashing (LSH) technique and hierarchical clustering trees are used to search for these binary features.We demonstrate the efficiency of our algorithms by real-time RGB-D SLAM with loop closing detection in indoor image sequences taken with a handheld Kinect camera and comparative experiments using other algorithms in RTAB-Map dealing with a benchmark dataset.

View Article: PubMed Central - PubMed

Affiliation: School of Information Engineering, East China Jiaotong University, Nanchang 330013, China. hzhang69@utk.edu.

ABSTRACT
A kind of multi feature points matching algorithm fusing local geometric constraints is proposed for the purpose of quickly loop closing detection in RGB-D Simultaneous Localization and Mapping (SLAM). The visual feature is encoded with BRAND (binary robust appearance and normals descriptor), which efficiently combines appearance and geometric shape information from RGB-D images. Furthermore, the feature descriptors are stored using the Locality-Sensitive-Hashing (LSH) technique and hierarchical clustering trees are used to search for these binary features. Finally, the algorithm for matching of multi feature points using local geometric constraints is provided, which can effectively reject the possible false closure hypotheses. We demonstrate the efficiency of our algorithms by real-time RGB-D SLAM with loop closing detection in indoor image sequences taken with a handheld Kinect camera and comparative experiments using other algorithms in RTAB-Map dealing with a benchmark dataset.

No MeSH data available.