The Revisiting Problem in Simultaneous Localization and Mapping: A Survey on Visual Loop Closure Detection

Tsintotas, Konstantinos A.; Bampis, Loukas; Γαστεράτος, Αντώνιος

doi:10.1109/tits.2022.3175656

Cited by 76 publications

(31 citation statements)

References 354 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Many past methodologies for loop closure rely on specific sets of features along with a bag of words model (BoW). Exceptions to BoW exist [18], but bag of words has been shown to be useful for retrieving similar images for loop closure detection [10].…”

Section: Related Workmentioning

confidence: 99%

“…There have been many proposed methods for feature detection, but these have been split mainly into two categories. Methods like SuperPoint [7], SIFT [8], and ORB [9] are good at detecting geometric features, but fail in organic environments [10]. On the other hand, methods like SalientDSO [11], Salient Point Detection [12], and Feature Based SLAM [13], determine points of human interest, but only target key objects.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

HGI-SLAM: Loop Closure With Human and Geometric Importance Features

Mujoo¹,

Ng²

2022

Preprint

View full text Add to dashboard Cite

We present Human and Geometric Importance SLAM (HGI-SLAM), a novel approach to loop closure using salient and geometric features. Loop closure is a key element of SLAM, with many established methods for this problem. However, current methods are narrow, using either geometric or salient based features. We merge their successes into a model that outperforms both types of methods alone. Our method utilizes inexpensive monocular cameras and does not depend on depth sensors nor Lidar. HGI-SLAM utilizes geometric and salient features, processes them into descriptors, and optimizes them for a bag of words algorithm. By using a concurrent thread and combing our loop closure detection with ORB-SLAM2, our system is a complete SLAM framework. We present extensive evaluations of HGI loop detection and HGI-SLAM on the KITTI and EuRoC datasets. We also provide a qualitative analysis of our features. Our method runs in real time, and is robust to large viewpoint changes while staying accurate in organic environments. HGI-SLAM is an end-toend SLAM system that only requires monocular vision and is comparable in performance to state-of-the-art SLAM methods.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

HGI-SLAM: Loop Closure With Human and Geometric Importance Features

Mujoo¹,

Ng²

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Image retrieval and recognition, image matching, image reconstruction, digital compression, digital watermarking and motion-image sequence analysis all use geometric moments. The algorithm in this paper calculates the zero-order moment of each mask block to obtain the area of the mask block in the image, and the zero-order moment is calculated as shown in Equation (2). The first-order moment is used to calculate the centroid coordinate of each mask block, where it is regarded as a two-dimensional (2-D) semantic node, and the first-order moment calculation is shown in Equation (3).…”

Section: Momentmentioning

confidence: 99%

“…During the operation of VSLAM, both the visual sensor and the robot's motion estimation will generate errors, and if the errors continue to accumulate, they will seriously impair the mobile robot's judgment of its positioning and may even result in map construction failure [1]. Loop closure detection [2] is primarily used to determine whether the mobile robot's current position has been visited previously, which can effectively reduce the accumulated errors and achieve repositioning after the robot has lost its position, helping to ensure accurate positioning and map construction. The loop closure detection in the existing VSLAM system primarily determines whether the loop closure can be formed by calculating the similarity between the current frame and the keyframe; thus, loop closure detection is fundamentally a scene recognition and image matching problem [3,4], which compares the current scene in which the mobile robot is located in with the historical scene to determine whether the scene is the same.…”

Section: Introductionmentioning

confidence: 99%

Loop Closure Detection for Mobile Robot based on Multidimensional Image Feature Fusion

Wang

et al. 2022

Machines

View full text Add to dashboard Cite

Loop closure detection is a crucial part of VSLAM. However, the traditional loop closure detection algorithms are difficult to adapt to complex and changeable scenes. In this paper, we fuse Gist features, semantic features and appearance features of the image to detect the loop closures quickly and accurately. Firstly, we take advantage of the fast extraction speed of the Gist feature by using it to screen the loop closure candidate frames. Then, the current frame and the candidate frame are semantically segmented to obtain the mask blocks of various types of objects, and the semantic nodes are constructed to calculate the semantic similarity between them. Next, the appearance similarity between the images is calculated according to the shape of the mask blocks. Finally, based on Gist similarity, semantic similarity and appearance similarity, the image similarity calculation model can be built as the basis for loop closure detection. Experiments are carried out on both public and self-filmed datasets. The results show that our proposed algorithm can detect the loop closure in the scene quickly and accurately when the illumination, viewpoint and object change.

show abstract

“…Loop closure detection has been extensively studied by scholars [ 8 ]. Bag of Visual Words (BoVW) is a traditional method to achieve loop closure detection.…”

Section: Introductionmentioning

confidence: 99%

Loop Closure Detection Based on Residual Network and Capsule Network for Mobile Robot

Zhang

Zheng

Tan

et al. 2022

Sensors

View full text Add to dashboard Cite

Loop closure detection based on a residual network (ResNet) and a capsule network (CapsNet) is proposed to address the problems of low accuracy and poor robustness for mobile robot simultaneous localization and mapping (SLAM) in complex scenes. First, the residual network of a feature coding strategy is introduced to extract the shallow geometric features and deep semantic features of images, reduce the amount of image noise information, accelerate the convergence speed of the model, and solve the problems of gradient disappearance and network degradation of deep neural networks. Then, the dynamic routing mechanism of the capsule network is optimized through the entropy peak density, and a vector is used to represent the spatial position relationship between features, which can improve the ability of image feature extraction and expression to optimize the overall performance of networks. Finally, the optimized residual network and capsule network are fused to retain the differences and correlations between features, and the global feature descriptors and feature vectors are combined to calculate the similarity of image features for loop closure detection. The experimental results show that the proposed method can achieve loop closure detection for mobile robots in complex scenes, such as view changes, illumination changes, and dynamic objects, and improve the accuracy and robustness of mobile robot SLAM.

show abstract

The Revisiting Problem in Simultaneous Localization and Mapping: A Survey on Visual Loop Closure Detection

Cited by 76 publications

References 354 publications

HGI-SLAM: Loop Closure With Human and Geometric Importance Features

HGI-SLAM: Loop Closure With Human and Geometric Importance Features

Loop Closure Detection for Mobile Robot based on Multidimensional Image Feature Fusion

Loop Closure Detection Based on Residual Network and Capsule Network for Mobile Robot

Contact Info

Product

Resources

About