RISE: A Novel Indoor Visual Place Recogniser

Sánchez-Belenguer, Carlos; Wolfart, Erik; Vitor, Sequeira

doi:10.1109/icra40945.2020.9196871

Cited by 9 publications

(10 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We compare AR-Loop with PLCD [16], which is the most stable learning based algorithm at present [24], [25]. In case of the same datasets, precision-recall curves of two models are shown in Fig.…”

Section: B Experimental Results and Evaluation 1) Algorithmic Results And Evaluationmentioning

confidence: 99%

Adaptive Real-Time Loop Closure Detection Based on Image Feature Concatenation

Liu

Xiao

Lin

et al. 2021

2021 IEEE International Symposium on Circuits and Systems (ISCAS)

View full text Add to dashboard Cite

Simultaneous Localization and Mapping (SLAM) is used to solve the problem of autonomous localization and navigation of mobile robots in unknown environments. Loop closure detection is a key part of SLAM, which largely determines accuracy and stability of SLAM. In recent years, some experiments have proved that the loop closure detection system based on neural network is superior to the traditional loop closure detection in both accuracy and real-time performance. In this paper, we propose an adaptive real-time loop closure detection (AR-Loop) method based on monocular vision. A pre-trained convolutional neural network (CNN) is used to extract image features. Then features of different layers are concatenated as image descriptors. In addition, the adaptive candidate matching range algorithm and image-tosequence calibration algorithm are proposed to improve the performance of the algorithm. Extensive experiments have been conducted on several open datasets to validate the performance of AR-Loop. It has been demonstrated that the recall rate is increased by over 18% compared with other state-of-the-art algorithms when the precision is 100%.

show abstract

Section: B Experimental Results and Evaluation 1) Algorithmic Results And Evaluationmentioning

confidence: 99%

Adaptive Real-Time Loop Closure Detection Based on Image Feature Concatenation

Liu

Xiao

Lin

et al. 2021

2021 IEEE International Symposium on Circuits and Systems (ISCAS)

View full text Add to dashboard Cite

show abstract

“…Sánchez-Belenguer et al [27] developed RISE, an image retrieval based indoor place recogniser, which we are building upon. They create a 3D map of the environment with a laser and calibrated spherical camera mounted on a backpack.…”

Section: Image Retrieval For Place Recognition and Localizationmentioning

confidence: 99%

“…we want to have d(q, r) = 1.0 in the case of no overlap between q and r, d(q, r) = 0.0 in the case of full overlap. For this purpose, we adopt the overlap loss of Sánchez-Belenguer et al [27]:…”

Section: Objective Functionmentioning

confidence: 99%

“…But, in contrast to [27], we employ 2D image overlaps, which are available as the ground truth poses and the sizes of the areas covered by the images are known for training images.…”

Section: Objective Functionmentioning

confidence: 99%

“…image descriptors, for image retrieval. It consists of a Convolutional Neural Network (CNN) that is trained in Siamese fashion, using a loss function that is adopted from Sánchez-Belenguer et al [27]. Subsequently, we employ a k-d tree to find the reference images with most similar embeddings to that of the query image.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Deep Metric Learning for Ground Images

Radhakrishnan,

Schmid,

Scholz

et al. 2021

Preprint

View full text Add to dashboard Cite

Ground texture based localization methods are potential prospects for low-cost, highaccuracy self-localization solutions for robots. These methods estimate the pose of a given query image, i.e. the current observation of the ground from a downward-facing camera, in respect to a set of reference images whose poses are known in the application area. In this work, we deal with the initial localization task, in which we have no prior knowledge about the current robot positioning. In this situation, the localization method would have to consider all available reference images. However, in order to reduce computational effort and the risk of receiving a wrong result, we would like to consider only those reference images that are actually overlapping with the query image. For this purpose, we propose a deep metric learning approach that retrieves the most similar reference images to the query image. In contrast to existing approaches to image retrieval for ground images, our approach achieves significantly better recall performance and improves the localization performance of a state-of-the-art ground texture based localization method.

show abstract