Patch PlaNet: Landmark Recognition with Patch Classification Using Convolutional Neural Networks

Cunha, Kelvin B. da; Maggi, Lucas; Teichrieb, Verônica; Lima, João Paulo; Quintino, Jonysberg P.; Silva, Fábio Q. B. da; Santos, André L. M.; Pinho, Helder

doi:10.1109/sibgrapi.2018.00023

Cited by 4 publications

(3 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The use of DCNN architecture by [10] was carried out to improve accuracy in landmark classification. They patched the PlaNet model because the model has geolocation parameters that help in the prediction process.…”

Section: Related Workmentioning

confidence: 99%

Landmark Classification Service Using Convolutional Neural Network and Kubernetes

Aji¹

2020

IJATCSE

View full text Add to dashboard Cite

The use of Deep Learning for the image classification process has developed rapidly, one of which is in a method called Convolutional Neural Network (CNN). One use of the CNN method is to classify images. This study uses the CNN method to classify image datasets that have landmark categories. The results show that each model has an accuracy level with the highest value of 95% and the lowest value of 92%. The method for this research to produce a service that can be used by other services and or can be implemented in other resources so that the classification function can be used or developed. We show that our deployment method has good results seen with ResNet50 Model using 1200 concurrent users which response rates were smaller by 4,92% using autoscaling pods with one minimum pod and 6 maximum pods that had an error value of 26,58% compared with the best result from the other method.

show abstract

Section: Related Workmentioning

confidence: 99%

Landmark Classification Service Using Convolutional Neural Network and Kubernetes

Aji¹

2020

IJATCSE

View full text Add to dashboard Cite

show abstract

“…The spatial pyramid kernel-based bag-of-words histogram approach was used to extract image feature, and the artificial neural network was trained with extreme learning machine combine with sparse representation classifier for landmark image recognition. Cunha [30] has proposed the Patch PlaNet which considered landmark recognition as a classification problem and extended the PlaNet deep neural network model to perform the classification. Compared with original network, the performance of Patch PlaNet improves the accuracy of landmark recognition by 5-11 percentages.…”

Section: Introductionmentioning

confidence: 99%

A Structure Landmark-Based Radio Signal Mapping Approach for Sustainable Indoor Localization

Liu

Zhang

et al. 2021

Sustainability

View full text Add to dashboard Cite

Low cost and high reproducible is a key issue for sustainable location-based services. Currently, Wi-Fi fingerprinting based indoor positioning technology has been widely used in various applications due to the advantage of existing wireless network infrastructures and high positioning accuracy. However, the collection and construction of signal radio map (a basis for Wi-Fi fingerprinting-based localization) is a labor-intensive and time-cost work, which limit their practical and sustainable use. In this study, an indoor signal mapping approach is proposed, which extracts fingerprints from unknown signal mapping routes to construct the radio map. This approach employs special indoor spatial structures (termed as structure landmarks) to estimate the location of fingerprints extracted from mapping routes. A learning-based classification model is designed to recognize the structure landmarks along a mapping route based on visual and inertial data. A landmark-based map matching algorithm is also developed to attach the recognized landmarks to a map and to recover the location of the mapping route without knowing its initial location. Experiment results showed that the accuracy of landmark recognition model is higher than 90%. The average matching accuracy and location error of signal mapping routes is 96% and 1.2 m, respectively. By using the constructed signal radio map, the indoor localization error of two algorithms can reach an accuracy of 1.6 m.

show abstract

“…In contrast to studies that aim at inferring geo-location from images [9,10], representative image selection pays more attention to exploring users' visual preferences and visual similarity to images given a certain location. Therefore, it usually begins with clustering: Cluster the photos according to their coordinates, and then obtain semantic annotations by reverse geocoding [11,12] or selecting distinct tags with TF-IDF [6,13] and its variations [14].…”

Section: Introductionmentioning

confidence: 99%

Extracting Representative Images of Tourist Attractions from Flickr by Combining an Improved Cluster Method and Multiple Deep Learning Models

Han

Ren

et al. 2020

IJGI

View full text Add to dashboard Cite

Extracting representative images of tourist attractions from geotagged photos is beneficial to many fields in tourist management, such as applications in touristic information systems. This task usually begins with clustering to extract tourist attractions from raw coordinates in geotagged photos. However, most existing cluster methods are limited in the accuracy and granularity of the places of interest, as well as in detecting distinct tags, due to its primary consideration of spatial relationships. After clustering, the challenge still exists for the task of extracting representative images within the geotagged base image data, because of the existence of noisy photos occupied by a large area proportion of humans and unrelated objects. In this paper, we propose a framework containing an improved cluster method and multiple neural network models to extract representative images of tourist attractions. We first propose a novel time- and user-constrained density-joinable cluster method (TU-DJ-Cluster), specific to photos with similar geotags to detect place-relevant tags. Then we merge and extend the clusters according to the similarity between pairs of tag embeddings, as trained from Word2Vec. Based on the clustering result, we filter noise images with Multilayer Perceptron and a single-shot multibox detector model, and further select representative images with the deep ranking model. We select Beijing as the study area. The quantitative and qualitative analysis, as well as the questionnaire results obtained from real-life tourists, demonstrate the effectiveness of this framework.

show abstract

Patch PlaNet: Landmark Recognition with Patch Classification Using Convolutional Neural Networks

Cited by 4 publications

References 19 publications

Landmark Classification Service Using Convolutional Neural Network and Kubernetes

Landmark Classification Service Using Convolutional Neural Network and Kubernetes

A Structure Landmark-Based Radio Signal Mapping Approach for Sustainable Indoor Localization

Extracting Representative Images of Tourist Attractions from Flickr by Combining an Improved Cluster Method and Multiple Deep Learning Models

Contact Info

Product

Resources

About