English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Street view images classification aiming at urban land use analysis isdifficult because the class labels (e.g., commercial area), are concepts withhigher abstract level compared to the ones of general visual tasks (e.g.,persons and cars). Therefore, classification models using only visual featuresoften fail to achieve satisfactory performance. In this paper, a novel approachbased on a "Detector-Encoder-Classifier" framework is proposed. Instead ofusing visual features of the whole image directly as common image-level modelsbased on convolutional neural networks (CNNs) do, the proposed frameworkfirstly obtains the bounding boxes of buildings in street view images from adetector. Their contextual information such as the co-occurrence patterns ofbuilding classes and their layout are then encoded into metadata by theproposed algorithm "CODING" (Context encOding of Detected buildINGs). Finally,these bounding box metadata are classified by a recurrent neural network (RNN).In addition, we made a dual-labeled dataset named "BEAUTY" (Building dEtectionAnd Urban funcTional-zone portraYing) of 19,070 street view images and 38,857buildings based on the existing BIC GSV [1]. The dataset can be used not onlyfor street view image classification, but also for multi-class buildingdetection. Experiments on "BEAUTY" show that the proposed approach achieves a12.65% performance improvement on macro-precision and 12% on macro-recall overimage-level CNN based models. Our code and dataset are available athttps://github.com/kyle-one/Context-Encoding-of-Detected-Buildings/

Bounding Boxes Are All We Need: Street View Image Classification via Context Encoding of Detected Buildings