A Spatial Layout and Scale Invariant Feature Representation for Indoor Scene Classification
MetadataShow full item record
Unlike standard object classification, where the image to be classified contains one or multiple instances of the same object, indoor scene classification is quite different since the image consists of multiple distinct objects. Furthermore, these objects can be of varying sizes and are present across numerous spatial locations in different layouts. For automatic indoor scene categorization, large-scale spatial layout deformations and scale variations are therefore two major challenges and the design of rich feature descriptors which are robust to these challenges is still an open problem. This paper introduces a new learnable feature descriptor called 'spatial layout and scale invariant convolutional activations' to deal with these challenges. For this purpose, a new convolutional neural network architecture is designed which incorporates a novel 'spatially unstructured' layer to introduce robustness against spatial layout deformations. To achieve scale invariance, we present a pyramidal image representation. For feasible training of the proposed network for images of indoor scenes, this paper proposes a methodology, which efficiently adapts a trained network model (on a large-scale data) for our task with only a limited amount of available training data. The efficacy of the proposed approach is demonstrated through extensive experiments on a number of data sets, including MIT-67, Scene-15, Sports-8, Graz-02, and NYU data sets.
Showing items related by title, author, creator and subject.
Liu, T.; Tai, C.; Zhu, Maggie; Bagchi, J.; Allebach, J. (2017)© 2017, Society for Imaging Science and Technology. We propose a novel tool for re-rendering objects in indoor scene images with new textures. It aims to address the problem of too much manual work of positioning and ...
Fractals and fuzzy sets for modelling the heterogenity and spatial complexity of urban landscapes using multiscale remote sensing dataIslam, Zahurul (2004)This research presents models for the analysis of textural and contextual information content of multiscale remote sensing to select an appropriate scale for the correct interpretation and mapping of heterogeneous urban ...
Leoputra, Wilson Suryajaya (2009)Foreground object detection is a fundamental task in computer vision with many applications in areas such as object tracking, event identification, and behavior analysis. Most conventional foreground object detection ...