Proceedings ArticleDOI
Plan2Text: A framework for describing building floor plan images from first person perspective
Reads0
Chats0
TLDR
It is demonstrated that the proposed end-to-end framework for first person vision based textual description synthesis of building floor plans gives state of the art performance on challenging, real-world floor plan images.Abstract:
We focus on synthesis of textual description from a given building floor plan image based on the first-person vision perspective. Tasks like symbol spotting, wall and decor segmentation, semantic and perceptual segmentation has been done in the past on floor plans. Here, for the first time, we propose an end-to-end framework for first person vision based textual description synthesis of building floor plans. We demonstrate (qualitative and quantitatively) that the proposed framework gives state of the art performance on challenging, real-world floor plan images. Potential application of this work could be understanding floor plans, stability analysis of buildings, and retrieval.read more
Citations
More filters
Posted Content
SUGAMAN: Describing Floor Plans for Visually Impaired by Annotation Learning and Proximity based Grammar
TL;DR: SUGAMAN is the first framework for describing a floor plan and giving direction for obstacle-free movement within a building and can be applied to areas like understanding floor plans of historical monuments, stability analysis of buildings, and retrieval.
Journal ArticleDOI
Towards Robust Object Detection in Floor Plan Images: A Data Augmentation Approach
Shashank Mishra,Khurram Azeem Hashmi,Alain Pagani,Marcus Liwicki,Didier Stricker,Muhammad Zeshan Afzal +5 more
TL;DR: Wang et al. as discussed by the authors investigated the performance of the recently introduced Cascade Mask R-CNN network to solve object detection in floor plan images and experimentally established that deformable convolution works better than conventional convolutions in the proposed framework.
Book ChapterDOI
Semantic Segmentation and Topological Mapping of Floor Plans
TL;DR: In this article, a topological mapping method from the floor plan model based on deep learning semantic segmentation is proposed for assistive blind navigation purposes in unknown indoor environments, where disturbances such as image rotation, color transformation and Gaussian noises are taken into consideration in the training to enhance the robustness.
References
More filters
Journal ArticleDOI
Multiresolution gray-scale and rotation invariant texture classification with local binary patterns
TL;DR: A generalized gray-scale and rotation invariant operator presentation that allows for detecting the "uniform" patterns for any quantization of the angular space and for any spatial resolution and presents a method for combining multiple operators for multiresolution analysis.
Proceedings Article
ROUGE: A Package for Automatic Evaluation of Summaries
TL;DR: Four different RouGE measures are introduced: ROUGE-N, ROUge-L, R OUGE-W, and ROUAGE-S included in the Rouge summarization evaluation package and their evaluations.
Journal ArticleDOI
SLIC Superpixels Compared to State-of-the-Art Superpixel Methods
TL;DR: A new superpixel algorithm is introduced, simple linear iterative clustering (SLIC), which adapts a k-means clustering approach to efficiently generate superpixels and is faster and more memory efficient, improves segmentation performance, and is straightforward to extend to supervoxel generation.
Journal ArticleDOI
A Scaled Difference Chi-square Test Statistic for Moment Structure Analysis
Albert Satorra,Peter M. Bentler +1 more
TL;DR: In this paper, Satorra and Bentler's scaling corrections are used to improve the chi-square approximation of goodness-of-fit test statistics in small samples, large models, and nonnormal data.
Journal ArticleDOI
Faster and Better: A Machine Learning Approach to Corner Detection
TL;DR: A new heuristic for feature detection is presented and, using machine learning, a feature detector is derived from this which can fully process live PAL video using less than 5 percent of the available processing time.