Deep Hough Transform for Semantic Line Detection

@article{Han2020DeepHT,
  title={Deep Hough Transform for Semantic Line Detection},
  author={Qi Han and Kai Zhao and Jun Xu and Mingg-Ming Cheng},
  journal={ArXiv},
  year={2020},
  volume={abs/2003.04676}
}
In this paper, we put forward a simple yet effective method to detect meaningful straight lines, a.k.a. semantic lines, in given scenes. Prior methods take line detection as a special case of object detection, while neglect the inherent characteristics of lines, leading to less efficient and suboptimal results. We propose a one-shot end-to-end framework by incorporating the classical Hough transform into deeply learned representations. By parameterizing lines with slopes and biases, we perform… 
A Highly Efficient Model to Study the Semantics of Salient Object Detection.
TLDR
This work proposes an extremely light-weight holistic model tied to the SOD task that can be freed from classification backbones and trained from scratch, and then employs it to study the semantics of SOD models.
BBS-Net: RGB-D Salient Object Detection with a Bifurcated Backbone Strategy Network
TLDR
This paper proposes a bifurcated backbone strategy (BBS) to split the multi-level features of RGB-D salient object detection into teacher and student features, and utilizes a depth-enhanced module (DEM) to excavate informative parts of depth cues from the channel and spatial views.
ChainLineNet: Deep-Learning-Based Segmentation and Parameterization of Chain Lines in Historical Prints
TLDR
This work proposes an end-to-end trainable deep learning method for segmentation and parameterization of chain lines in transmitted light images of German prints from the 16th Century and shows superior qualitative and quantitative chain line detection results with high accuracy and reliability on the authors' historical dataset in comparison to competing methods.
ContrastMask: Contrastive Learning to Segment Every Thing
TLDR
This paper proposes a new method, named ContrastMask, which learns a mask segmentation model on both base and novel categories under a unified pixel-level contrastive learning framework, and demonstrates the superiority of this method, which outperforms previous state-of-the-arts methods.
Recognize Human Head Shot Top Down Based on Hough Transform
  • Y. He, Yiqun Huang, Zhibiao Li
  • Computer Science
    2021 the 7th International Conference on Communication and Information Processing (ICCIP)
  • 2021
TLDR
An algorithm is proposed to calculate the standard deviation of the angle of the detected edge points, and compare theStandard deviation value with the detectededge points, so as to judge whether the recognition of the circular object is correct.
Hough Transform-Based Angular Features for Learning-Free Handwritten Keyword Spotting
TLDR
The proposed KWS model outperforms state-of-the-art learning-free KWS methods considered here for comparison while evaluated on the present datasets and the features used in the present work perform better than the deep features extracted using InceptionV3, VGG19, and DenseNet121 models.
Object Detection from Radon Transformations using Machine Learning Techniques
Efficiently examining astronomical images for objects is becoming increasingly important as the space domain becomes more crowded. Our novel approach overcomes several challenges posed by using
Understanding 3D Object Articulation in Internet Videos
TLDR
This work proposes to investigate detecting and characterizing the 3D planar articulation of objects from ordinary RGB videos using a top-down detection system that finds planes that can be articulated and shows that this system can be trained on a combination of videos and 3D scan datasets.
EFFICIENT LINE DETECTION METHOD BASED ON 2D CONVOLUTION FILTER
  • P. Kowalski, P. Tojza
  • Engineering
    Informatyka, Automatyka, Pomiary w Gospodarce i Ochronie Środowiska
  • 2021
The article proposes an efficient line detection method using a 2D convolution filter. The proposed method was compared with the Hough transform, the most popular method of straight lines detection.
Harmonious Semantic Line Detection via Maximal Weight Clique Selection
TLDR
Experimental results demonstrate that the proposed algorithm can detect harmonious semantic lines effectively and efficiently and propose a novel metric, called HIoU, to assess the overall harmony of detected lines.
...
1
2
3
...

References

SHOWING 1-10 OF 94 REFERENCES
Deep Hough Transform for Semantic Line Detection
TLDR
This paper proposes a one-shot end-to-end framework by incorporating the classical Hough transform into deeply learned representations to detect meaningful straight lines, a.k.a. semantic lines, in given scenes.
Semantic Line Detection and Its Applications
TLDR
A semantic line detector using a convolutional neural network with multi-task learning, by regarding the line detection as a combination of classification and regression tasks, which shows that the proposed detector extracts semantic lines accurately and reliably.
Deep Hough Voting for 3D Object Detection in Point Clouds
TLDR
This work proposes VoteNet, an end-to-end 3D object detection network based on a synergy of deep point set networks and Hough voting that achieves state-of-the-art 3D detection on two large datasets of real 3D scans, ScanNet and SUN RGB-D with a simple design, compact model size and high efficiency.
Comparison of semantic segmentation approaches for horizon/sky line detection
TLDR
This paper provides a quantitative comparison of four recently proposed segmentation methods for autonomous horizon/sky line detection on an extensive data set and reports average accuracy and average absolute pixel error for each of the presented formulation.
PPGNet: Learning Point-Pair Graph for Line Segment Detection
TLDR
This paper proposes to describe junctions, line segments and relationships between them with a simple graph, which is more structured and informative than end-point representation used in existing line segment detection methods and introduces the PPGNet, a convolutional neural network that directly infers a graph from an image.
SpinNet: Spinning convolutional network for lane boundary detection
TLDR
A novel spinning convolution layer and a brand-new lane parameterization branch are designed and tested to detect lane boundaries from a global perspective, and it is shown that the proposed SpinNet outperforms state-of-the-art methods.
Learning to Parse Wireframes in Images of Man-Made Environments
TLDR
A learning-based approach to the task of automatically extracting a "wireframe" representation for images of cluttered man-made environments and two convolutional neural networks that are suitable for extracting junctions and lines with large spatial support are proposed.
Hyperpixel Flow: Semantic Correspondence With Multi-Layer Neural Features
TLDR
The proposed method, hyperpixel flow, sets a new state of the art on three standard benchmarks as well as a new dataset, SPair-71k, which contains a significantly larger number of image pairs than existing datasets, with more accurate and richer annotations for in-depth analysis.
Rethinking RGB-D Salient Object Detection: Models, Data Sets, and Large-Scale Benchmarks
TLDR
It is demonstrated that D3Net can be used to efficiently extract salient object masks from real scenes, enabling effective background-changing application with a speed of 65 frames/s on a single GPU.
...
1
2
3
4
5
...