PPGNet: Learning Point-Pair Graph for Line Segment Detection

Zhang, Ziheng; Li, Zhengxin; Bi, Ning; Zheng, Jianming; Wang, Jinlei; Huang, Kun; Luo, Weixin; Xu, Yanyu; Gao, Shenghua

doi:10.1109/cvpr.2019.00727

Cited by 84 publications

(70 citation statements)

References 60 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“… There are some challenges in PATTERN DETECTION, such as pose variation, varying illumination, scene occlusion, and sensor noise. The research literature about the repeated pattern or periodic structure detection provides a stable baseline in both 2D images [221,222] and 3d cloud-points [223][224][225][226].…”

Section: ) Object Detection In Daily Lifementioning

confidence: 99%

Exploring Deep Learning-Based Architecture, Strategies, Applications and Current Trends in Generic Object Detection: A Comprehensive Review

Aziz

Salam²,

Sheikh³

et al. 2020

IEEE Access

117

View full text Add to dashboard Cite

Object detection is a fundamental but challenging issue in the field of generic image analysis; it plays an important role in a wide range of applications and has been receiving special attention in recent years. Although there are enomerous methods exist, an in-depth review of the literature concerning generic detection remains. This paper provides a comprehensive survey of recent advances in visual object detection with deep learning. Covering about 300 publications that we survey 1) region proposal-based object detection methods such as R

show abstract

Section: ) Object Detection In Daily Lifementioning

confidence: 99%

Exploring Deep Learning-Based Architecture, Strategies, Applications and Current Trends in Generic Object Detection: A Comprehensive Review

Aziz

Salam²,

Sheikh³

et al. 2020

IEEE Access

117

View full text Add to dashboard Cite

show abstract

“…Therefore, we varied these factors while keeping the other parameters constant, see Table 1. The examples in (Zhang et al, 2019) consist of graphs with up to 75 times more junctions and edges than are present in our data. Moreover, the goal of this study was to detect every edge present in the image.…”

Section: Experiments and Discussionmentioning

confidence: 81%

“…In this chapter, we give a brief description of the PPGNet. For details of the PPGNet see (Zhang et al, 2019). The PPGNet is a CNN that takes an image as input and outputs detected line segments (edges) on that image as a graph.…”

Section: Ppgnetmentioning

confidence: 99%

“…Since recently, several deep neural network architectures have been available for edge graph detection on images. The given paper is a feasibility study in which the deep neural network Point-Pair Graph Network (PPGNet) (Zhang et al, 2019) is trained on hand-labeled orthoimages. The goal is to show that the quality of the recognized graph is sufficient to be used in a roof reconstruction pipeline.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Building Roof Vectorization With Ppgnet

Hensel

Goebbels

Kada³

2021

Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

Abstract. A challenge in data-based 3D building reconstruction is to find the exact edges of roof facet polygons. Although these edges are visible in orthoimages, convolution-based edge detectors also find many other edges due to shadows and textures. In this feasibility study, we apply machine learning to solve this problem. Recently, neural networks have been introduced that not only detect edges in images, but also assemble the edges into a graph. When applied to roof reconstruction, the vertices of the dual graph represent the roof facets. In this study, we apply the Point-Pair Graph Network (PPGNet) to orthoimages of buildings and evaluate the quality of the detected edge graphs. The initial results are promising, and adjusting the training parameters further improved the results. However, in some cases, additional work, such as post-processing, is required to reliably find all vertices.

show abstract

“…Unlike the Wireframe Parser, they only focus on detection of line segments, ignoring the relationship between the segments. Zhang et al [32] formuate the wireframe parsing task as a graph optimization problem.…”

Section: B Pixel-level Edge Detection and Line Segment Detectionmentioning

confidence: 99%

Wireframe Parsing With Guidance of Distance Map

Huang

Gao

2019

IEEE Access

Self Cite

View full text Add to dashboard Cite

We propose an end-to-end method for simultaneously detecting local junctions and global wireframe in man-made environment. Our pipeline consists of an anchor-free junction detection module, a distance map learning module, and a line segment proposing and verification module. A set of line segments are proposed from the predicted junctions with guidance of the learned distance map, and further verified by the proposal verification module. Experimental results show that our method outperforms the previous state-of-the-art wireframe parser by a descent margin. In terms of line segments detection, our method shows competitive performance on standard benchmarks. The proposed networks are end-to-end trainable and efficient. a INDEX TERMS Artificial neural networks, computer vision, feature extraction, image edge detection.

show abstract

PPGNet: Learning Point-Pair Graph for Line Segment Detection

Cited by 84 publications

References 60 publications

Exploring Deep Learning-Based Architecture, Strategies, Applications and Current Trends in Generic Object Detection: A Comprehensive Review

Exploring Deep Learning-Based Architecture, Strategies, Applications and Current Trends in Generic Object Detection: A Comprehensive Review

Building Roof Vectorization With Ppgnet

Wireframe Parsing With Guidance of Distance Map

Contact Info

Product

Resources

About