Walk the Lines: Object Contour Tracing CNN for Contour Completion of Ships

• URL: http://arxiv.org/abs/2004.06587v1
• Date: Tue, 14 Apr 2020 15:19:04 GMT
• Title: Walk the Lines: Object Contour Tracing CNN for Contour Completion of Ships
• Authors: Andr\'e Peter Kelm and Udo Z\"olzer
• Abstract summary: We develop a new contour tracing algorithm to enhance the results of the latest object contour detectors. The goal is to achieve a perfectly closed, 1 pixel wide and detailed object contour. We present the Walk the Lines (WtL) algorithm, a standard regression CNN trained to follow object contours.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We develop a new contour tracing algorithm to enhance the results of the latest object contour detectors. The goal is to achieve a perfectly closed, 1 pixel wide and detailed object contour, since this type of contour could be analyzed using methods such as Fourier descriptors. Convolutional Neural Networks (CNNs) are rarely used for contour tracing. However, we find CNNs are tailor-made for this task and that's why we present the Walk the Lines (WtL) algorithm, a standard regression CNN trained to follow object contours. To make the first step, we train the CNN only on ship contours, but the principle is also applicable to other objects. Input data are the image and the associated object contour prediction of the recently published RefineContourNet. The WtL gets a center pixel, which defines an input section and an angle for rotating this section. Ideally, the center pixel moves on the contour, while the angle describes upcoming directional contour changes. The WtL predicts its steps pixelwise in a selfrouting way. To obtain a complete object contour the WtL runs in parallel at different image locations and the traces of its individual paths are summed. In contrast to the comparable Non-Maximum Suppression method, our approach produces connected contours with finer details. Finally, the object contour is binarized under the condition of being closed. In case all procedures work as desired, excellent ship segmentations with high IoUs are produced, showing details such as antennas and ship superstructures that are easily omitted by other segmentation methods.

Related papers

• 3D Neural Edge Reconstruction [61.10201396044153]
  We introduce EMAP, a new method for learning 3D edge representations with a focus on both lines and curves. Our method implicitly encodes 3D edge distance and direction in Unsigned Distance Functions (UDF) from multi-view edge maps. On top of this neural representation, we propose an edge extraction algorithm that robustly abstracts 3D edges from the inferred edge points and their directions.
  arXiv  Detail & Related papers  (2024-05-29T17:23:51Z)
• Polygonal Point Set Tracking [50.445151155209246]
  We propose a novel learning-based polygonal point set tracking method. Our goal is to track corresponding points on the target contour. We present visual-effects applications of our method on part distortion and text mapping.
  arXiv  Detail & Related papers  (2021-05-30T17:12:36Z)
• Cuboids Revisited: Learning Robust 3D Shape Fitting to Single RGB Images [44.223070672713455]
  In particular, man-made environments commonly consist of volumetric primitives such as cuboids or cylinders. Previous approaches directly estimate shape parameters from a 2D or 3D input, and are only able to reproduce simple objects. We propose a robust estimator for primitive fitting, which can meaningfully abstract real-world environments using cuboids.
  arXiv  Detail & Related papers  (2021-05-05T13:36:00Z)
• Learning Spatio-Temporal Transformer for Visual Tracking [108.11680070733598]
  We present a new tracking architecture with an encoder-decoder transformer as the key component. The whole method is end-to-end, does not need any postprocessing steps such as cosine window and bounding box smoothing. The proposed tracker achieves state-of-the-art performance on five challenging short-term and long-term benchmarks, while running real-time speed, being 6x faster than Siam R-CNN.
  arXiv  Detail & Related papers  (2021-03-31T15:19:19Z)
• Learning Geometry-Disentangled Representation for Complementary Understanding of 3D Object Point Cloud [50.56461318879761]
  We propose Geometry-Disentangled Attention Network (GDANet) for 3D image processing. GDANet disentangles point clouds into contour and flat part of 3D objects, respectively denoted by sharp and gentle variation components. Experiments on 3D object classification and segmentation benchmarks demonstrate that GDANet achieves the state-of-the-arts with fewer parameters.
  arXiv  Detail & Related papers  (2020-12-20T13:35:00Z)
• End-to-end Deep Object Tracking with Circular Loss Function for Rotated Bounding Box [68.8204255655161]
  We introduce a novel end-to-end deep learning method based on the Transformer Multi-Head Attention architecture. We also present a new type of loss function, which takes into account the bounding box overlap and orientation.
  arXiv  Detail & Related papers  (2020-12-17T17:29:29Z)
• ContourCNN: convolutional neural network for contour data classification [0.0]
  This paper proposes a novel Convolutional Neural Network model for contour data analysis (ContourCNN) and shape classification. We employ circular convolution layers to handle the cyclical property of the contour representation. To address information sparsity, we introduce priority pooling layers that select features based on their magnitudes.
  arXiv  Detail & Related papers  (2020-09-20T11:56:47Z)
• ContourRend: A Segmentation Method for Improving Contours by Rendering [10.13129256609938]
  Mask-based segmentation can not handle contour features well on a coarse prediction grid. We propose Contourend which adopts convolution contour to refine segmentation contours. Our method reaches 72.41% mean intersection over union (IoU) and surpasses baseline Polygon-GCN by 1.22%.
  arXiv  Detail & Related papers  (2020-07-15T02:16:00Z)
• Quantization in Relative Gradient Angle Domain For Building Polygon Estimation [88.80146152060888]
  CNN approaches often generate imprecise building morphologies including noisy edges and round corners. We propose a module that uses prior knowledge of building corners to create angular and concise building polygons from CNN segmentation outputs. Experimental results demonstrate that our method refines CNN output from a rounded approximation to a more clear-cut angular shape of the building footprint.
  arXiv  Detail & Related papers  (2020-07-10T21:33:06Z)
• Convex Shape Prior for Deep Neural Convolution Network based Eye Fundus Images Segmentation [6.163107242394357]
  We propose a technique which can be easily integrated into the commonly used DCNNs for image segmentation. Our method is based on the dual representation of the sigmoid activation function in DCNNs. We show that our method is efficient and outperforms the classical DCNN segmentation methods.
  arXiv  Detail & Related papers  (2020-05-15T11:36:04Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.