“Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks”の学習報告

In the real world, a realistic setting for computer vision or multimedia recognition problems is that we have some classes containing lots of training data and many classes contain a small amount of training data. Therefore, how to use frequent classes to help learning rare classes for which it is harder to collect the training data is an open question. Learning with Shared Information is an emerging topic in machine learning, computer vision and multimedia analysis. There are different level of components that can be shared during concept modeling and machine learning stages, such as sharing generic object parts, sharing attributes, sharing transformations, sharing regularization parameters and sharing training examples, etc. Regarding the specific methods, multi-task learning, transfer learning and deep learning can be seen as using different strategies to share information. These learning with shared information methods are very effective in solving real-world large-scale problems. This special issue aims at gathering the recent advances in learning with shared information methods and their applications in computer vision and multimedia analysis. Both state-of-the-art works, as well as literature reviews, are welcome for submission. Papers addressing interesting real-world computer vision and multimedia applications are especially encouraged. Topics of interest include, but are not limited to:  • Multi-task learning or transfer learning for large-scale computer vision and multimedia analysis • Deep learning for large-scale computer vision and multimedia analysis • Multi-modal approach for large-scale computer vision and multimedia analysis • Different sharing strategies, e.g., sharing generic object parts, sharing attributes, sharing transformations, sharing regularization parameters and sharing training examples, • Real-world computer vision and multimedia applications based on learning with shared information, e.g., event detection, object recognition, object detection, action recognition, human head pose estimation, object tracking, location-based services, semantic indexing. • New datasets and metrics to evaluate the benefit of the proposed sharing ability for the specific computer vision or multimedia problem. • Survey papers regarding the topic of learning with shared information.  Authors who are unsure whether their planned submission is in scope may contact the guest editors prior to the submission deadline with an abstract, in order to receive feedback.

IEEE transactions on pattern analysis and machine intelligence

我的台灣, 看見心靈的故鄉 =2009林磐聳藝術與設計展

Computer vision-based techniques were developed to overcome the limitations of visual inspection by trained human resources and to detect structural damage in images remotely, but most methods detect only specific types of damage, such as concrete or steel cracks. To provide quasi real-time simultaneous detection of multiple types of damages, a Faster Region-based Convolutional Neural Network (Faster R-CNN)-based structural visual inspection method is proposed. To realize this, a database including 2,366 images (with 500 × 375 pixels) labeled for five types of damages—concrete crack, steel corrosion with two levels (medium and high), bolt corrosion, and steel delamination—is developed. Then, the architecture of the Faster R-CNN is modified, trained, validated, and tested using this database. Results show 90.6%, 83.4%, 82.1%, 98.1%, and 84.7% average precision (AP) ratings for the five damage types, respectively, with a mean AP of 87.8%. The robustness of the trained Faster R-CNN is evaluated and demonstrated using 11 new 6,000 × 4,000-pixel images taken of different structures. Its performance is also compared to that of the traditional CNN-based method. Considering that the proposed method provides a remarkably fast test speed (0.03 seconds per image with 500 × 375 resolution), a framework for quasi real-time damage detection on video using the trained networks is developed.

Autonomous Structural Visual Inspection Using Region-Based Deep Learning for Detecting Multiple Damage Types

Cracks are a growing threat to road conditions and have drawn much attention to the construction of intelligent transportation systems. However, as the key part of an intelligent transportation system, automatic road crack detection has been challenged because of the intense inhomogeneity along the cracks, the topology complexity of cracks, the inference of noises with similar texture to the cracks, and so on. In this paper, we propose CrackForest, a novel road crack detection framework based on random structured forests, to address these issues. Our contributions are shown as follows: 1) apply the integral channel features to redefine the tokens that constitute a crack and get better representation of the cracks with intensity inhomogeneity; 2) introduce random structured forests to generate a high-performance crack detector, which can identify arbitrarily complex cracks; and 3) propose a new crack descriptor to characterize cracks and discern them from noises effectively. In addition, our method is faster and easier to parallel. Experimental results prove the state-of-the-art detection precision of CrackForest compared with competing methods.

Automatic Road Crack Detection Using Random Structured Forests

This paper proposes a new algorithm for automatic crack detection from 2D pavement images. It strongly relies on the localization of minimal paths within each image, a path being a series of neighboring pixels and its score being the sum of their intensities. The originality of the approach stems from the proposed way to select a set of minimal paths and the two postprocessing steps introduced to improve the quality of the detection. Such an approach is a natural way to take account of both the photometric and geometric characteristics of pavement images. An intensive validation is performed on both synthetic and real images (from five different acquisition systems), with comparisons to five existing methods. The proposed algorithm provides very robust and precise results in a wide range of situations, in a fully unsupervised manner, which is beyond the current state of the art.

/pdf/automatic-crack-detection-on-two-dimensional-pavement-images-35nzns5lha.pdf

Automatic Crack Detection on Two-Dimensional Pavement Images: An Algorithm Based on Minimal Path Selection

In the field of noninvasive sensing techniques for civil infrastructures monitoring, this paper addresses the problem of crack detection, in the surface of the French national roads, by automatic analysis of optical images. The first contribution is a state of the art of the image-processing tools applied to civil engineering. The second contribution is about fine-defect detection in pavement surface. The approach is based on a multi-scale extraction and a Markovian segmentation. Third, an evaluation and comparison protocol which has been designed for evaluating this difficult task—the road pavement crack detection—is introduced. Finally, the proposed method is validated, analysed, and compared to a detection approach based on morphological tools.

/pdf/automatic-road-pavement-assessment-with-image-processing-3iti93m1zz.pdf

Automatic Road Pavement Assessment with Image Processing: Review and Comparison

Road surface conditions are continuously degrading due to meteorological conditions, ground movements and traffic that leads to the formation of defects, such as grabbing, holes, and cracks. This article presents a method to automatically distinguish images of road surfaces with defects from road surfaces without defects. This method, based on supervised learning, is generic and may be applied to all type of defects present in the images. They typically present strong textural information with patterns that show fluctuations at small scales and some uniformity at larger scales. The textural information is described by applying a large set of linear and nonlinear filters. To select the most pertinent ones for the current application, a supervised learning based on AdaBoost is performed. The whole process is tested both on a textural recognition task based on the VisTex image database and on road images collected by a dedicated road imaging system. A comparison with a recent crack detection algorithm from Oliveira and Correia demonstrates the proposed method's efficiency.

Automatic Road Defect Detection by Textural Pattern Recognition Based on AdaBoost

http://perso.lcpc.fr/sylvie.chambon/PUBLICATIONS/ChambonPR2011_Draft.pdf

Similarity measures for image matching despite occlusions in stereo vision

The Thin-Plate Spline warp has been shown to be a very effective parameterized model of the optic flow field between images of various types of deformable surfaces, such as a paper sheet being bent. Recent work has also used such warps for images of a smooth and rigid surface. Standard Thin-Plate Spline warps are however not rigid, in the sense that they do not comply with the epipolar geometry. They are also intrinsically affine, in the sense of the affine camera model, since they are not able to simply model the effect of perspective projection.

We propose three types of warps based on the Thin-Plate Spline. The first one is a rigid flexible warp. It describes the optic flow field induced by a smooth and rigid surface, and satisfies the affine epipolar geometry constraint. The second and third proposed warps extend the standard Thin-Plate Spline warp and the proposed rigid flexible warp to the perspective camera model. The properties of these warps are studied in details and a hierarchy is defined. Experimental results on simulated and real data are reported.

Sylvie Chambon

Papers

Automatic Crack Detection on Two-Dimensional Pavement Images: An Algorithm Based on Minimal Path Selection

Automatic Road Pavement Assessment with Image Processing: Review and Comparison

Automatic Road Defect Detection by Textural Pattern Recognition Based on AdaBoost

Similarity measures for image matching despite occlusions in stereo vision

Generalized Thin-Plate Spline Warps