Current IssuePrevious Issue  

Volume 6 No. 4
05 December 2020

Hiba Ramadan,Chaymae Lachqar,Hamid Tairi

2020, 6(4): 355-384.   doi:10.1007/s41095-020-0177-5
Abstract ( 38 HTML ( 0   PDF(719KB) ( 23 )   Save

Image segmentation is one of the most basic tasks in computer vision and remains an initial step of many applications. In this paper, we focus on interactive image segmentation (IIS), often referred to as foreground-background separation or object extraction, guided by user interaction. We provide an overview of the IIS literature by covering more than 150 publications, especially recent works that have not been surveyed before. Moreover, we try to give a comprehensive classification of them ...

Or Patashnik,Min Lu,Amit H. Bermano,Daniel Cohen-Or

2020, 6(4): 385-400.   doi:10.1007/s41095-020-0197-1
Abstract ( 13 HTML ( 1   PDF(903KB) ( 10 )   Save

Visualizing high-dimensional data on a 2Dcanvas is generally challenging. It becomes significantlymore difficult when multiple time-steps are to be presented, as the visual clutter quickly increases. Moreover, the challenge to perceive the significant temporal evolution is even greater. In this paper, we present a method to plot temporal high-dimensional data in a static scatterplot; it uses the established PCA technique to project data from multiple time-steps. The key idea is to extend each...

Xuanpeng Li,Lifeng Zhu,Qifan Xue,Dong Wang,Yongjie Jessica Zhang

2020, 6(4): 401-415.   doi:10.1007/s41095-020-0190-8
Abstract ( 21 HTML ( 0   PDF(1079KB) ( 9 )   Save

Prediction of the likely evolution of trafficscenes is a challenging task because of high uncertaintiesfrom sensing technology and the dynamic environment. It leads to failure of motion planning for intelligent agents like autonomous vehicles. In this paper, we propose a fluid-inspired model to estimate collision risk in road scenes. Multi-object states are detected and tracked, and then a stable fluid model is adopted to construct the risk field. Objects’ state spaces are used as the ...

Fan Zhang,Jinjiang Li,Peiqiang Liu,Hui Fan

2020, 6(4): 417-430.   doi:10.1007/s41095-020-0186-4
Abstract ( 15 HTML ( 0   PDF(657KB) ( 11 )   Save

A new method is presented to determine parameter values (knot) for data points for curve and surface generation. With four adjacent data points, a quadratic polynomial curve can be determined uniquely if the four points form a convex polygon. When the four data points do not form a convex polygon, a cubic polynomial curve with one degree of freedom is used to interpolate the four points, so that the interpolant has better shape, approximating the polygon formed by the four data points. The de...

Xiaolong Yang,Xiaohong Jia

2020, 6(4): 431-443.   doi:10.1007/s41095-020-0192-6
Abstract ( 16 HTML ( 0   PDF(1009KB) ( 11 )   Save

We present a simple yet efficient algorithmfor recognizing simple quadric primitives (plane, sphere, cylinder, cone) from triangular meshes. Our approach is an improved version of a previous hierarchical clustering algorithm, which performs pairwise clustering of trianglepatches from bottom to top. The key contributions of our approach include a strategy for priority and fidelity consideration of the detected primitives, and a scheme for boundary smoothness between adjacent clusters. Experime...

Naoto Ishikawa,Yoshinori Dobashi

2020, 6(4): 445-454.   doi:10.1007/s41095-020-0198-0
Abstract ( 6 HTML ( 0   PDF(698KB) ( 8 )   Save

We propose an efficient, specific method for estimating camera parameters from a single starry night image. Such an image consists of a collection of disks representing stars, so traditional estimation methods for common pictures do not work. Our method uses a database, a star catalog, that stores the positions of stars on the celestial sphere. Our method computes magnitudes (i.e., brightnesses) of stars in the input image and uses them to find the corresponding stars in the star catalog. Cam...

Dejun Zhang,Linchao He,Mengting Luo,Zhanya Xu,Fazhi He

2020, 6(4): 455-466.   doi:10.1007/s41095-020-0185-5
Abstract ( 13 HTML ( 0   PDF(1107KB) ( 5 )   Save

Deep convolutional networks have obtained remarkable achievements on various visual tasks due to their strong ability to learn a variety of features. A well-trained deep convolutional network can be compressed to 20%-40% of its original size by removing filters that make little contribution, as many overlapping features are generated by redundant filters. Model compression can reduce the number of unnecessary filters but does not take advantage of redundant filters since the training phase is...

Xinxin Liu,Yunfeng Zhang,Fangxun Bao,Kai Shao,Ziyi Sun,Caiming Zhang

2020, 6(4): 467-476.   doi:10.1007/s41095-020-0181-9
Abstract ( 19 HTML ( 0   PDF(707KB) ( 11 )   Save

This paper proposes a kernel-blending connection approximated by a neural network (KBNN) for image classification. A kernel mapping connection structure, guaranteed by the function approximation theorem, is devised to blend feature extraction and feature classification through neural network learning. First, a feature extractor learns features from the raw images. Next, an automatically constructed kernel mapping connection maps the feature vectors into a feature space. Finally, a linear clas...

Ding-Nan Zou,Song-Hai Zhang,Tai-Jiang Mu,Min Zhang

2020, 6(4): 477-487.   doi:10.1007/s41095-020-0184-6
Abstract ( 27 HTML ( 0   PDF(957KB) ( 11 )   Save

In this paper, we introduce an image dataset for fine-grained classification of dog breeds: the Tsinghua Dogs Dataset. It is currently the largest dataset for fine-grained classification of dogs, including 130 dog breeds and 70,428 real-world images. It has only one dog in each image and provides annotated bounding boxes for the whole body and head. In comparison to previous similar datasets, it contains more breeds and more carefully chosen images for each breed. The diversity within each br...