Yike Ma

Yike Ma

Auto-generated profile, based on publicly available information

Yike Ma

Institute of Computing Technology Chinese Academy of Sciences (CAS)

Research Focus & Metrics

Academic Career Length

16Years (2011-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
12 November 2022
Verified
Book Chapter
Closed access
PDF file
HXHang Xu
Hang Xu
QZQiang Zhao
Qiang Zhao
YMYike Ma
Yike Ma
XLXiaodong Li
Xiaodong Li
PYPeng Yuan
Peng Yuan
FDFeng Dai
Feng Dai

13 November 2017 in IEEE Transactions on Multimedia
Verified
Journal Article
Closed access
QZQiang Zhao
Qiang Zhao
FDFeng Dai
Feng Dai
YMYike Ma
Yike Ma
LWLiang Wan
Liang Wan
JZJiawan Zhang
Jiawan Zhang
YZYongdong Zhang
Yongdong Zhang
Nowadays superpixel algorithms are widely used in computer vision and computer graphics applications. However existing algorithms are designed for planar images, which are less suited to deal with wide angle images. In this paper, we present a superpixel segmentation method for 360° spherical images. Unlike previous methods, our approach explicitly considers the geometry for spherical images and makes clustering to spherical image pixels. It starts with the seeds defined by Hammersley points sampled on the sphere, then iterates between assignment step and update step which are both based on the distance metric respecting spherical geometry. We evaluate our method on the transformed Berkeley segmentation dataset and panorama segmentation dataset collected by ourselves. Experimental results show that our method can get better performance in terms of adherence to image boundaries and superpixel structural regularity. Furthermore, superpixels generated by our method can reserve the coherence across image boundaries and all have closed contours.

29 July 2023 in Electronics
Verified
Journal Article
Open access
PDF file
HXHang Xu
Hang Xu
XLXinyuan Liu
Xinyuan Liu
YMYike Ma
Yike Ma
ZZZunjie Zhu
Zunjie Zhu
SWShuai Wang
Shuai Wang
FDFeng Dai
Feng Dai
Rotated object detection is a challenging task due to the difficulties of locating the rotated objects and separating them effectively from the background. For rotated object prediction, researchers have explored numerous regression-based and classification-based approaches to predict a rotation angle. However, both paradigms are constrained by some flaws that make it difficult to accurately predict angles, such as multi-solution and boundary issues, which limits the performance upper bound of detectors. To address these issues, we propose a circular Gaussian distribution (CGD)-based method for angular prediction. We convert the labeled angle into a discrete circular Gaussian distribution spanning a single minimal positive period, and let the model predict the distribution parameters instead of directly regressing or classifying the angle. To improve the overall efficiency of the detection model, we also design a rotated object detector based on CenterNet. Experimental results on various public datasets demonstrated the effectiveness and superior performances of our method. In particular, our approach achieves better results than state-of-the-art competitors, with improvements of 1.92% and 1.04% in terms of AP points on the HRSC2016 and DOTA datasets, respectively.

21 April 2023 in Electronics
Verified
Journal Article
Open access
PDF file
HXHang Xu
Hang Xu
QZQiang Zhao
Qiang Zhao
YMYike Ma
Yike Ma
SWShuai Wang
Shuai Wang
CYChenggang Yan
Chenggang Yan
FDFeng Dai
Feng Dai
By providing a 360° field of view, spherical panoramas can convey vivid visual impressions. Thus, they are widely used in virtual reality systems and street view services. However, due to bandwidth or storage limitations, existing systems only provide sparsely captured panoramas and have limited interaction modes. Although there are methods that can synthesize novel views based on captured panoramas, the generated novel views all lie on the lines connecting existing views. Therefore these methods do not support free-viewpoint navigation. In this paper, we propose a new panoramic image-based rendering method for novel view generation. Our method represents each input panorama with a set of spherical superpixels and warps each superpixel individually so the method can deal with the occlusion and disocclusion problem. The warping is dominated by a two-term constraint, which can preserve the shape of the superpixel and ensure it is warped to the correct position determined by the 3D reconstruction of the scene. Our method can generate novel views that are far from input camera positions. Thus, it supports freely exploring the scene with a 360° field of view. We compare our method with three previous methods on datasets captured by ourselves and by others. Experiments show that our method can obtain better results.

21 December 2017 in Multimedia Tools and Applications
Verified
Journal Article
Closed access
PDF file
XWXuehui Wang
Xuehui Wang
FDFeng Dai
Feng Dai
YMYike Ma
Yike Ma
KGKe Gao
Ke Gao
YZYong Dong Zhang
Yong Dong Zhang

4 November 2022
Verified
Book Chapter
Closed access
PDF file
FDFeng Dai
Feng Dai
SZShuaibin Zhang
Shuaibin Zhang
HLHao Liu
Hao Liu
YMYike Ma
Yike Ma
QZQiang Zhao
Qiang Zhao