Yingxue Zhang's research while affiliated with Wuhan University and other places

Publications (13)

Article
Image compression is essential for remote sensing due to the large volume of produced remote sensing imagery and system's limited transmission or storage capacity. As one of the most important applications, classification might be affected due to the introduced distortion during compression. Hence, we perform a quantitative study on the effects of...
Article
In this paper, we review the recent advances in the pipeline of omnidirectional video processing including projection and evaluation. Being distinct from the traditional video, the omnidirectional video, also called panoramic video or 360 degree video, is in the spherical domain, thus specialized tools are necessary. For this type of video, each pi...
Article
With the development of virtual reality, higher quality panoramic videos are in great demand to guarantee the immersive viewing experience. Therefore, quality assessment attaches much importance to correlated technologies. Considering the geometric transformation in projection and the limited resolution of head-mounted device (HMD), a modified disp...
Article
In this paper, a model using color dictionary based sparse representation for 360° image saliency prediction is proposed, referred to as CDSR. The proposed model simulates human color perception, extracting the image features by color dictionary based sparse representation, combining with weighted center–surround differences between image patches....

Citations

... Finally, they regressed the multifrequency information and naturalness computation using SVR algorithm and predict the visual quality of panoramic image. Zhang et al. presented a no-reference based method for panoramic video quality assessment [60] . Their method extracts spatial and temporal features from the panoramic video. ...
... The parameters of target devices and databases that we used in our work are summarized in Table III. These datasets come from several sources [31,36,37], and they all have been used extensively in studies on visual quality topics in the past. As shown in Table III, our datasets include devices with a broad range of form factors: from 6" mobiles to 65" UHDTVs. ...
... The permutation or scrambling, or shuffling process is performed using P-Box. As illustrated in Fig. 5, P-Box can also be described as a bijection [40][41]. If input x and output y in IRM and FRM are indications using Eq. ...
... In this paper, we focus on providing high quality with the desire to have quite a high CR and to perform the compression quite quickly and automatically. If the quality degradation due to a lossy compression is limited, it is possible to expect that the RS data classification or object (e.g., crack) detection are performed well enough, and that the RS data being visualized are of a proper quality for analysis and so on [15][16][17]. ...
... After adding these noises to the combined dataset, we got four datasets, one for each of the previous noise types. These datasets were used as an input to the autoencoder and dual autoencoder, and the outputs of the autoencoder and dual autoencoder were compared with the original dataset without the noise using the structural similarity index, which is known as an estimation to compare the similarity of two images and is described by the following Equation [73]: ...
... Such immerse and interactive viewing experience renders existing quality assessment methods for planar videos [11][12][13][14][15][16][17] ineffective in predicting the perceived quality of 360°videos. Although several subjective quality studies [2][3][4][5][6][7][8][9][10] on omnidirectional videos have been conducted, they may have three limitations. First, most of the resulting databases contain synthetic distortions only, with compression artifacts being the most representative. ...
... All of these strategies necessitate a larger dataset for training, which makes the process lengthy and computationally complex, especially for IoUTs with limited resources. Colour dictionary based sparse representation is used in [10]. Dictionary based compression technique creates memory issue for low power embedded devices in IoUT. ...
... Of course, in order to make the scene seen by the audience more realistic, and to make the people roaming in this scene have a better sense of immersion, the picture must be made three-dimensional. erefore, this paper proposes a 3D technology on the basis of the existing, which converts International Transactions on Electrical Energy Systems the panoramic video shot according to specific requirements into a stereoscopic effect [12]. e application of 3D technology includes 3D animation, 3D virtual, 3D mural, and 3D stereo. ...
... Thus, there is an increasingly urgent need for quantitative comparison of eye movement indicators [23]. The scanpath map [24][25][26][27], heat map [28,29], and transition matrix [30] are several important methods for analyzing the sequence of fixation. The scanpath map represents the fixations as a sequential sequence, and vector-and character-based editing methods have been applied to calculate the similarity and difference of scanpaths. ...
... VR virtual scene modeling technology is mainly divided into two segments, i.e., modeling based on geometric model and modeling based on image [10]. The modeling technology based on geometric model firstly abstracts the real environment, and then uses the basic graphic unit to build the geometric model of the scene, and carries out such operations as position placement and coloring, and then converts them into pixels on the computer screen. ...