Mapping algorithm is the beginning of SLAM, having a significant influence on the design of the follow-up SLAM system and final results. However, the popular mapping algorithms are not robust enough. These algorithms most are based on feature detection but can’t effectively eliminate false matches under challenging circumstances. In addition to this, there is a need for faster algorithms to process higher pixel images with the development of RGB-D sensors. This paper presents a new mapping algorithm to solve the problems. The approach converts the smoothness constraints to offer ultra-robust feature matching. Then, it takes the image smoothness as a statistical likelihood to sore the feature points’ adjacent region. Finally, we use Bi-direction KD-Tree to improve the ICP algorithm. Experiments are carried out with nyuv2 data set. It is challenging enough to test the performance of the new algorithm.
© 2018, Springer Nature Singapore Pte Ltd.

Light filed imaging is becoming popular for its diversity of post-processing and a wide range of applications. Various kinds of research about light field such as light field compression methods are coming out one after the other in recent years. For better evaluation of the quality of light field images and the performance of compression algorithm, the study on quality assessment of light field is in desperate need. In this paper, in order to establish a light field quality assessment database for the subsequent research, we propose a methodology of subjective evaluation for light field image and use a 2D objective evaluation method to verify the methodology. Results show that this methodology can be successfully used to assess the quality of light field content.
© 2018, Springer Nature Singapore Pte Ltd.

The full-reference image quality assessment (IQA) method are limited in practical applications. Here we propose a no-reference quality assessment method for high dynamic range (HDR) images based on tensor space. First, the tensor decomposition is used to generate three feature maps of an HDR image, considering color and structure information of the HDR image. Second, for a given HDR image, the corresponding multi-scale manifold structure features are extracted from the first feature map. For the second and third feature maps of the HDR image, multi-scale contrast features are extracted. Finally, the extracted features are aggregated by support vector regression to obtain the objective quality score of the HDR image. Experimental results show that the proposed method is superior to some representative full and no-reference methods, and even superior to the full-reference HDR IQA method, HDR-VDP-2.2, on the Nantes database. The proposed method has a higher consistency with human visual perception.
© 2018 IEEE.

With the flourishment of 3D content, the loss of quality of the stereoscopic images has been a large problem while being received by human beings. We develop a new metric in this paper to automatically assess the quality of stereoscopic images with the guidance of reference images. Visual saliency (VS) has been largely explored by researchers in the past decade to find out which areas of an image attract most attention of the viewers. We use the similarity of the VS map between original and distorted images as one of the quality-aware features since the degradation of VS map of the images can depict the quality loss in a certain degree. Meanwhile, gradient magnitude (GM) is enriched with image information, and GM similarity is exploited as another feature. While the difference of binocular energy between original and distorted versions reflects the severities of distortion, it can also act as weights between stereo pairs to simulate the binocular perception properties. Therefore, we introduce the difference of binocular energy as part of the features. The depth/disparity information between stereo pairs contains much properties of stereoscopic vision, and we extract features from disparity map. Finally, in order to take advantage of all the features, we utilize support vector machine based regression module to derive the overall quality score. Experimental results show that the proposed algorithm can assess the image quality in a manner of high consistency with human judgments.
© Springer Nature Singapore Pte Ltd. 2017.

Recently, stereoscopic image quality assessment (SIQA) has been attracted more attention in academia and industry nowadays. In this paper, a wavelet decomposition and natural scene statistics based no reference stereoscopic image quality assessment algorithm is proposed. Our motivation is based on the observation that the statistics of the wavelet coefficients can be effectively captured by a generalized Gaussian distribution (GGD), and the distributions of image with different distortion have different shape and spread. The fitting parameters of GGD are extracted as the features. In this paper, stereoscopic image relevant information including stereo pairs, cyclopean image and binocular disparity are regarded as the factors that affecting stereoscopic image quality, and they are involved in the process of feature extraction. Support vector regression (SVR) is utilized to learn a regression model to predict the quality of stereoscopic image. Experimental results demonstrate that the proposed algorithm achieves high consistency with subjective assessment on two public available 3D image quality assessment databases.
© Springer Nature Singapore Pte Ltd. 2017.

This paper presents a 3D (Three dimensional) video stabilization algorithm combined with a joint spatial and temporal strategy. On the temporal axis, SURF (Speeded-Up Robust Features) are extracted from the consecutive frames and then motion parameters are estimated, with which we calibrate and compensate the video frames after smoothing the motion parameters using Kalman filtering. Then, on the spatial axis, a histogram statistics method based on the extracted features is applied to detect the vertical parallax between the two views. Adjustments are implemented only when the parallax is larger than the safety threshold, which is conducted through subjective assessment, to maintain the consistency of 3D videos. The experimental results have shown that the proposed method is effective to reduce the vertical instability and inconsistency between binocular views and improve the quality and comfortableness of 3D videos.
© Springer Nature Singapore Pte Ltd. 2017.

Tone-mapping operators are designed to apply high dynamic range (HDR) images on widely-used low dynamic range (LDR) devices. Developing well-performed tone-mapped image quality assessment (IQA) method is highly desired because traditional IQA method cannot be adopted in cross dynamic range quality measuring. To this end, we proposed a quality assessment method based on image exposure property. Specifically, an image exposure property determination model is utilized to segment HDR image into different exposure region. Then, quality features are extracted according to the distortion characteristics of each exposure region. Finally, the quality of tone-mapped image can be acquired by a trained regression model. Validation experiments on public database show that the proposed method can accurately predict the quality of tone-mapped image.
© 2017 IEEE.

3D holoscopic imaging can provide immersive 3D viewing experiences, which is considered to be a promising 3D acquisition and display solution. However, in order to proper storage and delivery such particular type of image, efficient coding schemes are of great importance. Therefore, in this paper, we propose a new coding scheme based on viewpoint image rendering. All the viewpoint images are rendered firstly from the 3D holoscopic contents. The total rendered viewpoint images are then arranged into a video sequence. HEVC inter coding method is utilized to remove the redundancy among the rendered viewpoint images. Experimental results show that the proposed coding scheme can achieve average 2.70 dB quality improvements for holoscopic images compared to HEVC intra standard.
© Springer Nature Singapore Pte Ltd. 2017.

With the flourishment of 3D content, more and more 3D videos need to be transmitted and stored. The contradiction between the bitrate and the quality loss of stereoscopic images becomes a bottleneck problem. To tackle the problem, the perception characteristics of human visual system (HVS) should be exploited. In this paper, we modify the just noticeable depth difference model (JNDD) and verify its effectiveness using subjective experimental results. The modified JNDD model (MJNDD) consists of a three-piecewise linear function, which is consistent with the characteristics of the physiological structure of HVS. Each segment of the three-piecewise linear function depicts the unique depth perception characteristics in the corresponding depth range. Since MJNDD obtains the support of the physiological experimental results, it fits the subjective experimental data more accurate than the state of the art JNDD models.
© Springer Nature Singapore Pte Ltd. 2017.

3D holoscopic system can provide continuous motion parallax throughout the viewing zone with precise convergence and depth perception, for which it is regarded as a promising technique for future 3D TV. In this paper, a 3D holoscopic image coding scheme based on Gaussian mixture models (GMM) is introduced firstly, taking full advantage of the intrinsic characteristic of such particular type of content. Due to the shortcomings of GMM based method, an improved method is thereafter put forward, in which many parameters that are insignificant in the final estimator of GMM based method are avoided, and more surrounding pixels are used to obtain the model parameters with the help of the least square method. Experimental results indicate that the improved method can obtain considerable gains over HEVC intra prediction and several other prediction methods.
© Springer Nature Singapore Pte Ltd. 2017.