Multiview High Dynamic Range Image Synthesis Using Fuzzy Broad Learning System

Abstract

Compared with the normal low dynamic range (LDR) images, high dynamic range (HDR) images provide more dynamic range and image details. Although the existing techniques for generating HDR images have a good effect for static scenes, they usually produce artifacts on the HDR images for dynamic scenes. In recent years, some learningbased approaches are used to synthesize HDR images and get good results. However, there are also many problems, including the deficiency of explaining and the time-consuming training process. In this paper, we propose a novel approach to synthesize multi-view HDR images through fuzzy broad learning system (FBLS). We use a set of multi-view LDR images with different exposure as input and transfer corresponding Takagi-Sugeno (TS) fuzzy subsystems, then the structure is expanded in a wide sense in the "enhancement groups" which transfer from the TS fuzzy rules with nonlinear transformation. After integrating fuzzy subsystems and enhancement groups with the trained-well weight, the HDR image is generated. In FBLS, applying the incremental learning algorithm and the pseudoinverse method to compute the weights can greatly reduce the training time. In addition, the fuzzy system has better interpretability. In the learning process, IF-THEN fuzzy rules can effectively help the model to detect artifacts and reject them in the final HDR result. These advantages solve the problem of existing deep learning methods. Furthermore, we set up a new dataset of multi-view LDR images with corresponding HDR ground truth to train our system. Our experimental results show that our system can synthesize high-quality multi-view HDR images, which has a higher training speed than other learning methods.

Virtual Reality and Its Application for Producing TV Programs

“…e method of reference [4] is compared with the proposed method, which is not high from the beginning of the experiment, nor does it increase significantly with the number of experiments. With the increase in the number of experiments, the fulfillment of the psychological requirements of the audience is gradually improved because this method recognizes faces in TV programs and then uses the adaptive stereo matching method to match images, effectively shortening the program production cycle and improving the quality of TV program production and the program competitiveness.…”

“…e virtual image is synthesized and used in TV program production. e experimental results reveal that the similarity between the exposure image and the reference viewpoint image drawn by this method is high, although this method has the problem of poor section appeal [4].…”

Research on multi-source data fusion target detection algorithm based on adaptive multi-scale and dynamic feature extraction

“…In recent years, Cameras and LiDAR have been widely used in object detection [1][2][3][4][5][6][7]. However, a single sensor has poor interference resistance and is easily affected by complex environments [8][9][10][11][12][13][14][15][16][17][18][19]. Cameras capture images quickly and provide rich texture information, but they struggle to detect the shape and specific location of objects and are susceptible to weather and environmental influences [20][21][22][23][24][25][26][27][28].…”

Infrared and visible video fusion method based on inter-frame feature association and PID control

“…The purpose of infrared and visible video fusion is to combine video features from different modalities, then obtain information-rich fused video. Video fusion can be considered as a special kind of video enhancement technology, usually, its downstream tasks contain object segmentation [3,4,5], object tracking [6], object detection and classification [7] ， video-based mesh reconstruction [8] and image synthesis [9] etc.…”