Depth image-based rendering (DIBR) is a process that uses one 2-D color image and its associated depth map to render virtual view 3-D images. One of the main problems in DIBR is how to reduce holes that occur on the generated virtual view images. In general, preprocessing the whole depth image by smoothing filter before image warping can reduce the hole occurrence. However, smoothing the whole depth image not only produces some geometric distortions on the generated virtual directional images, but also increases computation time. This paper proposes an adaptive edge-oriented smoothing process to solve the above problem, in which the adaptive smoothing filter for the depth map is determined by the characteristics of the hole region with or without vertical lines in the color image. The adaptive smoothing filter contains two types: the asymmetric smoothing filter is used to reduce the geometric distortions by smoothing the hole regions with vertical lines that belong to the background; and the horizontal smoothing filter is used to reduce hole occurrence and computation time by smoothing the hole regions without vertical lines. The experiment results show that the proposed method turns out to be a good tradeoff between time saving, hole reduction rate, and virtual view quality.

Using the optical camera in remote sensing is limited in various environmental conditions. This paper presents a system of combining deep learning and image transform algorithms to detect landslide location in satellite images. In the deep learning part, a convolution neural network is used to classify satellite images contain landslides. From landslide images classified, in order to accurately identify landslides under different lighting conditions, this paper proposes a transformation algorithm Hue – Bi-dimensional empirical mode decomposition (H-BEMD) to determine the landslide region and size. After the location of landslide is detected, we discover the size change of the landslide based on different time points. In this study, we record an accuracy of up to 96% in the classification process, and the accuracy of landslide location almost absolute.

Edge computing enables rapid data processing and decision-making on satellite payloads. Deploying deep learning-based techniques for low-light image enhancement improves early detection and tracking accuracy on satellite platforms, but it faces challenges due to limited computational resources. This paper proposes an edge-computing-enabled inference model specifically designed onboard satellites. The proposed model follows an encoder-decoder architecture to generate the illumination map with low multiplication matrix complexity, 25.52 GMac of 1920 X 1200 image size. To reduce nanosatellite hardware consumption with a single-precision floating-point format, the edge-computing-enabled inference model proposes a quantized convolution that computes signed values. The proposed inference model is deployed on Arm Cortex-M3 microcontrollers onboard satellite payload (86.74 times faster than normal convolution model) but also has a similar quality with the low-light enhanced in full-precision computing of lightweight training model by using the peak signal-to-noise ratio (PSNR, average of 28.94) and Structural Similarity Index (SSIM, average of 0.85) metrics.

A depth image based rendering (DIBR) is the process which uses one 2D color image and its associated depth image to render virtual view images. A problem in DIBR is how to reduce the number of holes occurring on the generated virtual view images. To reduce the holes occurrence, the depth image is pre-processed by smoothing filter before image warping. However, smoothing the whole depth image may introduce some geometric distortions on the generated virtual images and increase the computational time. In this paper, an adaptive edge-oriented smoothing process is proposed to solve the problem. The proposed method adopts an edge dependent depth filter to predict the holes region and then the horizontal smoothing filter is first employed on the predicted holes regions. If hole regions are with vertical edges, the depth image is further pre-processed by asymmetric smoothing filter. The experimental results show that the proposed method can reduce the geometric distortions on the virtual view and preserve the depth quality.

This study proposes an adaptive error concealment selection process in order to improve the quality of reconstructed images which have low computation complexity for multi-view video coding. In this study, the proposed algorithm uses the motion vector variances and texture histogram bins in the blocks neighboring the damaged block in order to define two correlations; the degree of motion and the degree of texture similarity. To increase the accuracy of the suitable EC for the damaged macro-block, these two correlations are used to select a suitable error concealment method for reconstructing the damaged macro-block through fuzzy reasoning. The motion degree indicates the motion complexity for the damaged macro-block, and the texture similarity degree indicates the spatial continuity between the damaged macro-block and its neighboring block. The proposed adaptive error concealment is selected to reduce concealing time on homogenous damaged blocks and to improve the reconstructed image quality on non-homogenous damaged blocks. The experiment results show that the proposed algorithm can reduce the concealing time by at least 1.16 s and can improve the peak signal-to-noise (PSNR) by 0.13 dB-2.44 dB and 0.11 dB-3.52 dB in the main views and auxiliary views, respectively. This proposed algorithm is suitable for the multi-view video transmission on the consumer electronic fields such as 3D mobile devices, 3D television.

Bi-dimensional empirical mode decomposition (BEMD) transforms 2D data into some intrinsic mode functions (IMFs). In this paper, BEMD is used in image preprocessing to determine features of landslides. BEMD omits noisy areas of a landslide image, correctly identifying features of the landslide to conduct training through the Convolutional Neural Networks (CNN) architecture. In satellite image recognition technology, optimization of data transferring between the ground station and the satellite is important. Hence, using BEMD at the pre-training stage of CNN (identifying landslide identification area) reduces the size of the trained model up to 3 times compared to applying the normal CNN architecture with the original images.