The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
Semantic lines characterize the layout of an image. Despite their importance in image analysis and scene understanding, there is no reliable research for semantic line detection. In this paper, we propose a semantic line detector using a convolutional neural network with multi-task learning, by regarding the line detection as a combination of classification and regression tasks. We use convolution...
A temporal superpixel algorithm based on proximity-weighted patch matching (TS-PPM) is proposed in this work. We develop the proximity-weighted patch matching (PPM), which estimates the motion vector of a superpixel robustly, by considering the patch matching distances of neighboring superpixels as well as the target superpixel. In each frame, we initialize superpixels by transferring the superpixel...
A background subtraction algorithm using an encoderdecoder structured convolutional neural network is proposed in this work, in order to segment out moving objects from the background. A target frame, its previous frame, and a background model are concatenated and fed into the network as the input. Then, the encoder generates a highlevel feature vector, and the decoder converts the feature vector...
A semi-supervised online video object segmentation algorithm, which accepts user annotations about a target object at the first frame, is proposed in this work. We propagate the segmentation labels at the previous frame to the current frame using optical flow vectors. However, the propagation is error-prone. Therefore, we develop the convolutional trident network (CTN), which has three decoding branches:...
A novel contour-constrained superpixel (CCS) algorithm is proposed in this work. We initialize superpixels and regions in a regular grid and then refine the superpixel label of each region hierarchically from block to pixel levels. To make superpixel boundaries compatible with object contours, we propose the notion of contour pattern matching and formulate an objective function including the contour...
In this work, we propose a weakly supervised online video object segmentation algorithm, which accepts a bounding box as user annotation. First, we estimate the initial distributions of the foreground and the background by employing a visual saliency detector. Next, we simulate movements of double random walkers, one for the foreground and the other for the background. To this end, we introduce a...
A novel RGB-D image segmentation algorithm is proposed in this work. This is the first attempt to achieve image segmentation based on the theory of multiple random walkers (MRW). We construct a multi-layer graph, whose nodes are superpixels divided with various parameters. Also, we set an edge weight to be proportional to the similarity of color and depth features between two adjacent nodes. Then,...
We propose a novel contrast enhancement method for dark images using the value gap expansion force (VGEF) and the sorted histogram equalization. Based on the observation that the inter-pixel relationship is analogous to the electrostatic force, we define the pixel field spread around each pixel and the pixel mass at each pixel position. We compute the VGEF exerted to a pixel by multiplying the pixel...
A histogram-based matching algorithm for stereo images captured under different illumination conditions is proposed in this work. The cumulative histogram of an image represents the ranks of relative pixel brightness, which are robust to illumination changes. Therefore, we design the matching cost based on the similarity of the cumulative histograms of stereo images. As an optional mode, the proposed...
An intermediate view synthesis scheme under varying illumination conditions is proposed in this work. First, we estimate the disparity map based on cumulative color histograms. Since the cumulative histogram of an image represents the brightness ranks of pixels, the disparity estimation is robust against varying illumination conditions. More specifically, we divide each image into segments, and compute...
We propose a new image projection method in an attempt to reduce the perceptual distortion in panoramic image mosaics. Specifically, we reduce the stretching distortion of some image patches and bending of straight lines. Since the stretching distortion usually occurs when projecting a viewing sphere to the cylindrical image surface in an oblique direction, we propose to use an adjustable cylindrical...
An efficient background subtraction algorithm using two-level sampling and silhouette detection is proposed in this work. In the two-level sampling, we identify moving objects at the block level and then at the pixel level. Then, in the silhouette detection, around each sampled foreground pixel, we refine the shapes of foreground objects. We also develop two fast modes for the silhouette detection,...
A real-time video segmentation algorithm, which can extract objects from video sequences even with non-stationary backgrounds, is proposed in this work. First, we segment the first frame into an object and a background interactively to build the probability density functions of colors in the object and the background. Then, for each subsequent frame, we construct a coherence strip, which is likely...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.