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.
Robots are typically equipped with multiple complementary sensors such as cameras and laser range finders. Camera generally provides dense 2D information while range sensors give sparse and accurate depth information in the form of a set of 3D points. In order to represent the different data sources in a common coordinate system, extrinsic calibration is needed. This paper presents a pipeline for...
Rapid growing of multimedia processing technologies enables many creative and powerful new applications. Due to the availability of multimedia reconstruction and editing tools, multimedia authentication gained a considerable attention. Some authentication is to be performed during the transmission of data via insecure networks. Data encryption is one of the frequently used method for secure data transmission...
It is the first step to complete edge detection of shaft part for the pose detection task. According to the characteristics of the shaft part image, an algorithm to improve contour detection is presented based on double thr eshold to extract the outline of shaft part. Freeman chain code is used to connect edge points for obtaining integrated contour information. The straightness of shaft image generatrix...
Automatic image annotation is a technique by which computer systems automatically assigns appropriate Keywords to input digital image. Smart cities are characterized by large volume of data, one of the prominent data types are images. In present research, images of smart cities are collected and then using automatic image annotation, several relevant indexing terms are proposed for every image. Using...
In this paper, we introduce robust and synergetic hand-crafted features and a simple but efficient deep feature from a convolutional neural network (CNN) architecture for defocus estimation. This paper systematically analyzes the effectiveness of different features, and shows how each feature can compensate for the weaknesses of other features when they are concatenated. For a full defocus map estimation,...
In this work, we present a method for improving a random sample consensus (RANSAC) based image segmentation algorithm by encapsulating it within a convolutional neural network (CNN). The improvements are gained by gradient descent training on the set of pre-RANSAC filtering and thresholding operations using a novel RANSAC-based loss function, which is geared toward optimizing the strength of the correct...
Free-hand sketch-based image retrieval (SBIR) is a specific cross-view retrieval task, in which queries are abstract and ambiguous sketches while the retrieval database is formed with natural images. Work in this area mainly focuses on extracting representative and shared features for sketches and natural images. However, these can neither cope well with the geometric distortion between sketches and...
Recent progress on saliency detection is substantial, benefiting mostly from the explosive development of Convolutional Neural Networks (CNNs). Semantic segmentation and saliency detection algorithms developed lately have been mostly based on Fully Convolutional Neural Networks (FCNs). There is still a large room for improvement over the generic FCN models that do not explicitly deal with the scale-space...
Supervised image segmentation methods usually start with information extracted from the learning phase to separate an image into non-overlapping regions. We have used user input information or seeds in our previous work to segment partially overlapped translucent regions. However providing a lot of seeds might sometimes be too time consuming that might make the method perform poorly or not work at...
Aggregating extra features has been considered as an effective approach to boost traditional pedestrian detection methods. However, there is still a lack of studies on whether and how CNN-based pedestrian detectors can benefit from these extra features. The first contribution of this paper is exploring this issue by aggregating extra features into CNN-based pedestrian detection framework. Through...
In this paper, we propose an accurate edge detector using richer convolutional features (RCF). Since objects in natural images possess various scales and aspect ratios, learning the rich hierarchical representations is very critical for edge detection. CNNs have been proved to be effective for this task. In addition, the convolutional features in CNNs gradually become coarser with the increase of...
Boundary and edge cues are highly beneficial in improving a wide variety of vision tasks such as semantic segmentation, object recognition, stereo, and object proposal generation. Recently, the problem of edge detection has been revisited and significant progress has been made with deep learning. While classical edge detection is a challenging binary problem in itself, the category-aware semantic...
In this paper, an invisible watermarking algorithm for satellite imagery using Curvelet Transform is proposed. The Raster image is split into smaller non-overlapping blocks. Haralick Co-occurrence texture features [1] are used to identify the area for embedding watermark in these blocks of Raster image. Thus multiple watermarks are embedded in any given image. Edges are selected for embedding watermark...
In this paper, we propose a novel approach for road width measurement from high resolution satellite or aerial images. The proposed approach has three main steps. First, we extract line segments and road center lines on the given remote sensing images. Second, we could obtain many pairs of parallel lines with width information by computing the positional relationship between each other. Then K-means...
We develop a new object-based image analysis (OBIA) software system, named remote-sensing knowledge finder (RSFinder), based on the region-line primitive association framework (RLPAF). In this system, straight-edge lines are promoted as line primitives for OBIA, which is fundamentally different with common OBIA systems, such as eCogntion and ENVI feature extraction module. Based on region-line collaborative...
A method for classifying objects into categories and indexing is proposed to implement object recognition. The relational measurements such as the distance between two points, color comparison is encoded by the attributed relational graph (ARG) representation to provide one-to-one correspondence between models and object features. If the contour is traversed counterclockwise, a sequence can be formed...
Detection, and localization of Bangla text from natural scene images are important prerequisites for developing Bangla OCR as well as many content-based image analyses. But there is no standard Bangla OCR to be used in the daily work. Due to the presence of some unique features, detection and localization of Bangla text have become more challenging than English text. In this paper, we have proposed...
Nowadays, recorded videos from surveillance cameras are important evidence for legal investigation in the field of forensic science. Videos may be modified to deviate contents by a person involves in a crime. In this paper, a video editing detection based on Scalable Color Descriptor (SCD) and Color Layout Descriptor (CLD) is proposed. The detection method is composed of two components: (1) generating...
In this paper, a learning approach is proposed to classify the fog situations into no fog, fog and dense fog three types. Feature vectors designed according to the contrast and details of foggy images are extracted to form the training set. By using the Gaussian Mixture Model to model the probability density of three situations and learning the parameters of the model with the expectation maximization...
Contour detection is a fundamental problem in computer vision. However, there is still a considerable disparity between detection results and actual contours. To detect object-level contours on the basis of comprehensive analysis of potential edges, we present a deep-learning-based approach with a conditional random fields (CRF) model. We obtain the initial edgemap with a VGGNet-based model, and establish...
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.