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.
Recent advances in semantic segmentation have mostly been achieved by utilizing deep convolutional neural networks (CNNs). In this paper, a novel indoor semantic segmentation method is proposed by integrating CNN and patch-level Conditional random fields (CRF). Multi-scale images are sent to CNN to capture objects of different sizes as well as to extract features at multiple scales. Patch-level CRF...
Morphological changes of retinal vessels such as arteriovenous (AV) nicking are signs of many systemic diseases. In this paper, an automatic method for AV-nicking detection is proposed. The proposed method includes crossover point detection and AV-nicking identification. Vessel segmentation, vessel thinning, and feature point recognition are performed to detect crossover point. A method of vessel...
Depth estimation, which is mostly performed by stereo vision, is a remarkable task in vision and scene understanding. In this paper, depth map estimation from a single image is investigated and applied in pedestrian candidate generation. To recover accurate depth map from a single image, a Markov Random Field (MRF) model that incorporates both image depth cues and the relationships between different...
Object detection is a hot spot of the research in computer vision since many applications require the determination of the object location. There are many object detection methods based on feature matching methods. In this paper, we locate object on robot operation system. The SIFT keypoints of the template and test images are extracted at first. Then, the matching method is proposed to find the template...
Accurate detection and position estimation of human objects is essential in many security applications including door access control, surveillance monitoring, intrusion detection, alarm monitoring and so on. This paper proposes an efficient approach for human detection and localization in secure access control by analysing facial features. The proposed technique captures the video scenes using a stereo...
Deep Convolutional Neural Networks(DCNNs) have recently shown great performance in many high-level vision tasks, such as image classification, object detection and more recently outdoor semantic segmentation. However, the convolutional layer only process the local regions in the image, ignoring the global context information. To overcome this poor localization property of Convolutional Neural Networks(CNNs),...
Superpixel segmentation becomes more and more popular in the fields of computer vision and image processing. The simple linear iterative clustering (SLIC) is widely used due to its high segmentation accuracy and low computational complexity. In this paper, we propose a variance adaptive SLIC (VASLIC) algorithm. The compactness factor of the proposed algorithm is determined according to the image neighbourhood...
Clustering is a process that aims to group the similar records in one cluster and dissimilar records in different clusters. K-means is one of the most popular and well-known clustering technique for its simplicity and light weight. However, the main drawback of K-means clustering technique is that it requires a user (data miner) to estimate the number of clusters in advance. Another limitation of...
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.