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.
In this paper we propose a new method for detecting object class instances based on Hough transform. Hough forests which are adapted to perform Hough transform have been efficiently used for single-class object detection. In this work we extend them using HaarHOG descriptor which is a combination of Haar wavelet and HOG descriptor. As a result, we increase the number of feature channels in Hough forests...
The major challenge of video surveillance systems is the automated detection and interpretation of events of interest. In case of an abnormal event taking place, an alert should be delivered. Generally, a video surveillance system's framework combines three main phases: moving objects extraction, moving objects classification and tracking, scenario recognition. The last stage depends on the aimed...
In this paper, we present a system for automatic object detection and pose estimation from a single depth map containing multiple objects for bin-picking applications. The proposed object detection algorithm is based on matching the keypoints extracted from the depth image by using the RANSAC algorithm with the spin image descriptor. In the proposed system, we combine the keypoint detection and the...
A method of concealing characters is proposed for degrading legibility of privacy sensitive textual information in natural scene, such as car license plate numbers and name tags. An important property of the proposed method is that it realizes selective concealing of characters, that is, the proposed method degrades legibility of character regions without degrading the quality of non-character regions...
Spatio-temporal context refers to the information of each pixel's historical status and its adjacent pixels. The proposed algorithm applies the spatio-temporal context to the detection of foregrounds. It is based on the codebook model. For each pixel, a weight value is calculated according to the spatio-temporal context of this pixel to influence the detecting conditions. The algorithm can make the...
In recent years, a lot of researches on traffic sign detection and recognition have been done. But most of them were tested under restricted conditions such as camera with high resolution and sensitivity, highway environment or road side having a lot of trees and very few distracting objects. In this paper, we present a fast and robust traffic sign detection system including two main stages: segmentation...
Intelligent vehicle perception involves the correct detection and tracking of moving objects. Taking into account all the possible information at early levels of the perception task can improve the final model of the environment. In this paper, we present an evidential fusion framework to represent and combine evidence from multiple lists of sensor detections. Our fusion framework considers the position,...
This paper presents depth evaluation of object detection for automated assembling robots. Pattern distortion analysis from structured light system figures out an object with the highest depth from its background. An automated assembling robot should priory select and pick an object with the highest depth to reduce physical harm during picking action of the robot arm. Object detection is then combined...
Three-dimensional object detection and recognition is increasingly in manipulation and navigation applications in autonomous service robots. It involves clustering points of the point cloud from an unstructured scene into objects candidates and estimating features to recognize the objects under different circumstances such as occlusions and clutter. This paper presents an efficient approach capable...
Detecting underwater objects is an important application in marine applications. Most of the techniques are based on the amplitude related techniques, whereby the amplitude of the received echo is used to detect objects within specified bounds. Amplitude techniques however are prone to interference and attenuation, thus limiting the capabilities of such systems. Hence, the aim of this paper is to...
This demo presents an AR application that helps the user to solve a jigsaw puzzle that consists of non-textured pieces with a discriminative shape. The pieces are detected, their poses are estimated and the ones that are correctly assembled are highlighted. In order to detect the pieces, the Depth-Assisted Rectification of Contours (DARC) method is used, which performs detection and pose estimation...
This paper proposes a new design and implementation method in supporting a smart surveillance system that can automatically detect abandoned and stolen objects in public places such as bus stations, train stations or airports. The developing system is implemented by using image processing techniques. In the circumstance such as when suspicious events (i.e. left unattended or stolen objects) have been...
Today for oceanographic research, many computer vision applications can be used in data analysis, indexing of underwater objects and the estimation of the population statistics of marine animals has been done with the help of the Remotely Operated Underwater Vehicles (ROV's). Scientific observation of the undersea environment is a challenging problem as it offers a potential for continuous observations...
Object detection and classification in video is an important step in the video surveillance. We propose efficient moving object detection, classification and evaluate its parameter by alternating the algorithm in effective way. The techniques like image subtraction, threshold and foreground detection will be used for object detection and patterns are used for classification. Then frame by frame the...
In computer vision extracting an object from an image automatically is too hard. Towards addressing this issue a comprehensive analysis of most of the Object detection through different Segmentations is performed taken from the major recent publications covering various aspects of the research in this area. We identify the following methods of the state-of-the-art techniques in which an object can...
This paper addresses the generic object counting problem with object overlapping occurring at varied levels and degrees. The overall image containing the objects is segmented from the background. Thereafter a combination of parameters is extracted from each of the segments to construct a parameter space. The overall space formed by these vectors contains redundant dimensions due to the existence of...
Development of automatic multiple intracellular-objects tracking methods is one of the significant challenges in Bioimage-Informatics. The challenge becomes more difficult in case the tracking targets have the same shape and appearance. In order to obtain stable results under that condition, we propose a tracking method based on global optimization. Particularly, we first detect tracking targets by...
Remotely sensed imagery of large bodies of water is often dappled with bright patches known as glint. Solar glint is light originating from the sun that reflects off the water surface directly into a camera's sensor. Glint reduces the ability to observe the water at depth, making complicated problems such as in-water parameter retrieval, benthic mapping, and submerged target detection especially difficult...
Occlusions are common in real world scenes and are a major obstacle to robust object detection. In this paper, we present a method to coherently reason about occlusions on many types of detectors. Previous approaches primarily enforced local coherency or learned the occlusion structure from data. However, local coherency ignores the occlusion structure in real world scenes and learning from data requires...
The study of social animal interactions is used as means for understanding animal behavior and biology. In this work, we describe a computerized method that utilizes 3D visual hull reconstruction to identify and localize rhesus macaques in their social groups. There are three major steps in this study. First, we collect experimental data from four synchronized cameras at different locations and angels...
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.