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.
Due to low brightness, the performance of autofocus will serious decline in low contrast images, making it quite difficult to locate the focus region. To tackle this challenge in computer vision, we perform autofocus by conducting a salient object detection method. Based on the mechanism of human visual system, salient object is detected by calculating global saliencies in superpixels. First, the...
The development of moving object detection systems has become of great interest in the video surveillance field. Although many foreground detection methods have been proposed, the problems of incomplete object shapes and misclassified shadow regions remain. We propose a new approach by combining bit-planes representation with gray-level co-occurrence matrix (GLCM). This allows the system to exploit...
Global 3D point cloud registration has been solved by finding putative matches between the point clouds for establishing alignment hypotheses. A naive approach would try to perform exhaustive search of triplets with a cubic runtime complexity in the number of data points. Super4PCS reduces this complexity to linear by making use of sets of 4 coplanar points. This paper proposes 2-Point-Normal Sets...
Automatic object detection in infrared images is a vital task for many military defense systems. The high detection rate and low false detection rate of this phase directly affect the performance of the following algorithms in the system as well as the general performance of the system. In this work, a fast and robust algorithm is proposed for detection of small and high intensity objects in infrared...
Usually, in radar imaging, the scatterers are supposed to respond the same way regardless of the angle from which they are viewed and have the same properties within the emitted spectral bandwidth. Nevertheless, new capacities in SAR imaging (large bandwidth, large angular extent) make this assumption obsolete. An original application of the Linear Time-Frequency Distributions (LTFD) in SAR imaging...
Pick-and-place is an important task in robotic manipulation. In industry, template-matching approaches are often used to provide the level of precision required to locate an object to be picked. However, if a robotic workstation is to handle numerous objects, brute-force template-matching becomes expensive, and is subject to notoriously hard-totune thresholds. In this paper, we explore the use of...
Moving objects detection or change detection in video sequences, is a fundamental task in video surveillance applications. Although, existing methods perform well on videos filmed by stationary cameras, these methods fail dramatically in videos filmed by non-stationary cameras. In particular, in very low frame rate and sudden illumination change scenarios, like Wide-Area Motion Imagery (WAMI). In...
Mapping and self-localization in unknown environments are fundamental capabilities in many robotic applications. These tasks typically involve the identification of objects as unique features or landmarks, which requires the objects both to be detected and then assigned a unique identifier that can be maintained when viewed from different perspectives and in different images. The data association...
In this paper, we propose a robust multi-object tracking algorithm for acquiring object oriented multi-angle videos, which takes advantages of two different tracking techniques represented by subdivided color histogram based tracking and labeling based tracking. Object models based on color histograms are further subdivided to differentiate similar color regions. Another tracking technique utilizes...
Recently, investigating boundary prior to aid other low-level image cues, have gained great attention in salient object detection. Although the salient regions are mostly located in the image center, the inverse might not necessarily be true. In addition, such kind of center-bias assumption is very simple and fragile, especially when salient regions often touch the image boundary or the images are...
In this work we study the problem of weakly supervised human body detection under difficult poses (e.g., multiview and/or arbitrary poses) within the framework of multi-instance learning (MIL). We first point out the existence of the so-called “vanishing gradient” problem in MIL with a noisy-or rule as its bagging model. This is mainly due to the independence assumption of the noisy-or rule, which...
This paper investigates precise pupil center localization in low-resolution images. Being an essential preprocessing step in many applications such as gaze estimation, face alignment as well as human-computer interaction, robust, precise, and efficient methods are necessary. We present a method for accurate eye center localization operating with images from simple off-the-shelf hardware such as webcams...
This paper presents efficient object tracking in video sequences using multiple features by embedding mean shift into particle filters. When clutter background and occlusions are present. Particle filtering is used because it is very robust and performs well for non-linear and non-Gaussian dynamic state estimation problems. The image features, such as shape, texture, color, contours, and random motion...
This paper tackles the object assignment problem in a multiple target tracking context. Multi-target association consists in defining at each time step the relations between two sets. One set is related to the newly detected objects and the other to the already known ones. In this paper, the Dempster-Shafer theory, also known as belief functions is used. The contribution lies in the development of...
Automatic semantic annotation of high-resolution optical satellite images is a task to assign one or several predefined semantic concepts to an image according to its content. The fundamental challenge arises from the difficulty of characterizing complex and ambiguous contents of the satellite images. To address this challenge, a diversity constrained joint multi-feature learning method is proposed...
Infrared small target detection is still one of the key techniques in the infrared search and track systems. We proposed a robust and efficient detection method by exploiting low-rank and sparse representation. We extend traditional low-rank and sparse representation to temporal domain. Initially, we use the proposed method to locate the suspected position of a target in the first frame. Then, we...
Gaussian Mixture Model (GMM) and its variations process images by per pixel, so they may be corrupted by noises and the computational cost is high. In this paper, we propose a robust moving object detection algorithm with a background dictionary learning. To do this, we first divide an image into multiple image patches that have the same sizes. Each patch is the object or background. Then, A background...
The premise and foundation of autonomous landing relative navigation based on vision for unmanned aerial vehicle (UAV) are accurate detection of landing cooperative target. In order to overcome the problem of cooperative target detection susceptible to illumination change and the interference, a new landing cooperative target detection algorithm based on low rank matrix recovery theory is proposed...
The neuromorphic visual processing framework mimicking the biological vision system offers an alternative process into applying computer vision in everyday environment. With the growing interest for an effective approach for making detection of vulnerable road users for the purpose of safety enhancement, the proposed neuromorphic visual processing was tested on vulnerable road users such as cyclists...
In this paper, a new image sequence model, obtained by learning in a multilayer self-organizing neural network, is proposed for moving microorganism detection in sewage treatment system. The model is able to handle diverse challenging scenarios accurately, such as dynamic background, gradual illumination variations, shadows cast and so on, which are robust against false detections for different types...
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.