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.
We propose a novel diminished reality method which is able to (i) automatically recognize the region to be diminished, (ii) work with a single RGB-D sensor, and (iii) work without pre-processing to generate a 3D model of the target scene by utilizing SLAM, segmentation, and recognition framework. Especially, regarding the recognition of the area to be diminished, our method is able to maintain high...
Augmented reality has seen a fast-growing gain of interest in the last few decades. Due to technological advances, smartphones are now devices that allow to experience augmented reality systems, anytime and anywhere. Although its emerging success among users, some problems AR have been reported inhibiting its full acceptance in our digital society. The aim of this paper is to present a study about...
Most ConvNets formulate object recognition from natural images as a single task classification problem, and attempt to learn features useful for object categories, but invariant to other factors of variation such as pose and illumination. They do not explicitly learn these other factors, instead, they usually discard them by pooling and normalization. Here, we take the opposite approach: we train...
In this paper we focus on automatically learning object models in the framework of keypoint based object recognition. The proposed method uses a collection of views of the objects to build the model. For each object the collection is composed of N×M views obtained rotating the object around its vertical and horizontal axis. As keypoint based object recognition using a complete set of views is computationally...
To realize automated checker system of cafeteria, we have developed a meal menu recognition system. This system employs a RGB-D sensor to get both color image and depth image. From these images, first we extract and distinguish each dishes. By knowing what type of dish is used for the meal, we can reduce candidates for meal menus, it leads up to improvement of menu recognition accuracy. Some experimental...
A recognition system for three-dimensional objects is proposed in this paper. This system consists of line laser projectors and a web camera in order to collect depth and curvature information of objects, leading to a compact and cost-effective system compared to light coding-based systems such as Microsoft Kinect. Curvature information of objects can be obtained through calculation of Fourier components...
While there are several promising approaches for visual object recognition the application of lightweight devices under varying image conditions and using low quality images still causes lots of problems to be solved. We introduce a new retrieval mechanism including standard orientation sensors helping the visual recognition process. We apply a view based model of the objects and the matching of the...
A new approach for lightweight video-based object recognition is introduced where a user moves a camera around a target object of interest. The extraction of image features and the retrieval algorithm is running in a lightweight mobile computer (tablet or phone). We apply a view based model of the objects and the matching of the query and candidate images is based on compact image descriptors coupled...
With the rapid development of modern information technology, target recognition plays an increasingly important role in agricultural production, national defense construction. However, the existing target recognition algorithm has many limitations, such as image distortion, difficult to recognize target image or poor recognition results because of camera angles and lighting conditions. Based on the...
This paper introduces a novel method, which utilizes local appearance descriptions in a more efficient way, for 3D object recognition. Geometrically consistent local features are identified using affine 3D and 2D geometric invariants, without any reliance on partial or global planarity. Geometric invariants replace the traditional, highly constrained 2D affine transform estimation/verification step,...
In this work we describe main features of software modules developed for Android smartphones that are dedicated for the blind users. The main module can recognise and match scanned objects to a database of objects., e.g. food or medicine containers. The two other modules are capable of detecting major colours and locate direction of the maximum brightness regions in the captured scenes. We conclude...
Recently, a surveillance system has been widely used for our circumstances for the purpose of observing volcano, tsunami, crime prevention, and so on. However, most of surveillance systems are consisted of handy cameras and mono-directional CCD cameras, and so it is caused "blind spot" on the system. In this paper, Omni-directional lens is introduced for Gigabit Ether Camera, and the Seamless...
In this paper, we propose a smart phone based interaction in Intelligent Space using object recognition and facing direction of user. The R-Fii (Real-world Flexible Intelligent Interface) which is an interaction method using the user's mobile device in intelligent space was proposed in the past. However, the R-Fii has some problems. The object recognition rate doesn't reach to the utilizable level...
Image feature based landmark detection is widely used in machine vision for mobile robotics applications. Advanced image feature extraction algorithms offer robust keypoint detection as being invariant to numerous transformations such as translation, rotation, scale change. Even slight changes in brightness, contrast or viewpoint do not affect feature point matching abilities. The most widely used...
Robust object recognition is a mandatory prerequisite for many applications in Service Robotics. A common approach is to capture a single image of the scene from a fixed position and to recognize all objects at once. This challenging task is even more demanding in everyday environments. We propose an approach for object recognition which makes use of mobile manipulation. An initial object belief is...
This paper describes a classification method using the selection of optimal sensing positions and invariance based on the third-correlation for the recognition of observed objects among those registered in an image database.
We study about the possibility of real-world user interface. We plan to construct AR communication tool in the small community. So distributed environment is required. To achieve the environment, concept oriented AR application is considerable. In this paper, we discuss about the framework for Augmented Reality applications.
Blind people navigate safely through a familiar room based on strong expectations about the location of objects. If something has been moved, added or removed, it can present a difficulty and potentially a danger. Human eyes are one of the most important body parts that help humans to understand and interact with their surroundings. Most learning and recognition of objects around us is accomplished...
The authors aim at recognition of multiple objects by using robot vision and its manipulation. In the case where multiple objects are arranged in a shelf, front objects may conceal some objects behind them. A robot can recognize these objects if it can recognize the front objects using prior knowledge and remove them with its arm. However, it sometimes fails to recognize the objects because of the...
In this paper, we address a novel task "cooking recognition task". Cooking recognition task is to keep recognizing a cooking action of a cook and the target food product of the action at any time of the cooking. The target object of the recognition could change its visual feature completely by peeling, cutting, and mixed with others during the task. Nonetheless, such food product is called...
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.