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.
Learning and then recognizing a path is a challenging task for state of the art algorithms in computer vision and robotics. In this paper, we present a new approach to visual localization along a path. Classically visual paths have been described using keyframes, single images taken at specific locations. Our method uses all the images of a path segment, Gabor-Gist and, principal component analysis...
In this paper we present an effective and robust system to classify fruits under varying pose and lighting conditions tailored for an object recognition system on a mobile platform. Therefore, we present results on the effectiveness of our underlying segmentation method using RGB as well as depth cues for the specific technical setup of our robot. A combination of RGB low-level visual feature descriptors...
Kinect camera is a new developed cheap senor, which captures color images along with per-pixel depth information. In this paper, a new object localization method, based on RGB-D image, is presented. On the basis of traditional image segmentation, the system determines the motion tracing object according to current environment. Then by using Back projection algorithm, the system implements the object...
A new framework capable of analyzing multi-beam sonar images for detecting and tracking underwater object using a BlueView (BV) Sonar is presented in this paper. This framework is applied to the design of an obstacle avoidance system for Unmanned Measurement Boat. The real-time sonar data flow collected by multi-beam sonar is expressed as an image and pre-processed by the system. According to the...
This paper proposes a vision-based behavior selection system using biologically-inspired visual attention selection mechanisms, i.e., Bottom-Up attention and Top-Down attention. We adopt purely Bottom-Up attention selection to identify conspicuous regions for obtaining the salient landmarks, while propose an object-based Top-Down attention method using low dimensional task-relevant feature for searching...
This paper presents a novel hand gesture recognition method based on Principal Directional Features (PDF). The image sequence is captured using a fixed mounted monocular camera to recognize dynamic gestures. Haar-like feature based cascaded classifier is used for hand area segmentation. Text based Principal Directional Features are extracted from the segmented images. Longest Common Subsequence algorithm...
This paper proposes a pre-attentive visual segmentation method by using Jeffrey divergence based irregular pyramid, termed as “JIP” algorithm. The proposed JIP algorithm obtains a suboptimal labeling solution under the condition that the number of segments is not manually given. This algorithm models each node at higher pyramidal levels as a probabilistic distribution, based on which Jeffrey divergence...
Image Matting is the key technology in image processing, video editing, and film-making applications. With the fast development of modern information technology, image matting has gained increasing interests from both academic and industrial communities. So what is Image Matting? And, What's the Role of Image Matting in Image Segmentation? In this paper, we will try to give a comprehensive and constructive...
A general vision approach for environment understanding of mobile robot is proposed, which is inspired by biological visual cortex. Gray level image from robot camera is firstly processed in the selective attention layer, and then in S and C layers for meaningful structure elements. With the help of the Sc layer designed for endpoints detection, the line segments map is generated to serve as the form...
This paper presents surface area calculation using point cloud from Kinect. The point cloud from Kinect is erroneous due to characteristics of this low cost device. Applying marching cube directly from such this point cloud, the resulting triangular mesh has multiple layers; despite the fact that their original surface has only one layer. In this paper, we bypass marching cube, which is ineffective...
This paper presents a novel image haze removal approach from single image. In the algorithm, the constant albedo and dark channel prior methods are combined to represent the transmission model of hazed image. And then, the watershed segmentation approach is introduced to decompose the input image into some gray level consistent areas. Compared with traditional fixed image partition schemes, better...
Controlling robots based on human motion recognition visually has attracted much attention recently. Classical methods are mainly with single viewpoint, like interaction via Microsoft Kinect depth sensor. However, such methods will strictly limit the interaction range and human users have to face the visual sensor. Stereo vision methods are helpful to implement a viewpoint-free system. Visual hull,...
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.