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 do staircase detection with a stereo vision based algorithm through NAO robot, using one of this cameras. Robot programming was implemented in Python language using ROS software. The detection algorithm is divided in two parts: line detection and depth perception. In line detection process we use Hough transform and vanishing point criteria for line segmentation. Respecting depth...
Gaze analysis in dynamic environments has remained an unresolved problem due to the complexities that pertain to the detection and tracking of objects in the visual environment. This study provides a solution to the problem for face-to-face communication, in which the visual objects in the environment are faces. The application that has been developed for this purpose is able to detect and track faces...
The main challenge of previous saliency detection method is the low quality of obtained saliency map which missed the edge and texture information easily. So it cannot reflect the integrated image salient information. Considering this problem, we propose a novel saliency measure method which combine region contrast and fast guided filter. This method utilizes region contrast method to obtain initial...
To improve the accuracy of surface defect detection, an approach of defect inspection based on visual saliency map and Support Vector Machine(SVM) is proposed. Monochrome fabric defect images are taken as examples in this paper. By analyzing the visual saliency maps of these images, the global associated value and the background associated value are extracted as the two features. After being normalized,...
Unsupervised segmentation of action segments in egocentric videos is a desirable feature in tasks such as activity recognition and content-based video retrieval. Reducing the search space into a finite set of action segments facilitates a faster and less noisy matching. However, there exist a substantial gap in machine's understanding of natural temporal cuts during a continuous human activity. This...
This paper presents an approach using range measurement through homography calculation to build 2D visual occupancy grid and control the robot through monocular vision. This approach is designed for a Cellbot architecture. The robot is equipped with wall following behavior to explore the environment, which enables the robot to trail objects contours, residing in the fuzzy control the responsibility...
Common visual recognition tasks such as classification, object detection, and semantic segmentation are rapidly reaching maturity, and given the recent rate of progress, it is not unreasonable to conjecture that techniques for many of these problems will approach human levels of performance in the next few years. In this paper we look to the future: what is the next frontier in visual recognition?...
Localizing functional regions of objects or affordances is an important aspect of scene understanding and relevant for many robotics applications. In this work, we introduce a pixel-wise annotated affordance dataset of 3090 images containing 9916 object instances. Since parts of an object can have multiple affordances, we address this by a convolutional neural network for multilabel affordance segmentation...
This paper addresses video summarization, or the problem of distilling a raw video into a shorter form while still capturing the original story. We show that visual representations supervised by freeform language make a good fit for this application by extending a recent submodular summarization approach [9] with representativeness and interestingness objectives computed on features from a joint vision-language...
Scene parsing, or recognizing and segmenting objects and stuff in an image, is one of the key problems in computer vision. Despite the communitys efforts in data collection, there are still few image datasets covering a wide range of scenes and object categories with dense and detailed annotations for scene parsing. In this paper, we introduce and analyze the ADE20K dataset, spanning diverse annotations...
Deep learning has been applied to saliency detection in recent years. The superior performance has proved that deep networks can model the semantic properties of salient objects. Yet it is difficult for a deep network to discriminate pixels belonging to similar receptive fields around the object boundaries, thus deep networks may output maps with blurred saliency and inaccurate boundaries. To tackle...
We present an end-to-end, multimodal, fully convolutional network for extracting semantic structures from document images. We consider document semantic structure extraction as a pixel-wise segmentation task, and propose a unified model that classifies pixels based not only on their visual appearance, as in the traditional page segmentation task, but also on the content of underlying text. Moreover,...
Visual narrative is often a combination of explicit information and judicious omissions, relying on the viewer to supply missing details. In comics, most movements in time and space are hidden in the gutters between panels. To follow the story, readers logically connect panels together by inferring unseen actions through a process called closure. While computers can now describe the content of natural...
We propose a weakly-supervised approach that takes image-sentence pairs as input and learns to visually ground (i.e., localize) arbitrary linguistic phrases, in the form of spatial attention masks. Specifically, the model is trained with images and their associated image-level captions, without any explicit region-to-phrase correspondence annotations. To this end, we introduce an end-to-end model...
We propose a weakly supervised semantic segmentation algorithm that uses image tags for supervision. We apply the tags in queries to collect three sets of web images, which encode the clean foregrounds, the common backgrounds, and realistic scenes of the classes. We introduce a novel three-stage training pipeline to progressively learn semantic segmentation models. We first train and refine a class-specific...
This paper focuses on indoor semantic segmentation using RGB-D data. Although the commonly used deconvolution networks (DeconvNet) have achieved impressive results on this task, we find there is still room for improvements in two aspects. One is about the boundary segmentation. DeconvNet aggregates large context to predict the label of each pixel, inherently limiting the segmentation precision of...
We introduce a novel strategy for learning to extract semantically meaningful features from aerial imagery. Instead of manually labeling the aerial imagery, we propose to predict (noisy) semantic features automatically extracted from co-located ground imagery. Our network architecture takes an aerial image as input, extracts features using a convolutional neural network, and then applies an adaptive...
We introduce a new large-scale data set of video URLs with densely-sampled object bounding box annotations called YouTube-BoundingBoxes (YT-BB). The data set consists of approximately 380,000 video segments about 19s long, automatically selected to feature objects in natural settings without editing or post-processing, with a recording quality often akin to that of a hand-held cell phone camera. The...
We propose a general framework called Network Dissection for quantifying the interpretability of latent representations of CNNs by evaluating the alignment between individual hidden units and a set of semantic concepts. Given any CNN model, the proposed method draws on a data set of concepts to score the semantics of hidden units at each intermediate convolutional layer. The units with semantics are...
Studies in visual perceptual learning investigate the way human performance improves with practice, in the context of relatively simple (and therefore more manageable) visual tasks. Building on the powerful tools currently available for the training of Convolution Neural Networks (CNN), networks whose original architecture was inspired by the visual system, we revisited some of the open computational...
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.