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 method to correct the aspect ratio distortion of images using convolutional neural network (CNN). The “aspect ratio”, which is focused on this research, is defined as the relative “image aspect ratio” (i.e. ratio of width to height of image) from non-stretched image. And the aspect ratio can be distorted by vertical or horizontal stretching, which does not maintain the image aspect ratio...
In this paper, we propose a method that automatically estimates surgical phases in a specified workflow with a multi-camera system. More specifically, our goal is to output an appropriate phase label for each one-second of input videos captured by multiple cameras in an operating room. The fundamental idea behind our work lies in constructing a hidden Markov model based on motion features, which are...
In this paper, we present a robust method to improve the accuracy of phases segmentation problem in a specified surgical workflow (SW) by learning a topic model from the optical flow (OF) motion features of general working contexts, such as the medical staffs, equipments and materials. We have an awareness of such working contexts by capturing the SW with multiple synchronized cameras. The main problems...
Talking heads synthesis with expressions from speech is proposed in this paper. Talking heads synthesis can be considered as a learning problem of sequence-to-sequence mapping, which consists of audio as input and video as output. To synthesize talking heads, we use SAVEE database which consists of videos of multiple sentences speeches recorded from front of face. Audiovisual data can be considered...
In this paper, we present two new methods to integrate latent Dirichlet allocation (LDA) which is a topic model for surgical workflow phase estimation with a hidden Markov model (HMM). The proposed methods are able to detect surgical phases automatically based on codebook which is built by quantizing the extracted optical flow vectors from the recorded videos of surgical processes. To detect the current...
In this research, we investigated a method of person identification in closed indoor environment, such as office or laboratory, under the condition which the members change their clothes day-by-day. Furthermore, we did not assume any constraint to posture or location of people even if a face of a person cannot be seen. This is a challenging problem due to the change of their pose and clothes cause...
Clothes give us a lot of information. For example, when we see a person we know, his clothes are helpful to recognize him as well as his face. However, person recognition by clothes is still challenging problem in the area of computer vision due to the variety of a person's clothes, which makes his appearance highly variable. To handle this problem, we propose a person-specific appearance representation...
We propose a robust method of estimating head orientation based on HOG. The proposed method is able to estimate head orientation with a camera even though when a user is not facing the camera. With this method, a head orientation can be estimated precisely in all three axes: roll, yaw, pitch. Furthermore, a simple and robust user identification method is composed by using the results of the Approximate...
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.