Variations of a Hough-Voting Action Recognition System
نویسندگان
چکیده
This paper presents two variations of a Hough-voting framework used for action recognition and shows classification results for lowresolution video and videos depicting human interactions. For low-resolution videos, where people performing actions are around 30 pixels, we adopt low-level features such as gradients and optical flow. For group actions with human-human interactions, we take the probabilistic action labels from the Hough-voting framework for single individuals and combine them into group actions using decision profiles and classifier combination.
منابع مشابه
Propagative Hough Voting for Human Activity Recognition
Hough-transform based voting has been successfully applied to both object and activity detections. However, most current Hough voting methods will suffer when insufficient training data is provided. To address this problem, we propose propagative Hough voting for activity analysis. Instead of letting local features vote individually, we perform feature voting using random projection trees (RPT)...
متن کاملRobust Iris Recognition in Unconstrained Environments
A biometric system provides automatic identification of an individual based on a unique feature or characteristic possessed by him/her. Iris recognition (IR) is known to be the most reliable and accurate biometric identification system. The iris recognition system (IRS) consists of an automatic segmentation mechanism which is based on the Hough transform (HT). This paper presents a robust IRS i...
متن کاملIsolated Character Recognition by Searching Features in Scene Images
Conventional segmentation technique cannot extract an isolated character and a touching character. In this paper, to utilize information of such characters, we propose a novel character recognition method based on extracting feature points and voting. The voting algorithm of the proposed method is similar to the generalized Hough transform. This method enables us to extract and recognize such t...
متن کاملEvaluation of the Parameters Involved in the Iris Recognition System
Biometric recognition is an automatic identification method which is based on unique features or characteristics possessed by human beings and Iris recognition has proved itself as one of the most reliable biometric methods available owing to the accuracy provided by its unique epigenetic patterns. The main steps in any iris recognition system are image acquisition, iris segmentation, iris norm...
متن کاملComment on: "Extended Hough transform for linear feature detection"
Cha et al. [1] recently proposed an efficient extendedHough transform (EHT) method for line detection. The most distinctive advantage of their EHT method is the ability to detect any line segment with desired length. In their proposed EHT method, first the input gray image with size h×w is transferred into the edge map by using the edge detector, e.g. the Sobel operator. For each edge pixel, th...
متن کامل