Gesture Recognition Using Template Based Random Forest Classifiers
نویسندگان
چکیده
This paper presents a framework for spotting and recognizing continuous human gestures. Skeleton based features are extracted from normalized human body coordinates to represent gestures. These features are then used to construct spatio-temporal template based Random Decision Forest models. Finally, predictions from different models are fused at score level to improve overall recognition performance. Our method has shown competitive results on the CHALEARN 2014 Looking at People dataset. Trained on a dataset of 20 gesture vocabulary and 7754 gesture samples, our method achieved a Jaccard Index score of 74.6% on the test set, reaching 7th place among contenders. Among methods that exclusively used skeleton based features, our method obtained the highest recognition performance.
منابع مشابه
Real-Time Hand Gesture Recognition Based on Sparse Positional Data
Low cost devices which provide depth data as well as images (RGB-D), such as the Kinect, have become extremely popular of late. A compact and accurate device launched recently draws attention: the Leap Motion. But despite its high acquisition rate and precision, the data it provides is extremely sparse. In this paper we present a methodology for gesture recognition capable of dealing with the s...
متن کاملExamining Classifiers Applied to Static Hand Gesture Recognition in Novel Sound Mixing System
The main objective of the paper is to present the methodology and results of examining various classifiers (Nearest Neighbor-like algorithm with nonnested generalization (NNge), Naive Bayes, C4.5 (J48), Random Tree, Random Forests, Artificial Neural Networks (Multilayer Perceptron), Support Vector Machine (SVM) used for static gesture recognition. A problem of effective gesture recognition is o...
متن کاملImprovement of Chemical Named Entity Recognition through Sentence-based Random Under-sampling and Classifier Combination
Chemical Named Entity Recognition (NER) is the basic step for consequent information extraction tasks such as named entity resolution, drug-drug interaction discovery, extraction of the names of the molecules and their properties. Improvement in the performance of such systems may affects the quality of the subsequent tasks. Chemical text from which data for named entity recognition is extracte...
متن کاملApplication of ensemble learning techniques to model the atmospheric concentration of SO2
In view of pollution prediction modeling, the study adopts homogenous (random forest, bagging, and additive regression) and heterogeneous (voting) ensemble classifiers to predict the atmospheric concentration of Sulphur dioxide. For model validation, results were compared against widely known single base classifiers such as support vector machine, multilayer perceptron, linear regression and re...
متن کاملGesture Recognition Using Image Comparison Methods
We introduce the use of appearance-based features, and tangent distance or the image distortion model to account for image variability within the hidden Markov model emission probabilities to recognize gestures. No tracking, segmentation of the hand or shape models have to be defined. The distance measures also perform well for template matching classifiers. We obtain promising first results on...
متن کامل