This article presents the design and implementation of a handheld Augmented Reality (AR) system called Mobile Augmented Reality Touring System (M.A.R.T.S). The results of experiments conducted during museum visits using this system are also described. These experiments aim at studying how such a tool can transform the visitor's learning experience by comparing it to two widely used museum systems. First, we present the museum's learning experience and a related model which emerged from the state of the art. This model consists of two types of activity experienced by the observer of a work of art: sensitive and analytical. Then, we detail M.A.R.T.S architecture and implementation. Our empirical study highlights the fact that AR can direct visitors' attention by emphasizing and superimposing. Its magnifying and sensitive effects are well perceived and appreciated by visitors. The obtained results reveal that M.A.R.T.S contributes to a worthwhile learning experience.
Automatic detection of animals that have strayed into human inhabited areas has important security and road safety applications. This paper attempts to solve this problem using deep learning techniques from a variety of computer vision fields including object detection, tracking, segmentation and edge detection. Several interesting insights are elicited into transfer learning while adapting models trained on benchmark datasets for real world deployment. Empirical evidence is presented to demonstrate the inability of detectors to generalize from training images of animals in their natural habitats to deployment scenarios of man-made environments. A solution is also proposed using semi-automated synthetic data generation for domain specific training. Code and data used in the experiments are made available to facilitate further work in this domain.
Very few benchmark exists for assessing pattern detection and recognition in streams in general and for gesture processing in particular. We propose a dedicated benchmark based on the construction of isolated gestures and gesture sequences datasets. This benchmark is associated to a general assessment methodology for streaming processing which first consists in labelling the stream according to some heuristics (that can be optimized on training data) and then aligning the ground truth labelling with the predicted one. 6 pattern recognition models (including DTW, KDTW, HMM, HCRF and SVM) have been accordingly evaluated using this benchmark. It turns out that the regularized kernelized version of DTW measure (KDTW) associated to a SVM is quite efficient, comparatively to the other models, for detecting and recognizing continuous gestures in streams.
Abstract-On-line supervised spotting and classification of subsequences can be performed by comparing some distance between the stream and previously learnt time series. However, learning a few incorrect time series can trigger disproportionately many false alarms. In this paper, we propose a fast technique to prune bad instances away and automatically select appropriate distance thresholds. Our main contribution is to turn the ill-defined spotting problem into a collection of single well-defined binary classification problems, by segmenting the stream and by ranking subsets of instances on those segments very quickly. We further demonstrate our technique's effectiveness on a gesture recognition application.
Very few benchmark exists for assessing pattern detection and recognition in streams in general and for gesture processing in particular. We propose a dedicated benchmark based on the construction of isolated gestures and gesture sequences datasets. This benchmark is associated to a general assessment methodology for streaming processing which first consists in labelling the stream according to some heuristics (that can be optimized on training data) and then aligning the ground truth labelling with the predicted one. 6 pattern recognition models (including DTW, KDTW, HMM, HCRF and SVM) have been accordingly evaluated using this benchmark. It turns out that the regularized kernelized version of DTW measure (KDTW) associated to a SVM is quite efficient, comparatively to the other models, for detecting and recognizing continuous gestures in streams.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.