Abstract | ||
---|---|---|
We propose an automatic approach to detect falls in home environment. A Support Vector Machine based classifier is fed by a set of selected features extracted from human body silhouette tracking. The classifier is followed by filtering operations taking into account the temporal nature of a video. The features are based on height and width of human body bounding box, the user's trajectory with her/his orientation, Projection Histograms and moments of order 0, 1 and 2. We study several combinations of usual transformations of the features (Fourier Transform, Wavelet transform, first and second derivatives), and we show experimentally that it is possible to achieve high performance using a single camera.We evaluated the robustness of our method using a realistic dataset. Experiments show that the best tradeoff between classification performance and time processing result is obtained combining the original data with their first derivative. The global error rate is lower than 1%, and the recall, specificity and precision are high (respectively 0.98, 0.996 and 0.942). The resulting system can therefore be used in a real environment. Hence, we also evaluated the robustness of our system regarding location changes. We proposed a realistic and pragmatic protocol which enables performance to be improved by updating the training in the current location, with normal activities records. |
Year | DOI | Venue |
---|---|---|
2012 | 10.1109/SITIS.2012.155 | Signal Image Technology and Internet Based Systems |
Keywords | Field | DocType |
human body silhouette tracking,robust svm,resulting system,performance evaluation,real environment,fall detection solution,high performance,realistic dataset,current location,human body,location change,classification performance,home environment,feature extraction,wavelet transforms,support vector machines,fourier transforms | Computer vision,Pattern recognition,Computer science,Support vector machine,Robustness (computer science),Feature extraction,Artificial intelligence,Discrete wavelet transform,Margin classifier,Wavelet transform,Minimum bounding box,Wavelet | Conference |
ISBN | Citations | PageRank |
978-1-4673-5152-2 | 22 | 0.80 |
References | Authors | |
6 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Imen Charfi | 1 | 55 | 3.24 |
Johel Miteran | 2 | 80 | 7.94 |
Julien Dubois | 3 | 146 | 18.76 |
Mohamed Atri | 4 | 154 | 27.75 |
Rached Tourki | 5 | 144 | 25.21 |