Abstract | ||
---|---|---|
This paper introduces principal motion components (PMC), a new method for one-shot gesture recognition. In the considered scenario a single training video is available for each gesture to be recognized, which limits the application of traditional techniques (e.g., HMMs). In PMC, a 2D map of motion energy is obtained per each pair of consecutive frames in a video. Motion maps associated to a video are processed to obtain a PCA model, which is used for recognition under a reconstruction-error approach. The main benefits of the proposed approach are its simplicity, easiness of implementation, competitive performance and efficiency. We report experimental results in one-shot gesture recognition using the ChaLearn Gesture Dataset; a benchmark comprising more than 50,000 gestures, recorded as both RGB and depth video with a Kinectcamera. Results obtained with PMC are competitive with alternative methods proposed for the same data set. |
Year | DOI | Venue |
---|---|---|
2017 | 10.1007/s10044-015-0481-3 | Pattern Anal. Appl. |
Keywords | Field | DocType |
gesture recognition,pca | Computer vision,Gesture,Computer science,Gesture recognition,Speech recognition,Artificial intelligence,RGB color model,One-shot learning | Journal |
Volume | Issue | ISSN |
20 | 1 | 1433-755X |
Citations | PageRank | References |
11 | 0.60 | 33 |
Authors | ||
5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Hugo Jair Escalante | 1 | 939 | 73.89 |
Isabelle Guyon | 2 | 11033 | 1544.34 |
Vassilis Athitsos | 3 | 1908 | 126.48 |
Pat Jangyodsuk | 4 | 140 | 6.64 |
Jun Wan | 5 | 255 | 22.37 |