Abstract | ||
---|---|---|
To design a good human detector, we may collect a huge number of data, and train the detector off-line. However, even if the training data set is very large, it may not contain enough information for some particular environment, and the obtained model may not work well. In this paper, we study incremental learning of a support vector machine-based human detector in an office environment, and investigate the "growth process" of the detector. Experimental results show that it is possible to obtain a good human detector customized to a certain environment with less data via incremental learning. |
Year | DOI | Venue |
---|---|---|
2017 | 10.1109/MCSoC.2017.25 | 2017 IEEE 11th International Symposium on Embedded Multicore/Many-core Systems-on-Chip (MCSoC) |
Keywords | Field | DocType |
human detection,support vector machine,incremental learning | Training set,Histogram,Pattern recognition,Computer science,Incremental learning,Support vector machine,Feature extraction,Artificial intelligence,Detector | Conference |
ISBN | Citations | PageRank |
978-1-5386-3442-4 | 1 | 0.38 |
References | Authors | |
0 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Tatsuya Hanyu | 1 | 1 | 0.72 |
Qiangfu Zhao | 2 | 214 | 62.36 |