Name
Abstract | ||
|---|---|---|
We propose a deep discriminative appearance model (DDAM) based on convolutional neural network (CNN) for pedestrians. The training stage of our supervised D-DAM model does not depend on a large amount of data. In our model, we introduce a progressive batch refinement technique to fine tune the CNN for modeling the appearance of the pedestrian. After fine-tuning, the model achieves 98% accuracy for pedestrian and non-pedestrian classification. Moreover, we also introduce a novel discrimination index (DI) for evaluating the spatio-temporal discrimination effectiveness of both hand-crafted and deep features. We perform experiments on pre-trained CNN model, our D-DAM model, and 3 baseline hand-crafted features including HoG, LBP, and Color histogram. The results show that our D-DAM model achieves higher classification accuracy and better spatio-temporal discrimination ability compared to all the hand-crafted features. |
Year | DOI | Venue |
|---|---|---|
2018 | 10.1109/CVCS.2018.8496556 | 2018 Colour and Visual Computing Symposium (CVCS) |
Keywords | Field | DocType |
Convolutional neural network,appearance model,discrimination index,hand-crafted feature | Pedestrian,Color histogram,Pattern recognition,Convolutional neural network,Computer science,Active appearance model,Artificial intelligence,Discriminative model | Conference |
ISBN | Citations | PageRank |
978-1-5386-5646-4 | 0 | 0.34 |
References | Authors | |
10 | 3 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Mohib Ullah | 1 | 22 | 8.82 |
| Ahmed Kedir Mohammed | 2 | 4 | 1.75 |
| Faouzi Alaya Cheikh | 3 | 168 | 38.47 |