Abstract | ||
---|---|---|
In this paper, we investigated the deep learning model for object classification. Robust classification networks were trained based on Deep Belief Networks (DBN) combined with several object representations included image pixel value, feature histogram by Histogram of Oriented Gradients (HOG) operator and eigen-features to distinguish four categories: pedestrian, biker, vehicle and others in the real scene. In addition, an image dataset called NUPTERC, in which the sample images collected from real surveillance video and Internet, was built to test the proposed methods. Experiments based on NUPTERC dataset demonstrated that the proposed deep learning architecture could achieve superior person vehicle classification performance under illumination changes, large pose variations and different resolution. |
Year | DOI | Venue |
---|---|---|
2014 | 10.1109/ICNC.2014.6975819 | ICNC |
Keywords | Field | DocType |
pedestrians,belief networks,robust classification networks,image representation,object classification,image pixel value,real surveillance video,nupterc dataset,dbn,object representations,feature histogram,deep belief networks,feature extraction,image classification,internet,person-vehicle classification,histogram of oriented gradients operator,video surveillance | Computer science,Deep belief network,Artificial intelligence,Contextual image classification,Machine learning | Conference |
ISSN | Citations | PageRank |
2469-8814 | 1 | 0.65 |
References | Authors | |
7 | 5 |