A Model of Saliency-Based Visual Attention for Rapid Scene Analysis
IEEE Transactions on Pattern Analysis and Machine Intelligence
Advances in kernel methods: support vector learning
Advances in kernel methods: support vector learning
Unsupervised Segmentation of Color-Texture Regions in Images and Video
IEEE Transactions on Pattern Analysis and Machine Intelligence
Saliency, Scale and Image Description
International Journal of Computer Vision
A decision-theoretic generalization of on-line learning and an application to boosting
EuroCOLT '95 Proceedings of the Second European Conference on Computational Learning Theory
Attentional Selection for Object Recognition A Gentle Way
BMCV '02 Proceedings of the Second International Workshop on Biologically Motivated Computer Vision
Models of bottom-up and top-down visual attention
Models of bottom-up and top-down visual attention
Support Vector Machine with Weighted Summation Kernel Obtained by Adaboost
AVSS '06 Proceedings of the IEEE International Conference on Video and Signal Based Surveillance
Vehicular traffic density estimation via statistical methods with automated state learning
AVSS '07 Proceedings of the 2007 IEEE Conference on Advanced Video and Signal Based Surveillance
Hi-index | 0.00 |
Salient detection is one of the major interests with the computer vision research. Most of the existing object-detection work focuses on the efficiency and accuracy of detecting kinds of objects without attending the saliency of the objects. In this paper, we apply salient features in a traditional object detection process with an algorithm combining both bottom-up and top-down approaches, aiming to detect meaningful objects exhibiting saliency. We define salient region as distinct areas detected in an image in a bottom-up phase, and the salient feature as semantic features in representing an object in the top-down phase where we apply a boosting algorithm to accommodate kinds of classifiers including Support Vector Machine (SVM) and an enhanced Adaboost classifiers. Final experiments indicate that our proposed object detector is fairly effective compared with the state of the art.