Multi-object detection via joint saliency, sparseness, locality and depth

被引：0

作者：

Xiao, Degui ^{[1
]}

Zhang, Ting ^{[1
]}

Cao, Yu ^{[2
]}

机构：

[1] College of Computer Science and Electronic Engineering, Hunan University, Changsha

[2] Department of Computer Science, University of Massachusetts Lowell, Lowell, MA

来源：

Journal of Computational Information Systems | 2015年 / 11卷 / 16期

基金：

中国国家自然科学基金;

关键词：

Deep learning; Object detection; Saliency;

D O I：

10.12733/jcis14976

中图分类号：

学科分类号：

摘要：

Compared with traditional methods for object detection focusing on single human brain mechanism, this paper proposes a method for multi-object detection by combining human brain multi-mechanism, which imitates the process of human brain dealing with information and is much close to artificial intelligence. The multi-mechanism including saliency, sparseness, locality and depth, is used to represent object-level feature. The saliency is extracted to get rough object region, and a deep model combines non-negative sparse coding, non-negative locality-constraint linear coding, salient pooling and local grouping to obtain abstract features expression. Finally, features use LibSVM to multi-object detection. Compared with state-of-the-art object detection methods, the proposed method shows better results. © 2015 by Binary Information Press

引用

页码：5865 / 5872

页数：7

共 13 条

[1]

Liu Z., Huang K., Tan T., Foreground Object Detection Using Top-Down Information Based on EM Framework, IEEE Transactions on Image Processing, 21, 9, pp. 4204-4217, (2012)

[2]

Xiao D., Zhu H., Liu L., Vision information fusion algorithm for road detection based on DS evidence theory, Journal of Computational Information Systems, 9, 21, pp. 8531-8540, (2013)

[3]

Fang Y., Lin W., Lau C.T., Lee B.-S., A visual attention model combining top-down and bottom-up mechanisms for salient object detection, IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), (2011)

[4]

Han J., Sun L., Zhang D., Hu X., Cheng G., Guo L., Visual attention computation in video of driving environment, IEEE International Conference on Multimedia and Expo (ICME), pp. 1-6, (2014)

[5]

Wang J., Yang J., Yu K., Lv F., Huang T., Gong Y., Locality-constrained Linear Coding for image classification, CVPR, pp. 3360-3367, (2010)

[6]

Girshick R., Donahue J., Darrell T., Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation, CVPR, pp. 580-587, (2014)

[7]

Yang J., Yang M.-H., Learning Hierarchical Image Representation with Sparsity, Saliency and Locality, Proc. BMVC, pp. 1-11, (2011)

[8]

Grandinetti L., Lippert T., Brain-Inspired Computing, (2013)

[9]

Alexe B., Deselaers T., Ferrari V., Measuring the Objectness of Image Windows, IEEE Transactions on Pattern Analysis and Machine Intelligence, 34, 11, pp. 2189-2202, (2012)

[10]

Zhang C., Liu J., Tian Q., Xu C., Image classification by non-negative sparse coding, low-rank and sparse decomposition, CVPR, pp. 1673-1680, (2011)

← 1 2 →