在本文中，我們提出一種與物件類別無關的物件可能性估計方法，能夠找到一副圖像中可能存在的物件的位置。為了實現這個目的，我們結合超級畫素與基於圖的分割兩種方法，高效地產生候選的一個物件區域集合，輔助後續物件偵測的工作。不僅使用分割演算法，我們還允許所有相鄰的超級畫素依據它們的相似程度彼此融合。然後，我們使用歸一化的邊界訊息來描述每一個物件位置的“明晰邊界”屬性，並利用一個提前訓練好的分類器來衡量這些位置的物件可能性。為了
發揮了窮舉搜索的優勢，同時又避免產生過多的重合度很高的物件位置，我們對我們方法的每一個步驟做了多樣化的操作，並使用非最大化抑制的方法減少產生的物件位置數量。完成這些工作後，我們能夠得到一個小且精的物件位置集合（在PASCAL VOC 2007的測試集上，實現77.4%的平均最優重合度（MABO）及94.4%召回率（DR））。通過結合不同的參數得到的結果，我們的方法的表現可以進一步提升，達到89.2%的MABO值和99.4%的DR 值。

In this thesis, we present a class-independent objectness estimation method searching possible object locations in one image. Towards this goal, we combine superpixels with graph-based segmentation to efficiently generate candidate regions for object detection. Beyond segmentation, our approach allows each of the hypotheses to iteratively merge with its neighboring superpixels based on their similarity. Then we use normed edge feature %which successfully reduces the noises of complex background's texture,to describe the close-boundary characteristics of the bounding box for each hypothesis and measure the associated objectness afterward by a pre-trained classifier. To utilize the advantage of exhaustive search and avoid generating too many high-overlap hypotheses, we diversify each step of our approach and apply non-maximal suppression(NMS) to refine the hypotheses. Thereafter, by using the proposed algorithm, we obtain a small set of high-quality hypothesized object locations(77.4% Mean Average Best Overlap(MABO) and 94.4% detection rate(DR) for all the objects in PASCAL VOC 2007 test set). By using the proposed strategies, the performance is increased to 89.2% MABO and 99.4% DR.

1
Introduction

2
Related Work
2.1
Saliency Detection
2.2
Objectness Measures
2.3
Object Detection

3
Proposed Algorithm
3.1
Graph Construction and Bottom-up Search
3.2
Normed Edge Feature and Top-down Objectness Estimation

4
Experimental Evaluation
4.1
High Concentration
4.2
High Overlap
4.3
High Computational Efficiency
4.4
Object Detection

5
Conclusion and Future Work

References

Achanta, R., Shaji, A., Smith, K., Lucchi, A., Fua, P., & Susstrunk, S. (2012). Slic superpixels compared to state-of-the-art superpixel methods. Pattern Analysis and
Machine Intelligence, IEEE Transactions on, 34(11), 2274–2282.
Alexe, B., Deselaers, T., & Ferrari, V. (2010). What is an object? In Computer vision and pattern recognition (cvpr), 2010 ieee conference on (pp. 73–80).
Alexe, B., Deselaers, T., & Ferrari, V. (2012). Measuring the objectness of image windows. Pattern Analysis and Machine Intelligence, IEEE Transactions on, 34(11),
2189–2202.
Branson, S., Beijbom, O., & Belongie, S. (2013). Efficient large-scale structured learning.
In Computer vision and pattern recognition (cvpr), 2013 ieee conference on (pp.1806–1813).
Bruce, N., & Tsotsos, J. (2006). Saliency based on information maximization. Advances
in neural information processing systems, 18, 155.
Carreira, J., & Sminchisescu, C. (2012). Cpmc: Automatic object segmentation using
constrained parametric min-cuts. Pattern Analysis and Machine Intelligence, IEEE
Transactions on, 34(7), 1312–1328.
Cheng, M.-M., Zhang, G.-X., Mitra, N. J., Huang, X., & Hu, S.-M. (2011). Global
contrast based salient region detection. In Computer vision and pattern recognition
(cvpr), 2011 ieee conference on (pp. 409–416).
Cheng, M.-M., Zhang, Z., Lin, W.-Y., & Torr, P. H. S. (2014). BING: Binarized normed
gradients for objectness estimation at 300fps.
In Computer vision and pattern
recognition (cvpr), 2014 ieee conference on.
Dalal, N., & Triggs, B. (2005). Histograms of oriented gradients for human detection. In
Computer vision and pattern recognition (cvpr), 2005 ieee conference on (Vol. 1,
pp. 886–893).
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (n.d.). Imagenet large
scale visual recognition competition 2012 (ilsvrc2012). http://http://www.image-
net.org/challenges/LSVRC/2012/.
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009). Imagenet: A
large-scale hierarchical image database. In Computer vision and pattern recognition
(cvpr), 2009 ieee conference on (pp. 248–255).
Dollár, P., & Zitnick, C. L. (2013). Structured forests for fast edge detection. In Computer
vision (iccv), 2011 ieee international conference on.
Duan, L., Wu, C., Miao, J., Qing, L., & Fu, Y. (2011). Visual saliency detection by
spatially weighted dissimilarity. In Computer vision and pattern recognition (cvpr),
2011 ieee conference on (pp. 473–480).
Endres, I., & Hoiem, D. (2010). Category independent object proposals. In Computer
vision (eccv), 2010 european conference on (pp. 575–588). Springer.
Endres, I., & Hoiem, D. (2014). Category-independent object proposals with diverse
ranking. Pattern Analysis and Machine Intelligence, IEEE Transactions on, 36(2),
222-234.
Everingham, M., Van Gool, L., Williams, C. K., Winn, J., & Zisserman, A. (2010).
The pascal visual object classes (voc) challenge. International journal of computer
vision, 88(2), 303–338.
Everingham, M., Van Gool, L., Williams, C. K. I., Winn, J., & Zisserman, A.
(n.d.). The PASCAL Visual Object Classes Challenge 2007 (VOC2007) Results.
http://www.pascal-network.org/challenges/VOC/voc2007/workshop/index.html.
Fan, R.-E., Chang, K.-W., Hsieh, C.-J., Wang, X.-R., & Lin, C.-J. (2008). Liblinear: A
library for large linear classification. The Journal of Machine Learning Research,
9, 1871–1874.
Fecteau, J. H., & Munoz, D. P. (2006). Salience, relevance, and firing: a priority map for
target selection. Trends in cognitive sciences, 10(8), 382–390.
Felzenszwalb, P. F., Girshick, R. B., McAllester, D., & Ramanan, D. (2010). Object
detection with discriminatively trained part-based models. Pattern Analysis and
Machine Intelligence, IEEE Transactions on, 32(9), 1627–1645.
Felzenszwalb, P. F., & Huttenlocher, D. P. (2004). Efficient graph-based image segmen-
tation. International Journal of Computer Vision, 59(2), 167–181.
Fidler, S., Mottaghi, R., Yuille, A., & Urtasun, R. (2013). Bottom-up segmentation for
top-down detection. In Computer vision and pattern recognition (cvpr), 2013 ieee
conference on (pp. 3294–3301).
Girshick, R., Donahue, J., Darrell, T., & Malik, J. (2014). Rich feature hierarchies
for accurate object detection and semantic segmentation. In Computer vision and
pattern recognition (cvpr), 2014 ieee conference on.
Hare, S., Saffari, A., & Torr, P. H. (2012). Efficient online structured output learning for
keypoint-based object tracking. In Computer vision and pattern recognition (cvpr),
2012 ieee conference on (pp. 1894–1901).
Hariharan, B., Malik, J., & Ramanan, D. (2012). Discriminative decorrelation for clus-
tering and classification. In Computer vision (eccv), 2012 european conference on
(pp. 459–472). Springer.
Itti, L., Koch, C., Niebur, E., et al. (1998). A model of saliency-based visual attention for
rapid scene analysis. Pattern Analysis and Machine Intelligence, IEEE Transactions
on, 20(11), 1254–1259.
Jia, Y.
(2013).
Caffe: An open source convolutional architecture for fast feature
embedding.
Lang, C., Nguyen, T. V., Katti, H., Yadati, K., Kankanhalli, M., & Yan, S. (2012). Depth
matters: Influence of depth cues on visual saliency. In Computer vision (eccv),
2012 european conference on (pp. 101–115). Springer.
Li, N., Ye, J., Ji, Y., Ling, H., & Yu, J. (2014). Saliency detection on light field. In
Computer vision and pattern recognition (cvpr), 2014 ieee conference on.
Li, X., Lu, H., Zhang, L., Ruan, X., & Yang, M.-H. (2013). Saliency detection via
dense and sparse reconstruction. In Computer vision (iccv), 2013 ieee international
conference on (pp. 2976–2983).
Mai, L., Niu, Y., & Liu, F. (2013). Saliency aggregation: A data-driven approach. In
Computervisionandpatternrecognition(cvpr), 2013ieeeconferenceon(pp.1131–
1138).
Maki, A., Nordlund, P., & Eklundh, J.-O. (2000). Attentional scene segmentation: in-
tegrating depth and motion. Computer Vision and Image Understanding, 78(3),
351–373.
Malisiewicz, T., Gupta, A., & Efros, A. A. (2011). Ensemble of exemplar-svms for
object detection and beyond. In Computer vision (iccv), 2011 ieee international
conference on (pp. 89–96).
Uijlings, J. R., van de Sande, K. E., Gevers, T., & Smeulders, A. W. (2013). Selective
search for object recognition. International journal of computer vision, 104(2),
154–171.
Valenti, R., Sebe, N., & Gevers, T. (2009). Image saliency by isocentric curvedness
and color. In Computer vision (iccv), 2009 ieee international conference on (pp.
2185–2192).
van de Sande, K. E., Uijlings, J. R., Gevers, T., & Smeulders, A. W. (2011). Segmentation
as selective search for object recognition. In Computer vision (iccv), 2011 ieee
international conference on (pp. 1879–1886).
Wei, Y., Wen, F., Zhu, W., & Sun, J. (2012). Geodesic saliency using background priors.
In Computer vision (eccv), 2012 european conference on (pp. 29–42). Springer.
Wertheim, A. (2010). Visual conspicuity: A new simple standard, its reliability, validity
and applicability. Ergonomics, 53(3), 421–442.
Yan, Q., Xu, L., Shi, J., & Jia, J. (2013). Hierarchical saliency detection. In Computer
vision and pattern recognition (cvpr), 2013 ieee conference on (pp. 1155–1162).
Yang, C., Zhang, L., Lu, H., Ruan, X., & Yang, M.-H. (2013). Saliency detection via
graph-based manifold ranking. In Computer vision and pattern recognition (cvpr),
2013 ieee conference on (pp. 3166–3173).
Zhang, Z., Warrell, J., & Torr, P. H. (2011). Proposal generation for object detection
using cascaded ranking svms. In Computer vision and pattern recognition (cvpr),
2011 ieee conference on (pp. 1497–1504).