Open Access Open Access  Restricted Access Subscription or Fee Access

Object Detection with Improved Shape Context Features

Jayakrishna Sunkara, L. Ramasubba Reddy, L. Rajyalakshmi, K. Anitha, K. Santhipriya, M. Prathapreddy

Abstract


We presented a new approach for detecting objects by
combining top-down recognition with improved shape context
features and bottom-up segmentation.There are two main steps in this method:hypothesis generation step and verification step.In hypothesis generation step we use top-down recognition with improved shape context features and in verification step we use bottom-up segmentation. Our improved shape context features are more robust to
object deformation and background clutter. The shape context is used to generate a set of hypothesis of object location and figure ground mask, which have high recall and low precision rate.In the verification step, we first compute a set of feasible segmentation that are consistent with top-down object hypothesis, then we propose a false positive pruning procedure to prune out false positives. We found the fact that
false positive regions typically do not align with any feasible imagesegmentation.From our experiment we show that this simple framework achieve both high recall and high precision with only a few positive training examples and this method can be generalized to many object classes.


Keywords


Shape Context, Hypothesis, False Positive Prunings

Full Text:

PDF

References


Viola, P.A., Jones, M.J.: Rapid object detection using a boosted cascade

of simple features. In: CVPR. (2001).

Borenstein, E., Ullman, S.: Class-specific, top-down segmentation. In:

ECCV (2). (2002).

Levin, A., Weiss, Y.: Learning to combine bottom-up and top-down

segmentation. In: ECCV. (2006).

Leibe, B., Seemann, E., Schiele, B.: Pedestrian detection in crowded

scenes. In: CVPR. (2005).

Ferrari, V., Tuytelaars, T., Gool, L.J.V.: Object detection by contour

segment networks. In: ECCV. (2006).

Kokkinos, I., Maragos, P., Yuille, A.L.: Bottom-up & top-down object

Detection using primal sketch features and graphical models. In: CVPR.

(2006).

Zhao, L., Davis, L.S.: Closely coupled object detection and segmentation.

In: ICCV. (2005).

Ren, X., Berg, A.C., Malik, J.: Recovering human body configurations

using pair wise constraints between parts. In: ICCV. (2005).

Mori, G., Ren, X., Efros, A.A., Malik, J.: Recovering human body

configurations: Combining segmentation and recognition. In: CVPR

(2004).

Srinivasan, P., Shi, J.: Bottom-up recognition and parsing of the human

body. In: CVPR. (2007).

Felzenszwalb, P.F., Huttenlocher, D.P.: Pictorial structures for object

recognition. International Journal of Computer Vision 61(1) (2005).

Dalal, N., Triggs, B.: Histograms of oriented gradients for human

detection. In: CVPR. (2005).

Belongie, S.,Malik, J., Puzicha, J.: Shape matching and object recognition

using shape contexts. IEEE Trans. Pattern Anal Mach.Intell. 24(4) (2002).

Mori, G., Belongie, S.J., Malik, J.: Efficient shape matching using

contexts. Trans. Pattern Anal Mach. Intell. 27(11) (2005).

Thayananthan, A., Stenger, B., Torr, P.H.S., Cipolla, R.: Shape context

and chamfer in cluttered scenes. In: CVPR (2003).

Rubner, Y., Tomasi, C., Guibas, L.J.: A metric for distributions with

applications to image databases. In: ICCV. (1998).

Ramanan, D.: Using segmentation to verify object hypotheses. In: CVPR.

(2007).

Shi, J., Malik, J.: Normalized cuts and image segmentation. In: CVPR.

(1997).


Refbacks

  • There are currently no refbacks.


Creative Commons License
This work is licensed under a Creative Commons Attribution 3.0 License.