Free-shape subwindow search for object localization

Zhang, Zhiqi; Cao, Yu; Salvi, Dhaval; Oliver, Kenton; Waggoner, Jarrell; Wang, Song

doi:10.1109/cvpr.2010.5540095

Cited by 17 publications

(39 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As seen in our experiments, our approach significantly outperforms recent polygonal and free-shape object detection methods [47,43].…”

Section: Introductionsupporting

confidence: 51%

“…Delineating polygonal regions is then accomplished by finding those cycles that minimize an appropriate objective function. Even though the number of potential cycles can grow very large even in moderately-sized graphs, this can be done efficiently when the objective function can be written as a sum of terms, one for each edge of the cycle [45,47]. However, this is limiting because using more complex non-linear…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Free-Shape Polygonal Object Localization

Sun¹,

Christoudias²,

Fua³

2014

Computer Vision – ECCV 2014

View full text Add to dashboard Cite

Abstract. Polygonal objects are prevalent in man-made scenes. Early approaches to detecting them relied mainly on geometry while subsequent ones also incorporated appearance-based cues. It has recently been shown that this could be done fast by searching for cycles in graphs of line-fragments, provided that the cycle scoring function can be expressed as additive terms attached to individual fragments. In this paper, we propose an approach that eliminates this restriction. Given a weighted linefragment graph, we use its cyclomatic number to partition the graph into managebly-sized sub-graphs that preserve nodes and edges with a high weight and are most likely to contain object contours. Object contours are then detected as maximally scoring elementary circuits enumerated in each sub-graph. Our approach can be used with any cycle scoring function and multiple candidates that share line fragments can be found. This is unlike in other approaches that rely on a greedy approach to finding candidates. We demonstrate that our approach significantly outperforms the state-of-the-art for the detection of building rooftops in aerial images and polygonal object categories from ImageNet.

show abstract

“…As seen in our experiments, our approach significantly outperforms recent polygonal and free-shape object detection methods [47,43].…”

Section: Introductionsupporting

confidence: 51%

Section: Introductionmentioning

confidence: 99%

Free-Shape Polygonal Object Localization

Sun¹,

Christoudias²,

Fua³

2014

Computer Vision – ECCV 2014

View full text Add to dashboard Cite

show abstract

“…Therefore, we search for n c (set to 3 in our implementation) contours. After getting one optimal contour, we simply set the saliency value inside of it to zero instead of removing corresponding segments like [30]. Then we re-run the ratio contour algorithm.…”

Section: Shape Prior Extractionmentioning

confidence: 99%

“…Note that computed optimal contour is actually a polygon. Since we prefer pixel-wise segmentation, unlike [30] which straightly outputs the optimal contour, we choose to integrate shape prior into the energy minimization framework for binary salient object segmentation (section 3). See sample images in Fig.…”

Section: Shape Prior Extractionmentioning

confidence: 99%

See 1 more Smart Citation

Automatic salient object segmentation based on context and shape prior

Jiang¹,

Wang²,

Yuan³

et al. 2011

Procedings of the British Machine Vision Conference 2011

398

333

View full text Add to dashboard Cite

We propose a novel automatic salient object segmentation algorithm which integrates both bottom-up salient stimuli and object-level shape prior, i.e., a salient object has a well-defined closed boundary. Our approach is formalized as an iterative energy minimization framework, leading to binary segmentation of the salient object. Such energy minimization is initialized with a saliency map which is computed through context analysis based on multi-scale superpixels. Object-level shape prior is then extracted combining saliency with object boundary information. Both saliency map and shape prior update after each iteration. Experimental results on two public benchmark datasets show that our proposed approach outperforms state-of-the-art methods.

show abstract