2014 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2014)
Columbus, OH, USA
June 23, 2014 to June 28, 2014
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/CVPR.2014.29
In this work we propose a technique to combine bottom-up segmentation, coming in the form of SLIC superpixels, with sliding window detectors, such as Deformable Part Models (DPMs). The merit of our approach lies in "cleaning up" the low-level HOG features by exploiting the spatial support of SLIC superpixels, this can be understood as using segmentation to split the feature variation into object-specific and background changes. Rather than committing to a single segmentation we use a large pool of SLIC superpixels and combine them in a scale-, position- and object-dependent manner to build soft segmentation masks. The segmentation masks can be computed fast enough to repeat this process over every candidate window, during training and detection, for both the root and part filters of DPMs. We use these masks to construct enhanced, background-invariant features to train DPMs. We test our approach on the PASCAL VOC 2007, outperforming the standard DPM in 17 out of 20 classes, yielding an average increase of 1.7% AP. Additionally, we demonstrate the robustness of this approach, extending it to dense SIFT descriptors for large displacement optical flow.
Image segmentation, Object detection, Standards, Feature extraction, Computational modeling, Deformable models, Semantics
E. Trulls, S. Tsogkas, I. Kokkinos, A. Sanfeliu and F. Moreno-Noguer, "Segmentation-Aware Deformable Part Models," 2014 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Columbus, OH, USA, 2014, pp. 168-175.