International Journal of Computer Vision - Special issue on statistical and computational theories of vision: Part II
Histograms of Oriented Gradients for Human Detection
CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 1 - Volume 01
Probability and Computing: Randomized Algorithms and Probabilistic Analysis
Probability and Computing: Randomized Algorithms and Probabilistic Analysis
Object Detection with Discriminatively Trained Part-Based Models
IEEE Transactions on Pattern Analysis and Machine Intelligence
Cascaded models for articulated pose estimation
ECCV'10 Proceedings of the 11th European conference on Computer vision: Part II
A coarse-to-fine approach for fast deformable object detection
CVPR '11 Proceedings of the 2011 IEEE Conference on Computer Vision and Pattern Recognition
Sparse kernel approximations for efficient classification and detection
CVPR '12 Proceedings of the 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Hi-index | 0.00 |
Computing part scores is the main computational bottleneck in object detection with Deformable Part Models. In this work we introduce an efficient method to obtain bounds on part scores, which we then integrate with deformable model detection. As in [1] we rapidly approximate the inner product between a weight vector and HOG-based features by quantizing the HOG cells onto a codebook and replace their inner product with the lookup of a precomputed score. The novelty in our work consists in combining this lookup-based estimate with the codebook quantization error so as to construct probabilistic bounds to the exact inner product. In particular we use Chebyshev's inequality to obtain probably correct bounds for the inner product at each image location. We integrate these bounds with both the Dual-Tree Branch-and-Bound work of [2,3] and the Cascade-DPMs of [4]; in both cases the bounds are used in a first phase to conservatively construct a short-list of locations, for which the exact inner products are subsequently evaluated. We quantitatively evaluate our method and demonstrate that it allows for approximately a twofold speedup over both [2] and [4] with negligible loss in accuracy.