Learning Sampling Distributions for Efficient Object Detection

@article{Pang2017LearningSD,
  title={Learning Sampling Distributions for Efficient Object Detection},
  author={Yanwei Pang and Jiale Cao and Xuelong Li},
  journal={IEEE Transactions on Cybernetics},
  year={2017},
  volume={47},
  pages={117-129}
}
Object detection is an important task in computer vision and machine intelligence systems. Multistage particle windows (MPW), proposed by Gualdi et al., is an algorithm of fast and accurate object detection. By sampling particle windows (PWs) from a proposal distribution (PD), MPW avoids exhaustively scanning the image. Despite its success, it is unknown how to determine the number of stages and the number of PWs in each stage. Moreover, it has to generate too many PWs in the initialization… Expand
Interactive Hierarchical Object Proposals
TLDR
An architecture to integrate human interaction with the global information of the whole image for objectness scoring is explored and designed, which is able to significantly improve the performance with a minimum number of object proposals. Expand
Object Discovery via Cohesion Measurement
TLDR
The affinity matrices originally used in image segmentation methods based on spectral clustering are reinvestigate and a novel object discovery method is proposed to discover objects latent in an image by utilizing the eigenvectors of the affinity matrix. Expand
Cascade Learning by Optimally Partitioning
TLDR
An optimal cascade learning algorithm (iCascade) which iteratively partitions the strong classifiers into two parts until predefined number of stages are generated and proves in theory why more new weak classifiers in the current stage are required compared to that of the previous stage. Expand
CLASS: Collaborative Low-Rank and Sparse Separation for Moving Object Detection
TLDR
The extensive experiments on both public and newly created video sequences suggest that CLASS achieves superior performance and comparable efficiency against other state-of-the-art approaches. Expand
Robust and Efficient Corner Detector Using Non-Corners Exclusion
TLDR
A robust and efficient corner detector (RECD) improved from Harris corner detector is proposed, using the principle of the feature from accelerated segment test (FAST) algorithm for corner pre-detection in order to rule out non-corners and retain many strong corners as real corners. Expand
Efficient Outlier Detection for High-Dimensional Data
TLDR
This work proposes an efficient and effective outlier detection algorithm, which is also robust to the parameter ${k}$ of nearest neighbors, and introduces a concept called local projection score (LPS) to represent deviation degree of an observation to its neighbors. Expand
Towards Real-Time Accurate Object Detection in Both Images and Videos Based on Dual Refinement
TLDR
A dual refinement network (DRN) is developed for high-performance static detection, where a multi-deformable head is further designed to leverage contextual information for describing objects to achieve significantly enhanced detection accuracy. Expand
Dual Refinement Networks for Accurate and Fast Object Detection in Real-World Scenes
TLDR
A novel anchor-offset detection including an anchor refinement, a feature offset refinement, and a deformable detection head is designed for two-step regression and capture of accurate detection features in static and temporal scenes in real time. Expand
FPGA based Object Detection using Background Subtraction and Variable Threshold Technique
Visual surveillance plays a vital role in last few years, because of the increasing need for security Object detection is mainly used in surveillance purpose and computer vision systems and is anExpand
A Comparative Study and State-of-the-art Evaluation for Pedestrian Detection
TLDR
An overview of the state-of-the-art performance of current deep learning pedestrian detectors and a comparison of these detectors is provided and Evaluation criteria, popular datasets used for evaluation and a quantitative results are described. Expand
...
1
2
3
4
...

References

SHOWING 1-10 OF 51 REFERENCES
Multistage Particle Windows for Fast and Accurate Object Detection
TLDR
This work proposes a paradigm that casts object detection into a statistical-based search using a Monte Carlo sampling for estimating the likelihood density function with Gaussian kernels and demonstrates that the proposed method provides higher detection rates and accuracy as well as a lower computational burden. Expand
Selective Search for Object Recognition
TLDR
This paper introduces selective search which combines the strength of both an exhaustive search and segmentation, and shows that its selective search enables the use of the powerful Bag-of-Words model for recognition. Expand
Edge Boxes: Locating Object Proposals from Edges
TLDR
A novel method for generating object bounding box proposals using edges is proposed, showing results that are significantly more accurate than the current state-of-the-art while being faster to compute. Expand
Efficient Subwindow Search: A Branch and Bound Framework for Object Localization
TLDR
A simple yet powerful branch and bound scheme that allows efficient maximization of a large class of quality functions over all possible subimages and converges to a globally optimal solution typically in linear or even sublinear time, in contrast to the quadratic scaling of exhaustive or sliding window search. Expand
Real-time Accurate Object Detection using Multiple Resolutions
  • Wei Zhang, G. Zelinsky, D. Samaras
  • Computer Science
  • 2007 IEEE 11th International Conference on Computer Vision
  • 2007
TLDR
This work proposes a multi-resolution framework inspired by human visual search for general object detection that produced better performance for pedestrian detection than state-of-the-art methods, and was faster during both training and testing. Expand
Distributed Object Detection With Linear SVMs
TLDR
This paper develops a distributed object detection framework (DOD) by making the best use of spatial-temporal correlation, and develops CHOG-DOD as an instance of DOD framework, a cell-based HOG (CHOG) algorithm, where the features in one cell are not shared with overlapping blocks. Expand
Fast PRISM: Branch and Bound Hough Transform for Object Class Detection
TLDR
This paper addresses the task of efficient object class detection by means of the Hough transform by demonstrating PRISM’s flexibility by two complementary implementations: a generatively trained Gaussian Mixture Model as well as a discriminatively trained histogram approach. Expand
Robust Object Detection with Interleaved Categorization and Segmentation
TLDR
A novel method for detecting and localizing objects of a visual category in cluttered real-world scenes that is applicable to a range of different object categories, including both rigid and articulated objects and able to achieve competitive object detection performance from training sets that are between one and two orders of magnitude smaller than those used in comparable systems. Expand
Fast Feature Pyramids for Object Detection
TLDR
For a broad family of features, this work finds that features computed at octave-spaced scale intervals are sufficient to approximate features on a finely-sampled pyramid, and this approximation yields considerable speedups with negligible loss in detection accuracy. Expand
Branch&Rank for Efficient Object Detection
TLDR
A novel aspect of branch&rank is that a better ranking function is expected to decrease the number of classifier calls during detection, and this efficiency enables the use of strong and also costly classifiers like non-linear SVMs with RBF-$$\chi ^2$$χ2 kernels. Expand
...
1
2
3
4
5
...