The Experts below are selected from a list of 60 Experts worldwide ranked by ideXlab platform
Zhen Lei - One of the best experts on this subject based on the ideXlab platform.
-
aggregate Channel features for multi view face detection
International Journal of Central Banking, 2014Co-Authors: Bin Yang, Junjie Yan, Zhen LeiAbstract:Face detection has drawn much attention in recent decades since the seminal work by Viola and Jones. While many subsequences have improved the work with more powerful learning algorithms, the feature representation used for face detection still can’t meet the demand for effectively and efficiently handling faces with large appearance variance in the wild. To solve this bottleneck, we borrow the concept of Channel features to the face detection domain, which extends the Image Channel to diverse types like gradient magnitude and oriented gradient histograms and therefore encodes rich information in a simple form. We adopt a novel variant called aggregate Channel features, make a full exploration of feature design, and discover a multiscale version of features with better performance. To deal with poses of faces in the wild, we propose a multi-view detection approach featuring score re-ranking and detection adjustment. Following the learning pipelines in ViolaJones framework, the multi-view face detector using aggregate Channel features surpasses current state-of-the-art detectors on AFW and FDDB testsets, while runs at 42 FPS
-
aggregate Channel features for multi view face detection
arXiv: Computer Vision and Pattern Recognition, 2014Co-Authors: Bin Yang, Junjie Yan, Zhen LeiAbstract:Face detection has drawn much attention in recent decades since the seminal work by Viola and Jones. While many subsequences have improved the work with more powerful learning algorithms, the feature representation used for face detection still can't meet the demand for effectively and efficiently handling faces with large appearance variance in the wild. To solve this bottleneck, we borrow the concept of Channel features to the face detection domain, which extends the Image Channel to diverse types like gradient magnitude and oriented gradient histograms and therefore encodes rich information in a simple form. We adopt a novel variant called aggregate Channel features, make a full exploration of feature design, and discover a multi-scale version of features with better performance. To deal with poses of faces in the wild, we propose a multi-view detection approach featuring score re-ranking and detection adjustment. Following the learning pipelines in Viola-Jones framework, the multi-view face detector using aggregate Channel features shows competitive performance against state-of-the-art algorithms on AFW and FDDB testsets, while runs at 42 FPS on VGA Images.
Markku Renfors - One of the best experts on this subject based on the ideXlab platform.
-
energy detection under iq imbalance with single and multi Channel direct conversion receiver analysis and mitigation
IEEE Journal on Selected Areas in Communications, 2014Co-Authors: Ahmet Gokceoglu, Sener Dikmese, Mikko Valkama, Markku RenforsAbstract:Direct-conversion radio receivers can offer highly integrated low-cost hardware solutions for cognitive radio (CR) devices. Such receivers are, however, also very sensitive to various radio frequency (RF) impairments such as IQ imbalance, which can considerably limit the spectrum sensing capabilities. Most of the existing spectrum sensing studies in literature assume an ideal RF receiver and hence neglect the impacts of such practical RF hardware limitations. In this article, we study energy detection (ED) based spectrum sensing in both single-Channel and multi-Channel direct-conversion receiver scenarios impaired by IQ imbalance. With complex Gaussian primary user (PU) signal models, we first derive the detection and false alarm probabilities in closed-form for both receiver scenarios. The analytical results, confirmed through extensive simulations, show that while the single-Channel receiver scenario is fairly robust to IQ imbalance, the wideband multi-Channel sensing receiver is very sensitive to the Image Channel crosstalk induced by IQ imbalance. More specifically, it is shown that the false alarm probability of multi-Channel energy detection increases significantly, compared to ideal RF receiver case, and the exact performance depends on the Image Channel power level and IQ imbalance values. In order to prevent such degradation in the ability to identify free spectrum, a waveform level interference cancellation method is then proposed to mitigate the Image Channel crosstalk. The optimum cancellation coefficient yielding interference-free signal is first derived, being also complemented with a practical coefficient sample estimator. An explicit condition is also derived for which the proposed cancellation scheme deploying the practical coefficient sample estimator provides performance gain in the sensing decisions compared to uncompensated energy detection. Extensive computer simulations with various signal and imbalance conditions are provided which demonstrate that the proposed enhanced energy detection can suppress the Image Channel crosstalk efficiently, yielding detection and false alarm probabilities essentially identical to those of an ideal RF receiver.
Haibin Ling - One of the best experts on this subject based on the ideXlab platform.
-
A novel pixel neighborhood differential statistic feature for pedestrian and face detection
Pattern Recognition, 2017Co-Authors: Jifeng Shen, Wankou Yang, Jun Li, Xin Zuo, Haibin LingAbstract:Motivated by the successful application of Local Binary Pattern (LBP), in this paper we propose a novel pixel neighborhood differential statistic feature for pedestrian and face detection based on the multiple Channel maps. The calculation of LBP comprises of two steps, Pixel Differential Feature (PDF) calculation and PDF sign encoding. The PDF distills discriminative information of local region that can improve the performance of the pedestrian detector, but the encoding step degrades the performance due to the quantization error. Although PDF is more discriminative than original Channel maps, it has a much higher dimension than the original feature maps, and consequently requiring large computation cost. To address this issue, the pixel neighborhood differential pattern is learned with both supervised and unsupervised learning methods, which allow discovering discriminative pixel differential patterns in local area and achieving state-of-the-art results. Specifically, our method firstly aggregates the Image Channel maps into cell maps with max pooling. Then, pixel neighborhood differential feature based on each Channel cell maps are calculated which contributes to encoding discriminative information in each local area and benefits the performance improvements. In addition, we attempt to learn discriminative differential statistic patterns by using linear discriminative analysis (LDA) and principle component analysis (PCA) for further performance improvement. Two sets of experiments are conducted on pedestrian detection and face detection respectively. The INRIA, Caltech, and ETH datasets are used for pedestrian detection, and the FDDB and AFW datasets for multi-view face detection. The experimental results show that our method achieves superior performance in comparison with the state-of-the-arts while running at 20 fps for 480×640 Images.
Bin Yang - One of the best experts on this subject based on the ideXlab platform.
-
aggregate Channel features for multi view face detection
International Journal of Central Banking, 2014Co-Authors: Bin Yang, Junjie Yan, Zhen LeiAbstract:Face detection has drawn much attention in recent decades since the seminal work by Viola and Jones. While many subsequences have improved the work with more powerful learning algorithms, the feature representation used for face detection still can’t meet the demand for effectively and efficiently handling faces with large appearance variance in the wild. To solve this bottleneck, we borrow the concept of Channel features to the face detection domain, which extends the Image Channel to diverse types like gradient magnitude and oriented gradient histograms and therefore encodes rich information in a simple form. We adopt a novel variant called aggregate Channel features, make a full exploration of feature design, and discover a multiscale version of features with better performance. To deal with poses of faces in the wild, we propose a multi-view detection approach featuring score re-ranking and detection adjustment. Following the learning pipelines in ViolaJones framework, the multi-view face detector using aggregate Channel features surpasses current state-of-the-art detectors on AFW and FDDB testsets, while runs at 42 FPS
-
aggregate Channel features for multi view face detection
arXiv: Computer Vision and Pattern Recognition, 2014Co-Authors: Bin Yang, Junjie Yan, Zhen LeiAbstract:Face detection has drawn much attention in recent decades since the seminal work by Viola and Jones. While many subsequences have improved the work with more powerful learning algorithms, the feature representation used for face detection still can't meet the demand for effectively and efficiently handling faces with large appearance variance in the wild. To solve this bottleneck, we borrow the concept of Channel features to the face detection domain, which extends the Image Channel to diverse types like gradient magnitude and oriented gradient histograms and therefore encodes rich information in a simple form. We adopt a novel variant called aggregate Channel features, make a full exploration of feature design, and discover a multi-scale version of features with better performance. To deal with poses of faces in the wild, we propose a multi-view detection approach featuring score re-ranking and detection adjustment. Following the learning pipelines in Viola-Jones framework, the multi-view face detector using aggregate Channel features shows competitive performance against state-of-the-art algorithms on AFW and FDDB testsets, while runs at 42 FPS on VGA Images.
Junjie Yan - One of the best experts on this subject based on the ideXlab platform.
-
aggregate Channel features for multi view face detection
International Journal of Central Banking, 2014Co-Authors: Bin Yang, Junjie Yan, Zhen LeiAbstract:Face detection has drawn much attention in recent decades since the seminal work by Viola and Jones. While many subsequences have improved the work with more powerful learning algorithms, the feature representation used for face detection still can’t meet the demand for effectively and efficiently handling faces with large appearance variance in the wild. To solve this bottleneck, we borrow the concept of Channel features to the face detection domain, which extends the Image Channel to diverse types like gradient magnitude and oriented gradient histograms and therefore encodes rich information in a simple form. We adopt a novel variant called aggregate Channel features, make a full exploration of feature design, and discover a multiscale version of features with better performance. To deal with poses of faces in the wild, we propose a multi-view detection approach featuring score re-ranking and detection adjustment. Following the learning pipelines in ViolaJones framework, the multi-view face detector using aggregate Channel features surpasses current state-of-the-art detectors on AFW and FDDB testsets, while runs at 42 FPS
-
aggregate Channel features for multi view face detection
arXiv: Computer Vision and Pattern Recognition, 2014Co-Authors: Bin Yang, Junjie Yan, Zhen LeiAbstract:Face detection has drawn much attention in recent decades since the seminal work by Viola and Jones. While many subsequences have improved the work with more powerful learning algorithms, the feature representation used for face detection still can't meet the demand for effectively and efficiently handling faces with large appearance variance in the wild. To solve this bottleneck, we borrow the concept of Channel features to the face detection domain, which extends the Image Channel to diverse types like gradient magnitude and oriented gradient histograms and therefore encodes rich information in a simple form. We adopt a novel variant called aggregate Channel features, make a full exploration of feature design, and discover a multi-scale version of features with better performance. To deal with poses of faces in the wild, we propose a multi-view detection approach featuring score re-ranking and detection adjustment. Following the learning pipelines in Viola-Jones framework, the multi-view face detector using aggregate Channel features shows competitive performance against state-of-the-art algorithms on AFW and FDDB testsets, while runs at 42 FPS on VGA Images.
