Results 1 - 10 of 15

The fastest deformable part model for object detection

by Junjie Yan, Zhen Lei, Longyin Wen, Stan Z. Li - In CVPR , 2014
"... This paper solves the speed bottleneck of deformable part model (DPM), while maintaining the accuracy in de-tection on challenging datasets. Three prohibitive steps in cascade version of DPM are accelerated, including 2D cor-relation between root filter and feature map, cascade part pruning and HOG ..."
Abstract - Cited by 13 (2 self) - Add to MetaCart
This paper solves the speed bottleneck of deformable part model (DPM), while maintaining the accuracy in de-tection on challenging datasets. Three prohibitive steps in cascade version of DPM are accelerated, including 2D cor-relation between root filter and feature map, cascade part pruning and HOG feature extraction. For 2D correlation, the root filter is constrained to be low rank, so that 2D cor-relation can be calculated by more efficient linear combi-nation of 1D correlations. A proximal gradient algorithm is adopted to progressively learn the low rank filter in a dis-criminative manner. For cascade part pruning, neighbor-hood aware cascade is proposed to capture the dependence in neighborhood regions for aggressive pruning. Instead of explicit computation of part scores, hypotheses can be pruned by scores of neighborhoods under the first order ap-proximation. For HOG feature extraction, look-up tables are constructed to replace expensive calculations of orien-tation partition and magnitude with simpler matrix index operations. Extensive experiments show that (a) the pro-posed method is 4 times faster than the current fastest DPM method with similar accuracy on Pascal VOC, (b) the pro-posed method achieves state-of-the-art accuracy on pedes-trian and face detection task with frame-rate speed. 1.
(Show Context)

Ten years of pedestrian detection, what have we learned

by Rodrigo Benenson, Mohamed Omran, Jan Hosang, Bernt Schiele - In ECCV Workshops , 2014
"... Abstract Paper-by-paper results make it easy to miss the forest for the trees.We analyse the remarkable progress of the last decade by dis-cussing the main ideas explored in the 40+ detectors currently present in the Caltech pedestrian detection benchmark. We observe that there exist three families ..."
Abstract - Cited by 10 (1 self) - Add to MetaCart
Abstract Paper-by-paper results make it easy to miss the forest for the trees.We analyse the remarkable progress of the last decade by dis-cussing the main ideas explored in the 40+ detectors currently present in the Caltech pedestrian detection benchmark. We observe that there exist three families of approaches, all currently reaching similar detec-tion quality. Based on our analysis, we study the complementarity of the most promising ideas by combining multiple published strategies. This new decision forest detector achieves the current best known performance
(Show Context)

Filtered channel features for pedestrian detection

by Shanshan Zhang, Rodrigo Benenson, Bernt Schiele - CVPR, 2015. Random Projection Feature for Pedestrian Detection PLOS ONE | DOI:10.1371/journal.pone.0142820 November 16, 2015 9 / 10
"... This paper starts from the observation that multiple top performing pedestrian detectors can be modelled by using an intermediate layer filtering low-level features in combin-ation with a boosted decision forest. Based on this observa-tion we propose a unifying framework and experimentally explore d ..."
Abstract - Cited by 6 (0 self) - Add to MetaCart
This paper starts from the observation that multiple top performing pedestrian detectors can be modelled by using an intermediate layer filtering low-level features in combin-ation with a boosted decision forest. Based on this observa-tion we propose a unifying framework and experimentally explore different filter families. We report extensive results enabling a systematic analysis. Using filtered channel features we obtain top perform-ance on the challenging Caltech and KITTI datasets, while using only HOG+LUV as low-level features. When adding optical flow features we further improve detection quality and report the best known results on the Caltech dataset, reaching 93 % recall at 1 FPPI. 1.
(Show Context)

Local Decorrelation for Improved Pedestrian Detection

by Woonhyun Nam, Stradvision Inc, Joon Hee Han
"... Even with the advent of more sophisticated, data-hungry methods, boosted deci-sion trees remain extraordinarily successful for fast rigid object detection, achiev-ing top accuracy on numerous datasets. While effective, most boosted detectors use decision trees with orthogonal (single feature) splits ..."
Abstract - Cited by 6 (0 self) - Add to MetaCart
Even with the advent of more sophisticated, data-hungry methods, boosted deci-sion trees remain extraordinarily successful for fast rigid object detection, achiev-ing top accuracy on numerous datasets. While effective, most boosted detectors use decision trees with orthogonal (single feature) splits, and the topology of the resulting decision boundary may not be well matched to the natural topology of the data. Given highly correlated data, decision trees with oblique (multiple fea-ture) splits can be effective. Use of oblique splits, however, comes at considerable computational expense. Inspired by recent work on discriminative decorrelation of HOG features, we instead propose an efficient feature transform that removes correlations in local neighborhoods. The result is an overcomplete but locally decorrelated representation ideally suited for use with orthogonal decision trees. In fact, orthogonal trees with our locally decorrelated features outperform oblique trees trained over the original features at a fraction of the computational cost. The overall improvement in accuracy is dramatic: on the Caltech Pedestrian Dataset, we reduce false positives nearly tenfold over the previous state-of-the-art. 1
(Show Context)

Word channel based multiscale pedestrian detection without image resizing and using only one classifier

by Arthur Daniel Costea , Sergiu Nedevschi , Arthur Daniel Costea , Sergiu Nedevschi - In IEEE Conference on Computer Vision and Pattern Recognition , 2014
"... Abstract ..."
Abstract - Cited by 3 (0 self) - Add to MetaCart
Abstract not found
(Show Context)

Single-Pedestrian Detection Aided by 2-Pedestrian Detection

by Wanli Ouyang, Xingyu Zeng, Xiaogang Wang - IEEE TRANSACTIONS PATTERN ANALYSIS AND MACHINE INTELLIGENCE
"... In this paper, we address the challenging problem of detecting pedestrians who appear in groups. A new approach is proposed for single-pedestrian detection aided by 2-pedestrian detection. A mixture model of 2-pedestrian detectors is designed to capture the unique visual cues which are formed by nea ..."
Abstract - Cited by 1 (1 self) - Add to MetaCart
In this paper, we address the challenging problem of detecting pedestrians who appear in groups. A new approach is proposed for single-pedestrian detection aided by 2-pedestrian detection. A mixture model of 2-pedestrian detectors is designed to capture the unique visual cues which are formed by nearby pedestrians but cannot be captured by single-pedestrian detectors. A probabilistic framework is proposed to model the relationship between the configurations estimated by single- and 2-pedestrian detectors, and to refine the single-pedestrian detection result using 2-pedestrian detection. The 2-pedestrian detector can integrate with any single-pedestrian detector. 25 state-of-the-art single-pedestrian detection approaches are combined with the 2-pedestrian detector on three widely used public datasets: Caltech, TUD-Brussels, and ETH. Experimental results show that our framework improves all these approaches. The average improvement is 9 % on the Caltech-Test dataset, 11 % on the TUD-Brussels dataset and 17 % on the ETH dataset in terms of average miss rate. The lowest average miss rate is reduced from 37%

Pedestrian detection aided by deep learning semantic tasks

by Yonglong Tian, Ping Luo, Xiaogang Wang, Xiaoou Tang - In CVPR , 2015
"... Deep learning methods have achieved great successes in pedestrian detection, owing to its ability to learn dis-criminative features from raw pixels. However, they treat pedestrian detection as a single binary classification task, which may confuse positive with hard negative samples (Fig.1 (a)). To ..."
Abstract - Cited by 1 (1 self) - Add to MetaCart
Deep learning methods have achieved great successes in pedestrian detection, owing to its ability to learn dis-criminative features from raw pixels. However, they treat pedestrian detection as a single binary classification task, which may confuse positive with hard negative samples (Fig.1 (a)). To address this ambiguity, this work jointly op-timize pedestrian detection with semantic tasks, including pedestrian attributes (e.g. ‘carrying backpack’) and scene attributes (e.g. ‘vehicle’, ‘tree’, and ‘horizontal’). Rather than expensively annotating scene attributes, we transfer attributes information from existing scene segmentation datasets to the pedestrian dataset, by proposing a novel deep model to learn high-level features from multiple tasks and multiple data sources. Since distinct tasks have distinct convergence rates and data from different datasets have different distributions, a multi-task deep model is carefully designed to coordinate tasks and reduce discrepancies among datasets. Extensive evaluations show that the proposed approach outperforms the state-of-the-art on the challenging Caltech [9] and ETH [10] datasets where it reduces the miss rates of previous deep models by 17 and 5.5 percent, respectively.
(Show Context)

unknown title

by Thèse Présentée , 2014
"... pour l’obtention du grade de Docteur de l’UTC Information fusion for scene understanding Soutenue le 28 novembre 2014 Spécialité: Technologies de l’Information et des Systèmes ..."
Abstract - Add to MetaCart
pour l’obtention du grade de Docteur de l’UTC Information fusion for scene understanding Soutenue le 28 novembre 2014 Spécialité: Technologies de l’Information et des Systèmes
(Show Context)

Information fusion for scene understanding

by Hal Id Tel , 2014
"... HAL is a multi-disciplinary open access archive for the deposit and dissemination of sci-entific research documents, whether they are pub-lished or not. The documents may come from teaching and research institutions in France or abroad, or from public or private research centers. L’archive ouverte p ..."
Abstract - Add to MetaCart
HAL is a multi-disciplinary open access archive for the deposit and dissemination of sci-entific research documents, whether they are pub-lished or not. The documents may come from teaching and research institutions in France or abroad, or from public or private research centers. L’archive ouverte pluridisciplinaire HAL, est destinée au dépôt et a ̀ la diffusion de documents scientifiques de niveau recherche, publiés ou non, émanant des établissements d’enseignement et de recherche français ou étrangers, des laboratoires publics ou privés. Par Philippe XU Thèse présentée pour l’obtention du grade de Docteur de l’UTC Information fusion for scene understanding Soutenue le 28 novembre 2014 Spécialité: Technologies de l’Information et des Systèmes
(Show Context)

Basis Mapping Based Boosting for Object Detection

by Haoyu Ren, Ze-nian Li
"... We propose a novel mapping method to improve the train-ing accuracy and efficiency of boosted classifiers for object detection. The key step of the proposed method is a non-linear mapping on original samples by referring to the basis samples before feeding into the weak classifiers, where the basis ..."
Abstract - Add to MetaCart
We propose a novel mapping method to improve the train-ing accuracy and efficiency of boosted classifiers for object detection. The key step of the proposed method is a non-linear mapping on original samples by referring to the basis samples before feeding into the weak classifiers, where the basis samples correspond to the hard samples in the cur-rent training stage. We show that the basis mapping based weak classifier is an approximation of kernel weak clas-sifiers while keeping the same computation cost as linear weak classifiers. As a result, boosting with such weak clas-sifiers is more effective. In this paper, two different non-linear mappings are shown to work well. We adopt the LogitBoost algorithm to train the weak classifiers based on the Histogram of Oriented Gradient descriptor (HOG). Ex-perimental results show that the proposed approach signif-icantly improves the detection accuracy and training effi-ciency of the boosted classifier. It also achieves high per-formance on public datasets for both pedestrian detection and general object detection tasks. 1.
(Show Context)