Scale-aware Fast R-CNN for Pedestrian Detection

Li, Jianan; Liang, Xiaodan; Shen, Shengmei; Xu, Tingfa; Feng, Jiashi; Yan, Shuicheng

doi:10.48550/arxiv.1510.08160

Cited by 27 publications

(28 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Second, the FRCNN is a wellknown method in computer vision. Considering that few CNNs have been tested on both the Caltech and the VOC datasets, the FRCNN is a good choice [17], [44]. Here, we use the VGG-16 [45] as the back-bone network pretrained by the ImageNet dataset.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

A Taught-Obesrve-Ask (TOA) Method for Object Detection with Critical Supervision

Wu,

Huang,

et al. 2017

Preprint

View full text Add to dashboard Cite

Being inspired by child's learning experience -taught first and followed by observation and questioning, we investigate a critically supervised learning methodology for object detection in this work. Specifically, we propose a taught-observe-ask (TOA) method that consists of several novel components such as negative object proposal, critical example mining, and machine-guided question-answer (QA) labeling. To consider labeling time and performance jointly, new evaluation methods are developed to compare the performance of the TOA method, with the fully and weakly supervised learning methods. Extensive experiments are conducted on the PASCAL VOC and the Caltech benchmark datasets. The TOA method provides significantly improved performance of weakly supervision yet demands only about 3-6% of labeling time of full supervision. The effectiveness of each novel component is also analyzed.

show abstract

Section: Methodsmentioning

confidence: 99%

“…8. In these experiments, we implement the FRCNN adapted to the pedestrian detection problem according to [44]. We see from the figure that the performance gain is even more obvious for the Caltech dataset.…”

Section: Single-class Object Detectionmentioning

confidence: 99%

A Taught-Obesrve-Ask (TOA) Method for Object Detection with Critical Supervision

Wu,

Huang,

et al. 2017

Preprint

View full text Add to dashboard Cite

show abstract

“…Traditional pedestrian detectors, extended from Viola and Jones paradigm [27], such as ACF [9], LDCF [22], and Checkerboards [35], filter various Integral Channels Features (ICF) [10] before feeding them into a boosted decision forest, predominating the field of pedestrian detection for years. Coupled with the prevalence of deep convolutional neural network, CNN-based models [17,33,2] have pushed pedestrian detection results to an unprecedented level. In [33], given region proposals generated by a Region Proposal Network (RPN), CNN features extracted by an RoI pooling layer [13] are fed into a boosted forest; while in Cai et al [2], a downstream neural network architecture is proposed to preform end-to-end detection.…”

Section: Related Workmentioning

confidence: 99%

What Can Help Pedestrian Detection?

Mao

Xiao

Jiang³

et al. 2017

2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

280

146

View full text Add to dashboard Cite

Aggregating extra features has been considered as an effective approach to boost traditional pedestrian detection methods. However, there is still a lack of studies on whether and how CNN-based pedestrian detectors can benefit from these extra features. The first contribution of this paper is exploring this issue by aggregating extra features into CNNbased pedestrian detection framework. Through extensive experiments, we evaluate the effects of different kinds of extra features quantitatively. Moreover, we propose a novel network architecture, namely HyperLearner, to jointly learn pedestrian detection as well as the given extra feature. By multi-task training, HyperLearner is able to utilize the information of given features and improve detection performance without extra inputs in inference. The experimental results on multiple pedestrian benchmarks validate the effectiveness of the proposed HyperLearner.

show abstract

“…Due to its relevance in many fields, such as robotics and video surveillance, the problem of pedestrian detection has received considerable interests in the research community. Over the years, a large variety of features and algorithms have been proposed for improving detection systems, both with respect to speed [34,2,1,17] and accuracy [41,22,46,47,10,32].…”

Section: Related Workmentioning

confidence: 99%

“…Great strides in pedestrian detection research [3] have been made for challenging situations, such as cluttered background, substantial occlusions and tiny target appearance. As for many other computer vision tasks, in the last few years significant performance gains have been achieved thanks to approaches based on deep networks [21,1,17,32]. Additionally, the adoption of novel sensors, e.g.…”

Section: Introductionmentioning

confidence: 99%

Learning Cross-Modal Deep Representations for Robust Pedestrian Detection

Ouyang

Ricci

et al. 2017

2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

200

100

View full text Add to dashboard Cite

This paper presents a novel method for detecting pedestrians under adverse illumination conditions. Our approach relies on a novel cross-modality learning framework and it is based on two main phases. First, given a multimodal dataset, a deep convolutional network is employed to learn a non-linear mapping, modeling the relations between RGB and thermal data. Then, the learned feature representations are transferred to a second deep network, which receives as input an RGB image and outputs the detection results. In this way, features which are both discriminative and robust to bad illumination conditions are learned. Importantly, at test time, only the second pipeline is considered and no thermal data are required. Our extensive evaluation demonstrates that the proposed approach outperforms the state-ofthe-art on the challenging KAIST multispectral pedestrian dataset and it is competitive with previous methods on the popular Caltech dataset.

show abstract

Scale-aware Fast R-CNN for Pedestrian Detection

Cited by 27 publications

References 26 publications

A Taught-Obesrve-Ask (TOA) Method for Object Detection with Critical Supervision

A Taught-Obesrve-Ask (TOA) Method for Object Detection with Critical Supervision

What Can Help Pedestrian Detection?

Learning Cross-Modal Deep Representations for Robust Pedestrian Detection

Contact Info

Product

Resources

About