Scale-Aware Fast R-CNN for Pedestrian Detection

@article{Liang2018ScaleAwareFR,
  title={Scale-Aware Fast R-CNN for Pedestrian Detection},
  author={Xiaodan Liang and Shengmei Shen and Tingfa Xu and Jiashi Feng and Shuicheng Yan},
  journal={IEEE Transactions on Multimedia},
  year={2018},
  volume={20},
  pages={985-996}
}
In this paper, we consider the problem of pedestrian detection in natural scenes. [] Key Method The model introduces multiple built-in subnetworks which detect pedestrians with scales from disjoint ranges. Outputs from all of the subnetworks are then adaptively combined to generate the final detection results that are shown to be robust to large variance in instance scales, via a gate function defined over the sizes of object proposals. Extensive evaluations on several challenging pedestrian detection…

Context-aware pedestrian detection especially for small-sized instances with Deconvolution Integrated Faster RCNN (DIF R-CNN)

A novel context-aware pedestrian detection method is introduced by developing the DIF R-CNN, in which a deconvolutional module is integrated to bring additional context information which is helpful to improve the detection accuracy for small-sized pedestrian instances.

A Scale-Aware YOLO Model for Pedestrian Detection

A new framework is proposed, a scale-aware You Only Look Once framework which improves YOLOv3 in improving pedestrian detection of small scale pedestrian instances in a real-time manner, which outperforms the results of YOLov3 on public datasets and run at an average of 11 fps on a GPU.

Too Far to See? Not Really!—Pedestrian Detection With Scale-Aware Localization Policy

An active pedestrian detector that explicitly operates over multiple-layer neuronal representations of the input still image and is demonstrated to produce overall lower detection errors on widely used benchmarks, and it works particularly well with far-scale pedestrians.

Efficiently Handling Scale Variation for Pedestrian Detection

A novel pedestrian detector to better classify and regress proposals of different scales given by a region proposal network (RPN), which surpasses previous state-of-the-art methods with lower computational costs at test time.

Multi-Grained Deep Feature Learning for Pedestrian Detection

This paper jointly train a scale-aware network and a human parsing network in a semi-supervised manner to predict pedestrians of particular scales using most appropriate feature maps, by matching their receptive field with the target sizes.

Learning a Dynamic High-Resolution Network for Multi-Scale Pedestrian Detection

Experimental results indicate that the proposed dynamic HRNet is more capable of dealing with pedestrians of various scales, and thus improves the performance across different scales consistently.

Real-world pedestrian detection method enhanced by semantic segmentation

  • Qihua Peng
  • Computer Science
    J. Electronic Imaging
  • 2019
Extensive experiments on the recently published large-scale pedestrian detection benchmark, CityPersons, show that the additional supervision from semantic segmentation can significantly improve the detection accuracy without extra computational burdens during inference, which demonstrates the superiority of the proposed method.

Scale-Aware Hierarchical Detection Network for Pedestrian Detection

A scale-aware hierarchical detection network is proposed to effectively integrate multiscale pedestrian detection into a unified framework by adaptively perceiving the augmented feature level for special-scale pedestrian detection.

Multi-Grained Deep Feature Learning for Robust Pedestrian Detection

This paper jointly train a multi-scale network and a human parsing network in a weakly supervised manner to predict pedestrians of particular scales with the most appropriate feature maps, by matching their receptive fields with the target sizes.

AN EFFICIENT DEEP LEARNING FRAMEWORK FOR PEDESTRIAN DETECTION

An efficient framework based on deep CNN for pedestrian detection is proposed, especially for small-scale pedestrians that uses the reduced ResNet-34 architecture for generating convolution feature maps and a modified loss function based on cross entropy loss is used to increase the loss contribution from hard-to-detect smallsized pedestrians.
...

References

SHOWING 1-10 OF 76 REFERENCES

Is Faster R-CNN Doing Well for Pedestrian Detection?

A very simple but effective baseline for pedestrian detection, using an RPN followed by boosted forests on shared, high-resolution convolutional feature maps, presenting competitive accuracy and good speed.

Robust Multi-resolution Pedestrian Detection in Traffic Scenes

This paper takes pedestrian detection in different resolutions as different but related problems, and proposes a Multi-Task model to jointly consider their commonness and differences, which noticeably outperforms previous state-of-the-art techniques.

Deep Learning Strong Parts for Pedestrian Detection

This work proposes DeepParts, which consists of extensive part detectors that can detect pedestrian by observing only a part of a proposal, and yields a new state-of-the-art miss rate of 11:89%, outperforming the second best method by 10%.

Random Forests of Local Experts for Pedestrian Detection

A pedestrian detection method that efficiently combines multiple local experts by means of a Random Forest ensemble that consistently ranks among the top performers in all the datasets, being either the best method or having a small difference with the best one.

Pedestrian Detection: An Evaluation of the State of the Art

An extensive evaluation of the state of the art in a unified framework of monocular pedestrian detection using sixteen pretrained state-of-the-art detectors across six data sets and proposes a refined per-frame evaluation methodology.

Pedestrian detection aided by deep learning semantic tasks

This work jointly optimize pedestrian detection with semantic tasks, including pedestrian attributes and scene attributes, by proposing a novel deep model to learn high-level features from multiple tasks and multiple data sources.

Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation

This paper proposes a simple and scalable detection algorithm that improves mean average precision (mAP) by more than 30% relative to the previous best result on VOC 2012 -- achieving a mAP of 53.3%.

Learning Complexity-Aware Cascades for Deep Pedestrian Detection

CompACT cascades are shown to seek an optimal trade-off between accuracy and complexity by pushing features of higher complexity to the later cascade stages, where only a few difficult candidate patches remain to be classified.

Learning Mutual Visibility Relationship for Pedestrian Detection with a Deep Model

A mutual visibility deep model that jointly estimates the visibility statuses of overlapping pedestrians is proposed that has the lowest average miss rate on the Caltech-Train dataset and the ETH dataset and leads to 6–15 % improvements on multiple benchmark datasets.

Multiview random forest of local experts combining RGB and LIDAR data for pedestrian detection

An extensive evaluation is provided that gives insight into how each of these aspects (multi-cue, multi-modality and strong multi-view classifier) affect performance both individually and when integrated together.
...