Corpus ID: 49571680

Small-scale Pedestrian Detection Based on Somatic Topology Localization and Temporal Feature Aggregation

@article{Song2018SmallscalePD,
  title={Small-scale Pedestrian Detection Based on Somatic Topology Localization and Temporal Feature Aggregation},
  author={Tao Song and Leiyu Sun and Di Xie and Haiming Sun and Shiliang Pu},
  journal={ArXiv},
  year={2018},
  volume={abs/1807.01438}
}
A critical issue in pedestrian detection is to detect small-scale objects that will introduce feeble contrast and motion blur in images and videos, which in our opinion should partially resort to deep-rooted annotation bias. [...] Key Method Moreover, a post-processing scheme based on Markov Random Field (MRF) is introduced to eliminate ambiguities in occlusion cases. Applying with these methodologies comprehensively, we achieve best detection performance on Caltech benchmark and improve performance of small…Expand
Two-stream small-scale pedestrian detection network with feature aggregation for drone-view videos
  • Han-Ping Xie, Hyunchul Shin
  • Computer Science
  • Multidimens. Syst. Signal Process.
  • 2021
Detecting Pedestrians with YOLOv3 and Semantic Segmentation Infusion
S3D: Scalable Pedestrian Detection via Score Scale Surface Discrimination
Temporal-Context Enhanced Detection of Heavily Occluded Pedestrians
Box Guided Convolution for Pedestrian Detection
PRF-Ped: Multi-scale Pedestrian Detector with Prior-based Receptive Field
Taking a Look at Small-Scale Pedestrians and Occluded Pedestrians
Self-Mimic Learning for Small-scale Pedestrian Detection
Semantic Head Enhanced Pedestrian Detection in a Crowd
...
1
2
3
...

References

SHOWING 1-10 OF 43 REFERENCES
Scale-Aware Fast R-CNN for Pedestrian Detection
Too Far to See? Not Really!—Pedestrian Detection With Scale-Aware Localization Policy
Illuminating Pedestrians via Simultaneous Detection and Segmentation
A Diverse Dataset for Pedestrian Detection
Pedestrian Detection: An Evaluation of the State of the Art
Is Faster R-CNN Doing Well for Pedestrian Detection?
How Far are We from Solving Pedestrian Detection?
Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation
Flow-Guided Feature Aggregation for Video Object Detection
CityPersons: A Diverse Dataset for Pedestrian Detection
  • Shanshan Zhang, Rodrigo Benenson, B. Schiele
  • Computer Science
  • 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2017
...
1
2
3
4
5
...