paper-with-me

홈 › Papers

Optimized Pedestrian Detection for Multiple and Occluded People

2013-06-01 · CVPR 2013 6 · Sitapa Rujikietgumjorn, Robert T. Collins

We present a quadratic unconstrained binary optimization (QUBO) framework for reasoning about multiple object detections with spatial overlaps. The method maximizes an objective function composed of unary detection confidence scores and pairwise overlap constraints to determine which overlapping detections should be suppressed, and which should be kept. The framework is flexible enough to handle the problem of detecting objects as a shape covering of a foreground mask, and to handle the problem of filtering confidence weighted detections produced by a traditional sliding window object detector. In our experiments, we show that our method outperforms two existing state-ofthe-art pedestrian detectors.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

ObjectPedestrian Detection

Similar Papers 제목 키워드 기반

Occluded Pedestrian Detection Through Guided Attention in CNNs

2018-06-01 · CVPR 2018 6 · Shanshan Zhang, Jian Yang, Bernt Schiele

Pedestrian detection has progressed significantly in the last years. However, occluded people are notoriously hard to detect, as their appearance varies substantially depending on a wide range of partial occlusions. In t…

Pedestrian Detection

Discriminative Feature Transformation for Occluded Pedestrian Detection

2019-10-01 · ICCV 2019 10 · Chunluan Zhou, Ming Yang, Junsong Yuan

Despite promising performance achieved by deep con- volutional neural networks for non-occluded pedestrian de- tection, it remains a great challenge to detect partially oc- cluded pedestrians. Compared with non-occluded …

Pedestrian Detection

Mask-Guided Attention Network for Occluded Pedestrian Detection

2019-10-14 · ICCV 2019 10 · Yanwei Pang, Jin Xie, Muhammad Haris Khan, Rao Muhammad Anwer 외

Pedestrian detection relying on deep convolution neural networks has made significant progress. Though promising results have been achieved on standard pedestrians, the performance on heavily occluded pedestrians remains…

Pedestrian Detection

Multi-Scale Feature Pyramid Network: A Heavily Occluded Pedestrian Detection Network Based on ResNet

2021-03-05 · Sensors 2021 3 · Xiaotao Shao, Qing Wang, Wei Yang, Yun Chen 외

The existing pedestrian detection algorithms cannot effectively extract features of heavily occluded targets which results in lower detection accuracy. To solve the heavy occlusion in crowds, we propose a multi-scale f…

Object DetectionPedestrian Detection

Feature Calibration Network for Occluded Pedestrian Detection

2022-12-12 · Tianliang Zhang, Qixiang Ye, Baochang Zhang, Jianzhuang Liu 외

Pedestrian detection in the wild remains a challenging problem especially for scenes containing serious occlusion. In this paper, we propose a novel feature learning method in the deep learning framework, referred to as …

Pedestrian Detection