Graininess-Aware Deep Feature Learning for Pedestrian Detection

Lin, Chunze; Lu, Jiwen; Wang, Gang; Zhou, Jie

doi:10.1007/978-3-030-01240-3_45

Cited by 145 publications

(83 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Here, MGAN is compared to the following recent stateof-art methods: CompACT-Deep [3], DeepParts [28], MS-CNN [2], RPN+BF [30], SA-F.RCNN [12], MCF [4], SDS-RCNN [1], F.RCNN [31], F.RCNN+ATT-vbb [33], GDFL [13], and Bi-Box [36]. Tab.…”

Section: Caltech Datasetmentioning

confidence: 99%

“…Our MGAN achieives superior results with a log-average miss rate of 6.83 on this set. On the HO and R+HO sets, the GDFL detector [13] provides the best results among the existing methods with a log-average miss rate of 43.18 and 15.64, respectively. Our MGAN detector outperforms GDFL with an absolute gain of 5.02% and 1.80% on HO and R+HO sets, respectively.…”

Section: Caltech Datasetmentioning

confidence: 99%

“…Our approach obtains an absolute gain of 9.5% in log-average miss rate, compared to the best reported results [31] on the heavily occluded HO pedestrian set of CityPersons test set. Further, on the HO pedestrian set of Caltech dataset, our method achieves an absolute gain of 5.0% in log-average miss rate, compared to the best reported results [13]. Code and models are available at:…”

mentioning

confidence: 96%

See 2 more Smart Citations

Mask-Guided Attention Network for Occluded Pedestrian Detection

Pang

Xie

Khan

et al. 2019

2019 IEEE/CVF International Conference on Computer Vision (ICCV)

198

163

View full text Add to dashboard Cite

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 far from satisfactory. The main culprits are intra-class occlusions involving other pedestrians and inter-class occlusions caused by other objects, such as cars and bicycles. These result in a multitude of occlusion patterns. We propose an approach for occluded pedestrian detection with the following contributions. First, we introduce a novel maskguided attention network that fits naturally into popular pedestrian detection pipelines. Our attention network emphasizes on visible pedestrian regions while suppressing the occluded ones by modulating full body features. Second, we empirically demonstrate that coarse-level segmentation annotations provide reasonable approximation to their dense pixel-wise counterparts. Experiments are performed on CityPersons and Caltech datasets. Our approach sets a new state-of-the-art on both datasets. Our approach obtains an absolute gain of 9.5% in log-average miss rate, compared to the best reported results [31] on the heavily occluded HO pedestrian set of CityPersons test set. Further, on the HO pedestrian set of Caltech dataset, our method achieves an absolute gain of 5.0% in log-average miss rate, compared to the best reported results [13]. Code and models are available at:

show abstract

Section: Caltech Datasetmentioning

confidence: 99%

Section: Caltech Datasetmentioning

confidence: 99%

mentioning

confidence: 96%

See 1 more Smart Citation

Mask-Guided Attention Network for Occluded Pedestrian Detection

Pang

Xie

Khan

et al. 2019

2019 IEEE/CVF International Conference on Computer Vision (ICCV)

198

163

View full text Add to dashboard Cite

show abstract

“…F-DNN+SS [34] further uses a pixel-wise semantic segmentation network to refine the classification and improves accuracy at the expense of a significant loss in speed. GDFL [33] includes three components: a convolutional back-bone, a scale-aware pedestrian attention module and a zoom-inzoom-out module to identify small and occluded pedestrians. TLL-TFA [32] integrates the somatic topological line localization (TLL) networks and temporal feature aggregation for detecting multi-scale pedestrians.…”

Section: Evaluation With Respective To Occlusion and Scalementioning

confidence: 99%

“…TLL-TFA [32] integrates somatic Topological Line Localization (TLL) network and Temporal Feature Aggregation (TFA) to detect multi-scale pedestrians. Graininess-aware Deep Feature Learning method (GDFL) [33] uses scale-aware pedestrian attention masks and a zoom-inzoom-out module to identify small and occluded pedestrians. Fused Deep Neural Network (F-DNN) [34] combines multiple deep classifiers with a soft-reject strategy to refine proposals.…”

Section: Introductionmentioning

confidence: 99%

Hybrid channel based pedestrian detection

Tesema

Chen

et al. 2020

Neurocomputing

View full text Add to dashboard Cite

Pedestrian detection has achieved great improvements with the help of Convolutional Neural Networks (CNNs). CNN can learn high-level features from input images, but the insufficient spatial resolution of CNN feature channels (feature maps) may cause a loss of information, which is harmful especially to small instances. In this paper, we propose a new pedestrian detection framework, which extends the successful RPN+BF framework to combine handcrafted features and CNN features. RoI-pooling is used to extract features from both handcrafted channels (e.g. HOG+LUV, CheckerBoards or RotatedFilters) and CNN channels. Since handcrafted channels always have higher spatial resolution than CNN channels, we apply RoI-pooling with larger output resolution to handcrafted channels to keep more detailed information. Our ablation experiments show that the developed handcrafted features can reach better detection accuracy than the CNN features extracted from the VGG-16 net, and a performance gain can be achieved by combining them. Experimental results on Caltech pedestrian dataset with the original annotations and the improved annotations demonstrate the effectiveness of the proposed approach. When using a more advanced RPN in our framework, our approach can be further improved and get competitive results on both benchmarks.

show abstract