Learning Multilayer Channel Features for Pedestrian Detection

Cao, Jiale; Pang, Yanwei; Li, Xuelong

doi:10.1109/tip.2017.2694224

Cited by 108 publications

(51 citation statements)

References 56 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Both of the results are much better than the previous methods which combine handcrafted features and CNN features, e.g. CompACT [39] and MCF [40]. Our approach reaches the same results as previous RPN+BF [28] on the original Caltech dataset, and gets a better result of 6.41% over its 7.3% on Caltech dataset with the improved annotations.…”

Section: Evaluation With Respective To Occlusion and Scalesupporting

confidence: 57%

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

Section: Evaluation With Respective To Occlusion and Scalesupporting

confidence: 57%

Hybrid channel based pedestrian detection

Tesema

Chen

et al. 2020

Neurocomputing

View full text Add to dashboard Cite

show abstract

“…VGG16 [14] was applied to extract features, and a cascade AdaBoost classifier was trained based on these features [15,16]. Their good performance testified that CNNs have a strong power of extracting general and representative features without the need of human interference.…”

Section: Deep Neural Networkmentioning

confidence: 99%

Survey on Artificial Intelligence for Vehicles

Cheng

Guo

et al. 2018

Automot. Innov.

View full text Add to dashboard Cite

With the ever-increasing demand in urban mobility and modern logistics sector, the vehicle population has been steadily growing over the past several decades. One natural consequence of the vehicle population growth is the increase in traffic congestion. Almost all (metropolitan) cities including the major ones, like Los Angeles, Beijing, New York, are suffering from heavy traffic congestion. Statistics show that, in 2015, 43 cities in China are suffering a prolonged travel time of more than 1.5 h every day during rush hours. In the meanwhile, traffic accidents are plaguing the economic development as well.

show abstract

“…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%

Mask-Guided Attention Network for Occluded Pedestrian Detection

Pang

Xie

Khan

et al. 2019

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

Self Cite

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

Learning Multilayer Channel Features for Pedestrian Detection

Cited by 108 publications

References 56 publications

Hybrid channel based pedestrian detection

Hybrid channel based pedestrian detection

Survey on Artificial Intelligence for Vehicles

Mask-Guided Attention Network for Occluded Pedestrian Detection

Contact Info

Product

Resources

About