PedHunter: Occlusion Robust Pedestrian Detector in Crowded Scenes

Chi, Cheng; Zhang, Shifeng; Xing, Junliang; Lei, Zhen; Li, Stan Z.; Zou, Xudong

doi:10.1609/aaai.v34i07.6690

Cited by 86 publications

(59 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Some methods [58], [8], [52], [66] aim to improve small-scale pedestrian detection, while some methods [78], [83], [51] exploit the part or visible information for occluded pedestrian detection. To improve pedestrian detection in crowded scenes, some methods [63], [45], [33], [11] exploit how to combine the highly overlapping bounding boxes.…”

Section: B the Methods Of Object Detectionmentioning

confidence: 99%

TJU-DHD: A Diverse High-Resolution Dataset for Object Detection

Pang

Cao

et al. 2021

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

Vehicles, pedestrians, and riders are the most important and interesting objects for the perception modules of selfdriving vehicles and video surveillance. However, the state-of-theart performance of detecting such important objects (esp. small objects) is far from satisfying the demand of practical systems. Large-scale, rich-diversity, and high-resolution datasets play an important role in developing better object detection methods to satisfy the demand. Existing public large-scale datasets such as MS COCO collected from websites do not focus on the specific scenarios. Moreover, the popular datasets (e.g., KITTI and Citypersons) collected from the specific scenarios are limited in the number of images and instances, the resolution, and the diversity. To attempt to solve the problem, we build a diverse high-resolution dataset (called TJU-DHD). The dataset contains 115,354 high-resolution images (52% images have a resolution of 1624×1200 pixels and 48% images have a resolution of at least 2,560×1,440 pixels) and 709,330 labeled objects in total with a large variance in scale and appearance. Meanwhile, the dataset has a rich diversity in season variance, illumination variance, and weather variance. In addition, a new diverse pedestrian dataset is further built. With the four different detectors (i.e., the one-stage RetinaNet, anchor-free FCOS, two-stage FPN, and Cascade R-CNN), experiments about object detection and pedestrian detection are conducted. We hope that the newly built dataset can help promote the research on object detection and pedestrian detection in these two scenes. The dataset is available at https://github.com/tjubiit/TJU-DHD.

show abstract

Section: B the Methods Of Object Detectionmentioning

confidence: 99%

TJU-DHD: A Diverse High-Resolution Dataset for Object Detection

Pang

Cao

et al. 2021

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

show abstract

“…Zhou et al [ 31 ] presented a method of pedestrian detection: whereby the whole body and visible parts of pedestrians were respectively located by regressing two bounding boxes. Chi et al [ 32 ] proposed Pedhunter which can handle occlusion in pedestrian detection. However, the methods are complicated and take a long time.…”

Section: Related Workmentioning

confidence: 99%

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

Shao

Wang

Yang

et al. 2021

Sensors

View full text Add to dashboard Cite

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 feature pyramid network based on ResNet (MFPN) to enhance the features of occluded targets and improve the detection accuracy. MFPN includes two modules, namely double feature pyramid network (FPN) integrated with ResNet (DFR) and repulsion loss of minimum (RLM). We propose the double FPN which improves the architecture to further enhance the semantic information and contours of occluded pedestrians, and provide a new way for feature extraction of occluded targets. The features extracted by our network can be more separated and clearer, especially those heavily occluded pedestrians. Repulsion loss is introduced to improve the loss function which can keep predicted boxes away from the ground truths of the unrelated targets. Experiments carried out on the public CrowdHuman dataset, we obtain 90.96% AP which yields the best performance, 5.16% AP gains compared to the FPN-ResNet50 baseline. Compared with the state-of-the-art works, the performance of the pedestrian detection system has been boosted with our method.

show abstract

“…Double Anchor [ 31 ] detects the body and head for each person simultaneously with the help of a crossover strategy and develops a Joint NMS module for robust postprocessing. Like Bi-Box and Double Anchor, there are other methods, e.g., MGAN [ 32 ], PedHunter [ 33 ] and JointDet [ 34 ], to help pedestrian detection by additional detection of the visible part for each pedestrian, which promotes further progress of pedestrian detectors. Most of the above methods still follow the bounding box representation and set it as the regression target as with generic object detection.…”

Section: Related Workmentioning

confidence: 99%

Pedestrian Detection by Novel Axis-Line Representation and Regression Pattern

Zhang

Liu

2021

Sensors

View full text Add to dashboard Cite

The pattern of bounding box representation and regression has long been dominant in CNN-based pedestrian detectors. Despite the method’s success, it cannot accurately represent location, and introduces unnecessary background information, while pedestrian features are mainly located in axis-line areas. Other object representations, such as corner-pairs, are not easy to obtain by regression because the corners are far from the axis-line and are greatly affected by background features. In this paper, we propose a novel detection pattern, named Axis-line Representation and Regression (ALR), for pedestrian detection in road scenes. Specifically, we design a 3-d axis-line representation for pedestrians and use it as the regression target during network training. A line-box transformation method is also proposed to fit the widely used box-annotations. Meanwhile, we explore the influence of deformable convolution base-offset on detection performance and propose a base-offset initialization strategy to further promote the gain brought by ALR. Notably, the proposed ALR pattern can be introduced into both anchor-based and anchor-free frameworks. We validate the effectiveness of ALR on the Caltech-USA and CityPersons datasets. Experimental results show that our approach outperforms the baseline significantly through simple modifications and achieves competitive accuracy with other methods without bells and whistles.

show abstract

PedHunter: Occlusion Robust Pedestrian Detector in Crowded Scenes

Cited by 86 publications

References 37 publications

TJU-DHD: A Diverse High-Resolution Dataset for Object Detection

TJU-DHD: A Diverse High-Resolution Dataset for Object Detection

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

Pedestrian Detection by Novel Axis-Line Representation and Regression Pattern

Contact Info

Product

Resources

About