Multi-label Learning of Part Detectors for Heavily Occluded Pedestrian Detection

Zhou, Chunluan; Yuan, Junsong

doi:10.1109/iccv.2017.377

Cited by 128 publications

(74 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In real life complex scenarios, occlusion is ubiquitous challenging the accuracy of detectors, especially in crowded scenes. As indicated in [35,49,73], the part-based Fig. 1.…”

Section: Part Occlusion-aware Roi Pooling Unitmentioning

confidence: 99%

Occlusion-Aware R-CNN: Detecting Pedestrians in a Crowd

Zhang

Wen

Bian

et al. 2018

Lecture Notes in Computer Science

373

291

View full text Add to dashboard Cite

2[0000−0003−3109−5770] , Longyin Wen 3[0000−0001−5525−492X] , Xiao Bian 3[0000−0001−5447−6045] , Zhen Lei 1,2 [0000−0002−0791−189X] , andAbstract. Pedestrian detection in crowded scenes is a challenging problem since the pedestrians often gather together and occlude each other. In this paper, we propose a new occlusion-aware R-CNN (OR-CNN) to improve the detection accuracy in the crowd. Specifically, we design a new aggregation loss to enforce proposals to be close and locate compactly to the corresponding objects. Meanwhile, we use a new part occlusionaware region of interest (PORoI) pooling unit to replace the RoI pooling layer in order to integrate the prior structure information of human body with visibility prediction into the network to handle occlusion. Our detector is trained in an end-to-end fashion, which achieves state-of-the-art results on three pedestrian detection datasets, i.e., CityPersons, ETH, and INRIA, and performs on-pair with the state-of-the-arts on Caltech.

show abstract

“…In real life complex scenarios, occlusion is ubiquitous challenging the accuracy of detectors, especially in crowded scenes. As indicated in [35,49,73], the part-based Fig. 1.…”

Section: Part Occlusion-aware Roi Pooling Unitmentioning

confidence: 99%

Occlusion-Aware R-CNN: Detecting Pedestrians in a Crowd

Zhang

Wen

Bian

et al. 2018

Lecture Notes in Computer Science

373

291

View full text Add to dashboard Cite

show abstract

“…For the occlusion issue, many efforts have been made in the past years. A common framework [28,40,51,7,27,52] for occlusion handling is to learn a series of part detectors and integrate the results to localize occluded pedestrians. More recently, several works [46,50,38,44,49] focus on a more challenging issue of detecting pedestrian in a crowd.…”

Section: Related Workmentioning

confidence: 99%

Adaptive NMS: Refining Pedestrian Detection in a Crowd

Liu

Huang

Wang

2019

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

329

190

View full text Add to dashboard Cite

Pedestrian detection in a crowd is a very challenging issue. This paper addresses this problem by a novel Non-Maximum Suppression (NMS) algorithm to better refine the bounding boxes given by detectors. The contributions are threefold: (1) we propose adaptive-NMS, which applies a dynamic suppression threshold to an instance, according to the target density; (2) we design an efficient subnetwork to learn density scores, which can be conveniently embedded into both the single-stage and two-stage detectors; and (3) we achieve state of the art results on the CityPersons and CrowdHuman benchmarks.

show abstract

“…In the recent few years, CNN based methods have achieved great success on object detection and pedestrian detection [53], [4], [31], [59], [1], [2], [3]. At first, CNN [26], [45] is simply acted as the feature extractor for pedestrian detection, which is fed to the shallow classifier.…”

Section: A a Review Of Pedestrian Detectionmentioning

confidence: 99%

Taking a Look at Small-Scale Pedestrians and Occluded Pedestrians

Cao

Pang

Han

et al. 2020

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

Small-scale pedestrian detection and occluded pedestrian detection are two challenging tasks. However, most state-of-the-art methods merely handle one single task each time, thus giving rise to relatively poor performance when the two tasks, in practise, are required simultaneously. In this paper, it is found that small-scale pedestrian detection and occluded pedestrian detection actually have a common problem, i.e., inaccurate location problem. Therefore, solving this problem enables to improve the performance of both tasks. To this end, we pay more attention to the predicted bounding box with worse location precision and extract more contextual information around objects, where two modules (i.e., location bootstrap and semantic transition) are respectively proposed. The location bootstrap is used to re-weight the regression loss, where the loss of predicted bounding box far from the corresponding groundtruth is up-weighted and the loss of predicted bounding box near the corresponding ground-truth is down-weighted. Meanwhile, the semantic transition adds more contextual information and relieves the semantic inconsistency of skip-layer fusion. Since the location bootstrap is not used at the test stage and the semantic transition is light-weight, the proposed method does not add much extra computational costs during inference. Experiments on the challenging Citypersons and Caltech datasets show that the proposed method outperforms the state-of-the-art methods on the small-scale pedestrians and occluded pedestrians (e.g., 5.20% and 4.73% improvements on the Caltech).Index Terms-Small-scale pedestrians, occluded pedestrians, location bootstrap, and semantic transition. J. Cao and Y. Pang are with the

show abstract

Multi-label Learning of Part Detectors for Heavily Occluded Pedestrian Detection

Cited by 128 publications

References 19 publications

Occlusion-Aware R-CNN: Detecting Pedestrians in a Crowd

Occlusion-Aware R-CNN: Detecting Pedestrians in a Crowd

Adaptive NMS: Refining Pedestrian Detection in a Crowd

Taking a Look at Small-Scale Pedestrians and Occluded Pedestrians

Contact Info

Product

Resources

About