Visible Feature Guidance for Crowd Pedestrian Detection

• URL: http://arxiv.org/abs/2008.09993v2
• Date: Wed, 16 Sep 2020 11:23:38 GMT
• Title: Visible Feature Guidance for Crowd Pedestrian Detection
• Authors: Zhida Huang, Kaiyu Yue, Jiangfan Deng, Feng Zhou
• Abstract summary: We propose Visible Feature Guidance (VFG) for both training and inference. During training, we adopt visible feature to regress the simultaneous outputs of visible bounding box and full bounding box. Then we perform NMS only on visible bounding boxes to achieve the best fitting full box in inference.
• Score: 12.8128512764041
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Heavy occlusion and dense gathering in crowd scene make pedestrian detection become a challenging problem, because it's difficult to guess a precise full bounding box according to the invisible human part. To crack this nut, we propose a mechanism called Visible Feature Guidance (VFG) for both training and inference. During training, we adopt visible feature to regress the simultaneous outputs of visible bounding box and full bounding box. Then we perform NMS only on visible bounding boxes to achieve the best fitting full box in inference. This manner can alleviate the incapable influence brought by NMS in crowd scene and make full bounding box more precisely. Furthermore, in order to ease feature association in the post application process, such as pedestrian tracking, we apply Hungarian algorithm to associate parts for a human instance. Our proposed method can stably bring about 2~3% improvements in mAP and AP50 for both two-stage and one-stage detector. It's also more effective for MR-2 especially with the stricter IoU. Experiments on Crowdhuman, Cityperson, Caltech and KITTI datasets show that visible feature guidance can help detector achieve promisingly better performances. Moreover, parts association produces a strong benchmark on Crowdhuman for the vision community.

Related papers

• Occlusion-Aware Detection and Re-ID Calibrated Network for Multi-Object Tracking [38.36872739816151]
  Occlusion-Aware Attention (OAA) module in the detector highlights the object features while suppressing the occluded background regions. OAA can serve as a modulator that enhances the detector for some potentially occluded objects. We design a Re-ID embedding matching block based on the optimal transport problem.
  arXiv  Detail & Related papers  (2023-08-30T06:56:53Z)
• An Effective Motion-Centric Paradigm for 3D Single Object Tracking in Point Clouds [50.19288542498838]
  3D single object tracking in LiDAR point clouds (LiDAR SOT) plays a crucial role in autonomous driving. Current approaches all follow the Siamese paradigm based on appearance matching. We introduce a motion-centric paradigm to handle LiDAR SOT from a new perspective.
  arXiv  Detail & Related papers  (2023-03-21T17:28:44Z)
• Multi-view Tracking Using Weakly Supervised Human Motion Prediction [60.972708589814125]
  We argue that an even more effective approach is to predict people motion over time and infer people's presence in individual frames from these. This enables to enforce consistency both over time and across views of a single temporal frame. We validate our approach on the PETS2009 and WILDTRACK datasets and demonstrate that it outperforms state-of-the-art methods.
  arXiv  Detail & Related papers  (2022-10-19T17:58:23Z)
• STCrowd: A Multimodal Dataset for Pedestrian Perception in Crowded Scenes [78.95447086305381]
  Accurately detecting and tracking pedestrians in 3D space is challenging due to large variations in rotations, poses and scales. Existing benchmarks either only provide 2D annotations, or have limited 3D annotations with low-density pedestrian distribution. We introduce a large-scale multimodal dataset, STCrowd, to better evaluate pedestrian perception algorithms in crowded scenarios.
  arXiv  Detail & Related papers  (2022-04-03T08:26:07Z)
• Exploring Visual Context for Weakly Supervised Person Search [155.46727990750227]
  Person search has recently emerged as a challenging task that jointly addresses pedestrian detection and person re-identification. Existing approaches follow a fully supervised setting where both bounding box and identity annotations are available. This paper inventively considers weakly supervised person search with only bounding box annotations.
  arXiv  Detail & Related papers  (2021-06-19T14:47:13Z)
• DETR for Crowd Pedestrian Detection [114.00860636622949]
  The proposed detector PED(Pedestrian End-to-end Detector) outperforms both previous EDs and the baseline Faster-RCNN on CityPersons and CrowdHuman. It also achieves comparable performance with state-of-the-art pedestrian detection methods.
  arXiv  Detail & Related papers  (2020-12-12T11:02:05Z)
• Mutual-Supervised Feature Modulation Network for Occluded Pedestrian Detection [10.497367073305806]
  We propose a novel Mutual-Supervised Feature Modulation (MSFM) network to better handle occluded pedestrian detection. MSFM module calculates the similarity loss of full body boxes and visible body boxes corresponding to the same pedestrian. Our approach achieves superior performance compared to other state-of-the-art methods on two challenging pedestrian datasets.
  arXiv  Detail & Related papers  (2020-10-21T03:42:22Z)
• Dense Scene Multiple Object Tracking with Box-Plane Matching [73.54369833671772]
  Multiple Object Tracking (MOT) is an important task in computer vision. We propose the Box-Plane Matching (BPM) method to improve the MOT performacne in dense scenes. With the effectiveness of the three modules, our team achieves the 1st place on the Track-1 leaderboard in the ACM MM Grand Challenge HiEve 2020.
  arXiv  Detail & Related papers  (2020-07-30T16:39:22Z)
• NMS by Representative Region: Towards Crowded Pedestrian Detection by Proposal Pairing [25.050500817717108]
  The heavy occlusion between pedestrians imposes great challenges to the standard Non-Maximum Suppression (NMS) This paper proposes a novel Representative Region NMS approach leveraging the less occluded visible parts, effectively removing the redundant boxes without bringing in many false positives. Experiments on the challenging CrowdHuman and CityPersons benchmarks sufficiently validate the effectiveness of the proposed approach on pedestrian detection in the crowded situation.
  arXiv  Detail & Related papers  (2020-03-28T06:33:54Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.