Imagine the Unseen: Occluded Pedestrian Detection via Adversarial Feature Completion

• URL: http://arxiv.org/abs/2405.01311v1
• Date: Thu, 2 May 2024 14:20:20 GMT
• Title: Imagine the Unseen: Occluded Pedestrian Detection via Adversarial Feature Completion
• Authors: Shanshan Zhang, Mingqian Ji, Yang Li, Jian Yang,
• Abstract summary: We propose to complete features for occluded regions so as to align the features of pedestrians across different occlusion patterns. In order to narrow down the gap between completed features and real fully visible ones, we propose an adversarial learning method. We report experimental results on the CityPersons, Caltech and CrowdHuman datasets.
• Score: 31.488897675973657
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Pedestrian detection has significantly progressed in recent years, thanks to the development of DNNs. However, detection performance at occluded scenes is still far from satisfactory, as occlusion increases the intra-class variance of pedestrians, hindering the model from finding an accurate classification boundary between pedestrians and background clutters. From the perspective of reducing intra-class variance, we propose to complete features for occluded regions so as to align the features of pedestrians across different occlusion patterns. An important premise for feature completion is to locate occluded regions. From our analysis, channel features of different pedestrian proposals only show high correlation values at visible parts and thus feature correlations can be used to model occlusion patterns. In order to narrow down the gap between completed features and real fully visible ones, we propose an adversarial learning method, which completes occluded features with a generator such that they can hardly be distinguished by the discriminator from real fully visible features. We report experimental results on the CityPersons, Caltech and CrowdHuman datasets. On CityPersons, we show significant improvements over five different baseline detectors, especially on the heavy occlusion subset. Furthermore, we show that our proposed method FeatComp++ achieves state-of-the-art results on all the above three datasets without relying on extra cues.

Related papers

• Feature Completion Transformer for Occluded Person Re-identification [25.159974510754992]
  Occluded person re-identification (Re-ID) is a challenging problem due to the destruction of occluders. We propose a Feature Completion Transformer (FCFormer) to implicitly complement the semantic information of occluded parts in the feature space. FCFormer achieves superior performance and outperforms the state-of-the-art methods by significant margins on occluded datasets.
  arXiv  Detail & Related papers  (2023-03-03T01:12:57Z)
• Feature Calibration Network for Occluded Pedestrian Detection [137.37275165635882]
  We propose a novel feature learning method in the deep learning framework, referred to as Feature Network (FC-Net) FC-Net is based on the observation that the visible parts of pedestrians are selective and decisive for detection. Experiments on CityPersons and Caltech datasets demonstrate that FC-Net improves detection performance on occluded pedestrians up to 10%.
  arXiv  Detail & Related papers  (2022-12-12T05:48:34Z)
• ReDFeat: Recoupling Detection and Description for Multimodal Feature Learning [51.07496081296863]
  We recouple independent constraints of detection and description of multimodal feature learning with a mutual weighting strategy. We propose a detector that possesses a large receptive field and is equipped with learnable non-maximum suppression layers. We build a benchmark that contains cross visible, infrared, near-infrared and synthetic aperture radar image pairs for evaluating the performance of features in feature matching and image registration tasks.
  arXiv  Detail & Related papers  (2022-05-16T04:24:22Z)
• An Objective Method for Pedestrian Occlusion Level Classification [6.125017875330933]
  Occlusion level classification is achieved through the identification of visible pedestrian keypoints and through the use of a novel, effective method of 2D body surface area estimation. Experimental results demonstrate that the proposed method reflects the pixel-wise. occlusion level of pedestrians in images and is effective for all forms of. occlusion, including challenging edge cases such as self-occlusion, truncation. and inter-occluding pedestrians.
  arXiv  Detail & Related papers  (2022-05-11T11:27:41Z)
• The Impact of Partial Occlusion on Pedestrian Detectability [5.606792370296115]
  This research introduces a novel, objective benchmark for partially occluded pedestrian detection. It is used to facilitate the objective characterization of pedestrian detection models.
  arXiv  Detail & Related papers  (2022-05-10T11:21:18Z)
• 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)
• Deep Unsupervised Feature Selection by Discarding Nuisance and Correlated Features [7.288137686773523]
  Modern datasets contain large subsets of correlated features and nuisance features. In the presence of large numbers of nuisance features, the Laplacian must be computed on the subset of selected features. We employ an autoencoder architecture to cope with correlated features, trained to reconstruct the data from the subset of selected features.
  arXiv  Detail & Related papers  (2021-10-11T14:26:13Z)
• Holistic Guidance for Occluded Person Re-Identification [7.662745552551165]
  In real-world video surveillance applications, person re-identification (ReID) suffers from the effects of occlusions and detection errors. We introduce a novel Holistic Guidance (HG) method that relies only on person identity labels. Our proposed student-teacher framework is trained to address the problem by matching the distributions of between- and within-class distances (DCDs) of occluded samples with that of holistic (non-occluded) samples. In addition to this, a joint generative-discriminative backbone is trained with a denoising autoencoder, allowing the system to
  arXiv  Detail & Related papers  (2021-04-13T21:50:29Z)
• Generative Partial Visual-Tactile Fused Object Clustering [81.17645983141773]
  We propose a Generative Partial Visual-Tactile Fused (i.e., GPVTF) framework for object clustering. A conditional cross-modal clustering generative adversarial network is then developed to synthesize one modality conditioning on the other modality. To the end, two pseudo-label based KL-divergence losses are employed to update the corresponding modality-specific encoders.
  arXiv  Detail & Related papers  (2020-12-28T02:37:03Z)
• AdaFuse: Adaptive Multiview Fusion for Accurate Human Pose Estimation in the Wild [77.43884383743872]
  We present AdaFuse, an adaptive multiview fusion method to enhance the features in occluded views. We extensively evaluate the approach on three public datasets including Human3.6M, Total Capture and CMU Panoptic. We also create a large scale synthetic dataset Occlusion-Person, which allows us to perform numerical evaluation on the occluded joints.
  arXiv  Detail & Related papers  (2020-10-26T03:19:46Z)
• From Handcrafted to Deep Features for Pedestrian Detection: A Survey [148.35460817092908]
  Pedestrian detection is an important but challenging problem in computer vision. Over the past decade, significant improvement has been witnessed with the help of handcrafted features and deep features. In addition to single-spectral pedestrian detection, we also review multi-spectral pedestrian detection.
  arXiv  Detail & Related papers  (2020-10-01T14:51:10Z)

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.