Pedestrian Detection In Crowded Scenes Research Articles

Context feature fusion and enhanced non-maximum suppression for pedestrian detection in crowded scenes

Context feature fusion and enhanced non-maximum suppression for pedestrian detection in crowded scenes

Multi-Attribute NMS: An Enhanced Non-Maximum Suppression Algorithm for Pedestrian Detection in Crowded Scenes

Removing duplicate proposals is a critical process in pedestrian detection, and is usually performed via Non-Maximum Suppression (NMS); however, in crowded scenes, the detection proposals of occluded pedestrians are hard to distinguish from duplicate proposals, making the detection results inaccurate. In order to address the above-mentioned problem, the authors of this paper propose a Multi-Attribute NMS (MA-NMS) algorithm, which combines density and count attributes in order to adaptively adjust suppression, effectively preserving the proposals of occluded pedestrians while removing duplicate proposals. In order to obtain the density and count attributes, an attribute branch (ATTB), which uses a context extraction module (CEM) to extract the context of pedestrians, and then, concatenates the context with the features of pedestrians in order to predict both the density and count attributes simultaneously, is also proposed. With the proposed ATTB, a pedestrian detector, based on MA-NMS, is constructed for pedestrian detection in crowded scenes. Extensive experiments are conducted using the CrowdHuman and CityPersons datasets, and the results show that the proposed method outperforms mainstream methods on AP (average precision), Recall, and MR−2 (log-average miss rate), sufficiently validating the effectiveness of the proposed MA-NMS algorithm.

Improved YOLOX for pedestrian detection in crowded scenes

Improved YOLOX for pedestrian detection in crowded scenes

AD-DETR: DETR with asymmetrical relation and decoupled attention in crowded scenes.

Pedestrian detection in crowded scenes is widely used in computer vision. However, it still has two difficulties: 1) eliminating repeated predictions (multiple predictions corresponding to the same object); 2) false detection and missing detection due to the high scene occlusion rate and the small visible area of detected pedestrians. This paper presents a detection framework based on DETR (detection transformer) to address the above problems, and the model is called AD-DETR (asymmetrical relation detection transformer). We find that the symmetry in a DETR framework causes synchronous prediction updates and duplicate predictions. Therefore, we propose an asymmetric relationship fusion mechanism and let each query asymmetrically fuse the relative relationships of surrounding predictions to learn to eliminate duplicate predictions. Then, we propose a decoupled cross-attention head that allows the model to learn to restrict the range of attention to focus more on visible regions and regions that contribute more to confidence. The method can reduce the noise information introduced by the occluded objects to reduce the false detection rate. Meanwhile, in our proposed asymmetric relations module, we establish a way to encode the relative relation between sets of attention points and improve the baseline. Without additional annotations, combined with the deformable-DETR with Res50 as the backbone, our method can achieve an average precision of 92.6%, MR$ ^{-2} $ of 40.0% and Jaccard index of 84.4% on the challenging CrowdHuman dataset. Our method exceeds previous methods, such as Iter-E2EDet (progressive end-to-end object detection), MIP (one proposal, multiple predictions), etc. Experiments show that our method can significantly improve the performance of the query-based model for crowded scenes, and it is highly robust for the crowded scene.

High quality proposal feature generation for crowded pedestrian detection

Occlusion is a severe problem for pedestrian detection in crowded scenes. Due to the diversity of pedestrian postures and occlusion forms, leading to false detection and missed detection. In this paper, we propose a high quality proposal feature generation pedestrian detection algorithm to improve detection performance. Firstly, Dual-Region Feature Generation (DRFG) is proposed to generate high quality proposal features. Specifically, visible regions with less occlusion are introduced and low-precision proposals are generated for both the full-body and visible regions respectively. Then, proposals are respectively selected from the two kinds of proposals mentioned above to match in pairs, so as to guarantee a strong correspondence in information between the two proposals. Afterwards, the successfully matched proposal features are fused by Selective Kernel Feature Fusion (SKFF) to generate high quality proposal features. Secondly, Paired Multiple Instance Prediction(PMIP) is performed on the fused features to generate multiple prediction branches, and each prediction branch generates full-body and visible prediction box. Finally, Paired Non-Maximum Suppression(PNMS) is applied to the prediction boxes to reduce the false positives. Experiments have been conducted on CrowdHuman [1] and CityPersons [2] datasets. Comparing with baseline, our methods have achieved 5.9% AP and 1.5% MR−2 improvement on the above two datasets, sufficiently verifying the effectiveness of our methods in crowded pedestrian detection.

Co-Head Pedestrian Detection in Crowded Scenes

Co-Head Pedestrian Detection in Crowded Scenes

Dual-Task Integrated Network for Fast Pedestrian Detection in Crowded Scenes

Dual-Task Integrated Network for Fast Pedestrian Detection in Crowded Scenes

PedHunter: Occlusion Robust Pedestrian Detector in Crowded Scenes

Pedestrian detection in crowded scenes is a challenging problem, because occlusion happens frequently among different pedestrians. In this paper, we propose an effective and efficient detection network to hunt pedestrians in crowd scenes. The proposed method, namely PedHunter, introduces strong occlusion handling ability to existing region-based detection networks without bringing extra computations in the inference stage. Specifically, we design a mask-guided module to leverage the head information to enhance the feature representation learning of the backbone network. Moreover, we develop a strict classification criterion by improving the quality of positive samples during training to eliminate common false positives of pedestrian detection in crowded scenes. Besides, we present an occlusion-simulated data augmentation to enrich the pattern and quantity of occlusion samples to improve the occlusion robustness. As a consequent, we achieve state-of-the-art results on three pedestrian detection datasets including CityPersons, Caltech-USA and CrowdHuman. To facilitate further studies on the occluded pedestrian detection in surveillance scenes, we release a new pedestrian dataset, called SUR-PED, with a total of over 162k high-quality manually labeled instances in 10k images. The proposed dataset, source codes and trained models are available at https://github.com/ChiCheng123/PedHunter.

Learning Pixel-Level and Instance-Level Context-Aware Features for Pedestrian Detection in Crowds

Pedestrian detection in crowded scenes is an intractable problem in computer vision, in which occlusion often presents a great challenge. In this paper, we propose a novel context-aware feature learning method for detecting pedestrians in crowds, with the purpose of making better use of context information for dealing with occlusion. Unlike most current pedestrian detectors that only extract context information from a single and fixed region, a new pixel-level context embedding module is developed to integrate multi-cue context into a deep CNN feature hierarchy, which enables access to the context of various regions by multi-branch convolution layers with different receptive fields. In addition, to utilize the distinctive visual characteristics formed by pedestrians that appear in groups and occlude each other, we propose a novel instance-level context prediction module which is actually implemented by a two-person detector, to improve the one-person detection performance. Applying with these strategies, we achieve an efficient and lightweight detector that can be trained in an end-to-end fashion. We evaluate the proposed approach on two popular pedestrian detection datasets, i.e., Caltech and CityPersons. The extensive experimental results demonstrate the effectiveness of the proposed method, especially under heavy occlusion cases.

Joint components based pedestrian detection in crowded scenes using extended feature descriptors

This paper presents a framework for human detection based on the joint component model using extended feature descriptors. This framework provides two contributions for handling the partially occluded problem of pedestrian detection in crowded environments. First, it presents feature descriptors based on extension of two well-known feature descriptors for accommodation in partially occluded pedestrian detection. The feature descriptors, which use multiple scale blocks-based histograms of oriented gradients (MHOG) and parallelogram based Haar-like feature (PHF), are proposed for improving the accuracy of the detection system. As a result of using MHOG, an extensive feature space allows for the obtaining of highly discriminated features, which supports robust detection. On the other hand, the PHF is adaptive for the shape of human limbs in detection of pedestrians. This contribution also presents special data structures to store image intensities and image gradients for using an integral image method, which is helpful for fast computation for both feature descriptors. Second, the joint component model for human detection is proposed for the training and detecting of pedestrians in crowded scenes. The proposed detection method based on fusion of the boosting technique and the support vector machine (SVM) is presented. The SVM is known as one of the most efficient learning models for classification. The advantage of boosting is a strong classifier based on a combination set of weak classifiers. However, the performance of boosting depends on the kernel of element classifier. The method based on the extended feature descriptors and the joint component model is helpful for constructing an efficient classification. The experimental results demonstrate that this method for pedestrian detection outperforms current methods in crowded situations under a variety of outdoor environments.

Using Weighted Part Model for Pedestrian Detection in Crowded Scenes Based on Image Segmentation

In this paper, we present a pedestrian detection approach based on weighted part model in crowded scenes, instead of the deformable part model. To avoid the low detection rate in crowded scenes, a pedestrian cascaded detection algorithm based on selective search segmentation is used. Compared with the state-of-the-art methods on the database of PASCAL VOC2007 dataset and PETS2009 dataset, the proposed method achieves a better accuracy (42.3 and about 12 percent improvement) without decreasing the detection speed.

Kinect‐Based Pedestrian Detection for Crowded Scenes

AbstractPedestrian movement data including volumes, walking speeds, and trajectories are essential in transportation engineering, planning, and research. Although traditional image‐based pedestrian detectors provide very rich information, their performance degrades quickly with increased occurrence of occlusion. The three‐dimensional sensing capabilities of Microsoft's Kinect present a potential cost‐effective solution for occlusion‐robust pedestrian detection. This article proposes an efficient pedestrian detection approach for crowded scenes by fusing RGB and depth images from the Kinect. More specifically, we first extract the pedestrian contour regions from RGB images using background subtraction. Then, we develop a region clustering algorithm to extract pedestrians from the contour regions using depth information. Finally, a tracking and counting algorithm is designed to acquire pedestrian volumes. The proposed approach was proven effective with an average detection accuracy of 93.1% at 20 frames per second. These results demonstrate the feasibility of using the low‐cost Kinect device for real‐world pedestrian detection in crowded scenes.