Pedestrian detection in crowded scenes

By Bastian Leibe, Edgar Seemann, Bernt Schiele. 2005

1,013 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

End-to-End People Detection in Crowded Scenes (2015, methodology): “Early work employed a codebook of local features and Hough voting [13, 2], but still required complex tuning and multi-stage pipelines.”
Single-Pedestrian Detection Aided by Multi-pedestrian Detection (2013, background): “Features under investigation include Haar-like features [79], edgelets [87], shapelet [67], histogram of gradients (HOG) [10], dense SIFT [77], bag-of-words [43], integral histogram [66], color histogram [80], gradient histogram [99], covariance descriptor [76], co-occurrence features [69], local bi”
A mobile vision system for robust multi-person tracking (2008, background): “Several instantiations of this concept have been successfully demonstrated in recent years, among them the feedback from recognition to segmentation [4] [17], from geometry estimation to object detection [13] [15], and the often-used feedback from tracking to detection (e.g. [16]).”
Survey of Pedestrian Detection for Advanced Driver Assistance Systems (2010, methodology): “Chamfer matching is used to both verify and refine the found pedestrian shapes in [109].”
Efficient Mining of Frequent and Distinctive Feature Configurations (2007, methodology): “We start by summarizing the most important concepts and the terminology of association rule mining.”
The 2005 PASCAL Visual Object Classes Challenge (2005, background): “The ISM in itself is an interesting model, as it has recently shown impressive results on challenging object class detections problems [30].”
Detection and Tracking of Multiple, Partially Occluded Humans by Bayesian Combination of Edgelet based Part Detectors (2007, neutral): “Some methods use spatially global features as in Gavrila (2000), Felzenszwalb (2001) and Leibe et al. (2005); others use spatially local features as in Papageorgiou et al. (1998), Mohan et al. (2001), Viola et al. (2003), Mikolajczyk et al. (2004), Wu et al. (2005), Leibe et al. (2005), and Dalal…”
DecideNet: Counting Varying Density Crowds Through Attention Guided Detection and Density Estimation (2017, methodology): “Low-level features [8, 18, 27, 34] are then used for feature representation.”
Counting Vehicles with Cameras (2018, methodology): “In the monolithic detection the classifier is trained in order to recognize the whole object we want to detect [7], while in the part-based detection we looking for specific parts of the object (such as head and shoulders for people detection) [9].”
Pedestrian Detection: An Evaluation of the State of the Art (2012, background): “These appear most promising for low to medium resolution settings, under which segmentation [35] or keypoint [36], [37] based methods often fail.”
People tracking in RGB-D data with on-line boosted target models (2011, background): “In the computer vision literature, the problem of detecting, tracking and modeling humans has been extensively studied [7], [8], [9], [10].”
People-tracking-by-detection and people-detection-by-tracking (2008, methodology): “This research has been facilitated by the impressive advances in people detection methods [24, 3, 16].”
A discriminative deep model for pedestrian detection with occlusion handling (2012, methodology): “Most existing approaches [4, 10, 19, 29, 32, 33] assumed that the visibility of a part is independent of other parts and estimated the visibility by hard-thresholding the detection scores of parts.”
Occlusion-aware R-CNN: Detecting Pedestrians in a Crowd (2018, background): “[24] propose an implicit shape model to generate a set of pedestrian hypotheses that are further refined to obtain the visible regions.”
Privacy preserving crowd monitoring: Counting people without people models or tracking (2008, methodology): “This is a canonical example of a problem that vision technology addresses with privacy invasive methods: detect the people in the scene [3, 4, 5, 6, 7], track them over time [8, 9, 10], and count the number of tracks.”
Evaluation of Features Detectors and Descriptors based on 3D Objects (2005, background): “[24] compared detectors and descriptors when they are integrated in the framework of the full recognition system from [15].”