Monocular Pedestrian Detection: Survey and Experiments

By Markus Enzweiler, Dariu M. Gavrila. 2009

1,350 citations recorded by the source corpus.

Subfields: Automotive Engineering, 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 Automotive Engineering

In Computer Vision and Pattern Recognition

Citations in the corpus

The Cityscapes Dataset for Semantic Urban Scene Understanding (2016, background): “Specialized object-centric methods fall somewhere in between by focusing on detecting a certain subset of (mostly dynamic) scene constituents, e.g. [6,12,13,15].”
Skeleton-Based Online Action Prediction Using Scale Selection Network (2019, neutral): “[20], pedestrian detection [21], activity detection [22], [23], [24], [25], etc.”
Context-Based Pedestrian Path Prediction (2014, methodology): “For vision-based pedestrian detection, see recent surveys e.g. [10,12].”
CityPersons: A Diverse Dataset for Pedestrian Detection (2017, background): “INRIA [7], ETH [11], TudBrussels [29], and Daimler [10] represent early efforts to collect pedestrian datasets.”
How Far are We from Solving Pedestrian Detection? (2016, background): “Amongst existing pedestrian datasets [4, 9, 8], KITTI [10] and Caltech-USA are currently the most popular ones.”
SSNet: Scale Selection Network for Online 3D Action Prediction (2018, methodology): “Sliding window based design has been widely used in a series of computer vision tasks, such as object recognition [47], pedestrian detection [12], activity detection [48, 56, 77, 22], etc.”
Effective Fusion Factor in FPN for Tiny Object Detection (2020, background): “[4, 8, 31, 7, 6, 10, 34] are scene-rich and well-annotated datasets used for pedestrian detection task.”
Video-Based Human Behavior Understanding: A Survey (2013, background): “These approaches are mainly based on background segmentation [11].”
Discriminative Autoencoders for Small Targets Detection (2014, background): “Among the rare papers which tried to model small targets explicitly, we can mention the work of [21], which – in addition to introducing a new dataset of 36 × 18 pixels pedestrian images – has shown that good performance can be obtained by combining standard features such as Haar wavelets or HOG fea”
Multiresolution Models for Object Detection (2010, methodology): “We refer the reader to the recent surveys [2, 14] for an overview of contemporary approaches.”
Birdsnap: Large-Scale Fine-Grained Visual Categorization of Birds (2014, background): “For example, in pedestrian detection, knowledge of the ground plane and street layout can restrict a detector to regions of interest [10].”
Learning people detection models from few training samples (2011, background): “This might be explained by the fact that real data and virtual data appear more similar on the lower resolution DaimlerDB [11] automotive test data (pedestrian median height is 47 pixels), while for higher resolution (median pedestrian height on the multi-viewpoint test data is 184 pixel) the classi”
Multiview random forest of local experts combining RGB and LIDAR data for pedestrian detection (2015, background): “With more than a decade of history by now [1], pedestrian detection is still a very challenging task when applied under realistic conditions [2], [3], [4].”
Expecting the Unexpected: Training Detectors for Unusual Pedestrians with Adversarial Imposters (2017, background): “Pedestrian detection is a highly researched topic with mature methods, but most datasets focus on “everyday” scenes of people engaged in typical walking poses on sidewalks [9, 6, 13, 12, 48].”
Object Detection and Tracking for Autonomous Navigation in Dynamic Environments (2010, background): “In recent years, appearance-based object category detection has made great progress, cf. benchmarks such as Dollar et al. (2009), Everingham et al. (2008), and Enzweiler and Gavrila (2009).”
A survey on vision-based human action recognition (2010, methodology): “Different taxonomies have been proposed and here we adopt the hierarchy used by Moeslund et al. [90]: action primitive, action and activity.”
Object Detection in 20 Years: A Survey (2019, methodology): “We refer readers to the following surveys for more details on this topic [60, 303– 307].”
A Review on Video-Based Human Activity Recognition (2013, background): “Enzweiler and Gavrila [93] concentrate on the detection of pedestrians.”
Incremental learning with self-organizing maps (2017, methodology): “In addition, we use two datasets obtained from a visual pedestrian classification benchmark, the Daimler Pedestrian Detection Benchmark[30].”