An Experimental Study on Pedestrian Classification

By Stefan Munder, Dariu M. Gavrila. 2006

662 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Media Technology

How researchers see this paper

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

In Computer Vision and Pattern Recognition

In Media Technology

Citations in the corpus

Incremental Learning Through Deep Adaptation (2017, methodology): “Our evaluation protocol resembles that of [2], in the following ways: ﬁrst, we test our network on a variety of datasets 1 , namely: Caltech-256 [9], CIFAR-10 [15], Daimler [23] , GTSR [29], Omniglot [22] , Plankton imagery data [3] , Human Sketch dataset [6] and SVHN [24] .”
Detecting Pedestrians by Learning Shapelet Features (2007, background): “Munder and Gavrila [11] studied the problem of pedestrian classification with different features and classifiers.”
EuroCity Persons: A Novel Benchmark for Person Detection in Traffic Scenes (2018, background): “, Daimler-CB [16], CVC [17], andNICTA [18]) and detection (e.”
Max-margin additive classifiers for detection (2009, methodology): “Daimler Chrysler Pedestrian Dataset Our second set of experiments are on the Daimler Chrysler Pedestrian Benchmark dataset, created by Munder and Gavrila [27].”
Multi-cue Pedestrian Detection and Tracking from a Moving Vehicle (2007, background): “As Munder and Gavrila (2006) shows, the network is nevertheless able to capture relevant feature information from a local neighborhood.”
Pedestrian Detection: An Evaluation of the State of the Art (2012, methodology): “Older data sets, including the MIT [16], CVC [19], and NICTA [22] pedestrian data sets and the Daimler classification benchmark (Daimler-CB) [21], tend to contain cropped pedestrian windows only.”
Human detection using partial least squares analysis (2009, methodology): “Finally, we also demonstrate our method on detecting humans at very low resolutions (18 × 36 pixels) using the DaimlerChrysler dataset [18].”
Cat Head Detection - How to Effectively Exploit Shape and Texture Features (2008, methodology): “The image features are directly extracted from the image, such as intensity values [14], image patch [6], PCA coefficients [11], and wavelet coefficients [12,16,18].”
Survey of Pedestrian Detection for Advanced Driver Assistance Systems (2010, methodology): “…approach (i.e., target is detected as a whole) in [55], [70], Gavrila et al. propose a classifier that uses image gray-scale pixels as features and a neural network with local receptive fields (NN-LRFs [87]) as the learning machine that classifies the candidate ROIs generated by the Chamfer System.”
Pedestrian Detection: The Elephant In The Room (2020, background): “Over the years, several datasets for pedestrian detection have been created such as Town Center [3], USC [39], DaimlerDB [26], INRIA [10], ETH [13], and TUDBrussels [38].”
Monocular Pedestrian Detection: Survey and Experiments (2009, background): “Compared to previous pedestrian data sets, the availability of sequential images means that also hypothesis generation and tracking components of pedestrian systems can be evaluated, unlike with [28], [46], [49].”
Pedestrian Detection via Classification on Riemannian Manifolds (2008, neutral): “Ç”
An HOG-LBP human detector with partial occlusion handling (2009, neutral): “The results of The Pascal Challenge from 2005 to 2008 [12] and the recent research [8, 13, 15, 28, 18, 21] indicate that sliding window classifiers are presently the predominant method being used in object detection, or more specifically, human detection, due to their good performance.”
Vehicle detection in aerial imagery : A small target detection benchmark (2016, background): “[12, 13, 14, 15, 16]) – which is related to our problem but covers different needs – only a few of them specifically address object detection.”
Pedestrian Classification and Detection in Far Infrared Images (2015, methodology): “This approach is widely used by the computer vision community in different tasks even in infrared imagery [7–11].”