New features and insights for pedestrian detection

By Stefan Walk, Nikodem Majer, Konrad Schindler, Bernt Schiele. 2010

535 citations recorded by the source corpus.

Subfields: 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 Computer Vision and Pattern Recognition

Citations in the corpus

DeepSetNet: Predicting Sets with Deep Neural Networks (2016, background): “Traditional approaches follow the slidingwindow paradigm [44, 7, 46, 11, 2], where each possible (or rather plausible) image region is scored independently to contain a person or not.”
Pedestrian Detection with Unsupervised Multi-stage Feature Learning (2012, methodology): “Much of the work on pedestrian detection have focused on designing representative and powerful features [5, 9, 8, 38].”
Video Object Detection with an Aligned Spatial-Temporal Memory (2017, methodology): “tecting persons) [54,7]. Later work used hand-designed features by aggregating simple motion cues (based on optical ﬂow, temporal differences, or tracking), and focused mostly on pedestrian detection [51,9,23,2,52,39]. With the recent introduction of ImageNet VID [1], researchers have focused on mor”
Multi-target tracking by continuous energy minimization (2011, methodology): “Here, we detect pedestrians with a sliding window approach using both HOG features [6] and histograms of relative optic flow [18].”
Color attributes for object detection (2012, unknown): “On this dataset, our approach yields a significant gain of 14% in mean AP over conventional state-of-the-art methods.”
Pedestrian Detection: An Evaluation of the State of the Art (2012, methodology): “The filtering strategy used in our previous work [3] was too stringent and resulted in underreporting of detector performance (this was also independently observed by Walk et al. [28]).”
Video-Based Human Behavior Understanding: A Survey (2013, background): “Other works analyzed the periodic change in the optical flow [52], [53].”
A discriminative deep model for pedestrian detection with occlusion handling (2012, methodology): “Since most other relevant publications [28, 1] test on Caltech training dataset and use other datasets as training datasets, we choose the Caltech training dataset as our testing set and the INRIA training dataset as our training set to be consistent with them.”
What Can Help Pedestrian Detection? (2017, background): “, optical flow [1] and motion [29]) have been proved to be beneficial to traditional pedestrian detectors [28, 23] working on videos.”
Pedestrian Detection at Day/Night Time with Visible and FIR Cameras: A Comparison (2016, background): “[8], many other features and combinations of features have been proposed in the last decade, like HOG plus local binary patterns (LBP) [9], HOG plus color self similarity (CSS) [10], Haar features plus histogram of edges [11], integral channels [12] or macrofeatures [13], just to name a few.”
Exploring Weak Stabilization for Motion Feature Extraction (2013, background): “Significant progress has been made in static-image object detection over the past few years, in large part due to the improvement of lowlevel features coupled with classifiers such as SVMs [7] and boosting [26].”
Robust Multi-resolution Pedestrian Detection in Traffic Scenes (2013, background): “In recent years, especially due to the popularity of gradient features, pedestrian detection field has achieved impressive progresses in both effectiveness [6, 31, 43, 41, 19, 33] and efficiency [25, 11, 18, 4, 10].”
Taking a deeper look at pedestrians (2015, methodology): “JointDeep, MultiSDP, and SDN use a HOG+CSS+linear SVM detector (similar to [49]) for proposals.”
Multiple object tracking: A literature review (2014, methodology): “As it is related with motion, it is utilized to encode motion information [78], [79].”
Continuous Energy Minimization for Multitarget Tracking (2014, background): “oriented gradients (HOG) [13] and histograms of relative optic flow (HOF) [38].”
Fast Feature Pyramids for Object Detection (2014, unknown): “MF+Motion [76] – 51 55 60 –”