Example-Based Object Detection in Images by Components

By A. Mohan, Constantine Papageorgiou, Tomaso A. Poggio. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2001

1,177 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/448bd4e124175ad358078a7b930ecad994c97812

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

Robust Object Detection with Interleaved Categorization and Segmentation (2008, methodology): “Mohan et al. (2001) use a set of hand-deﬁned appearance parts, but learn an SVM-based conﬁguration classiﬁer for pedestrian detection.”
Survey of Pedestrian Detection for Advanced Driver Assistance Systems (2010, background): “Mohan et al. [74] use HWs and a quadratic SVM to independently classify four human parts (head, legs, right arm, and left arm).”
Recovering human body configurations: combining segmentation and recognition (2004, background): “More recent developments in pedestrian detection, such as Mohan et al. [7] and Viola et al. [18], are fairly successful in detecting people in common standing poses.”
Research Advances and Challenges of Autonomous and Connected Ground Vehicles (2019, methodology): “The features for the appearance-based pedestrian detection methods mainly include histogram of oriented gradients (HOG) [170], scale invariant feature transform (SIFT) [171], [172] and Haar wavelet [173], [174].”
Multimodal Video Indexing: A Review of the State-of-the-art (2004, background): “In [49] people detection is taken one step further, detecting not only the head, but the whole human body.”
A Survey of Recent Advances in Face Detection (2010, methodology): “In the literature, there had been many component-based object detectors that relied on semantically meaningful component detectors [112, 63, 5].”
Detection of multiple, partially occluded humans in a single image by Bayesian combination of edgelet part detectors (2005, methodology): “Nonetheless, we show a comparison with methods in [1] and [4] as they both use the MIT dataset that was available to us.”
Learning to detect objects in images via a sparse, part-based representation (2004, methodology): “Part-based representations for object detection form the basis for a number of theories of biological vision [2], [3], [4], [5], and have also been shown to offer advantages in computational approaches [6].”
Artificial vision in road vehicles (2002, methodology): “The system devised at the AI Lab of MIT [58] for automotive applications fuses the detection and validation steps into one.”
An Experimental Study on Pedestrian Classification (2006, background): “Support Vector Machines (SVM) [12] have evolved as a standard tool for a broad range of classification tasks, including pedestrian classification [5], [9].”
Human Detection via Classification on Riemannian Manifolds (2007, neutral): “Later, the work was extended to multiple classifiers trained to detect human parts, and the responses inside the detection window are combined to give the final decision [14].”
Cat Head Detection - How to Effectively Exploit Shape and Texture Features (2008, background): “For example, the human can be modeled as assemblies of parts [9,10] and the face can be detected using component detection [5].”
Independent component analysis of Gabor features for face recognition (2003, methodology): “Recent approaches emphasize on data-driven learning-based techniques, such as the statistical modeling methods [31], [43], [44], the neural network-based learning methods [40], [44], the statistical learning theory and SVM-based methods [ 32 ], the Markov random field based methods [39], and the col”
Histograms of oriented gradients for human detection (2005, neutral): “We have shown that using locally normalized histogram of gradient orientations features similar to SIFT descriptors [12] in a dense overlapping grid gives very good results for person detection, reducing false positive rates by more than an order of magnitude relative to the best Haar wavelet based ”
Co-occurrence Histograms of Oriented Gradients for Pedestrian Detection (2009, methodology): “The classifier is an RBF-kernel SVM.”
Multiresolution Models for Object Detection (2010, background): “Recent work has focused on models for handling pose variation [15,11,16,17,18], reducing complexity of learning [19,20]), and multicue combination [21,22].”
Empirical Analysis of Detection Cascades of Boosted Classifiers for Rapid Object Detection (2003, background): “Thus, for non-overlapping rectangles we have W H× r x y w h α, , , ,( )= 0 x x w W≤+,≤ 0 y y h H≤+,≤ x y 0≥, w h 0>, α 0° 45°,{ }∈ RecSum r( ) featureI ωi RecSum ri( )⋅ i I∈ 1 … N, ,{ }= ∑= ωi ℜ∈ ri N 2= .”