A discriminative deep model for pedestrian detection with occlusion handling

By Wanli Ouyang, Xiaogang Wang. 2012 IEEE Conference on Computer Vision and Pattern Recognition, 2012

318 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Ocean Engineering

View Paper: https://www.semanticscholar.org/paper/ad64a8facc91db1df448f7d933b224a127554bf0

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 Ocean Engineering

Citations in the corpus

Vehicle detection in aerial imagery : A small target detection benchmark (2016, unknown): “[54]) and more recently, Convolutional Deep Networks[11, 55, 56, 57, 58].”
A Deep Sum-Product Architecture for Robust Facial Attributes Analysis (2013, methodology): “The subsequent methods [21, 20, 18, 16] overcame this problem by learning noise models from training data.”
Learning Deep Representation with Large-Scale Attributes (2015, background): “Deep learning is effective for many vision tasks [17, 34, 43, 14, 19, 11, 26, 28, 23, 25, 44, 47, 21, 49, 5].”
Deep Learning Strong Parts for Pedestrian Detection (2015, methodology): “For example, it outperforms DBN-Isol, DBN-Mut and JointDeep, which are also based on part modeling, by 41, 36 and 26 percent.”
Multi-source Deep Learning for Human Pose Estimation (2014, methodology): “Our approaches in [37, 38, 36, 28] learns feature learning, translational deformation, and occlusion relationship in pedestrian detection; the approach in [48] learns relational filter pairs in face verification.”
Taking a deeper look at pedestrians (2015, background): “chines (RBMs) trained to reason about parts and occlusion (DBN-Isol) [32].”
Perceptual Generative Adversarial Networks for Small Object Detection (2017, background): “Recently, deep learning methods have greatly boosted the performance of pedestrian detection [29, 33, 28, 36, 41].”
DETRAC: A New Benchmark and Protocol for Multi-Object Tracking (2015, unknown): “ 566 ! D P 2005 ETH [16] 490 - 1.6k 1.8k - 9.4k ! ! D P 2007 NICTA [31] - - 18.7k - - 6.9k ! D P 2008 DDB [15] - - 15.6k21.8k - 56.5k ! D P 2009 Caltech [14] 67k - 192k 65k - 155k ! ! D P ! 2012 CUHK [30] - - - 1.06k - - ! D P 2012 KAIST [23] 50.2k - 41.5k45.1k - 44.7k ! ! D P ! ! 2015 KITTI-MOD [20”
Ten Years of Pedestrian Detection, What Have We Learned? (2014, background): “Note that these works use edge and colour features [40,34,28], or initialise network weights to edge-sensitive ﬁlters, rather than discovering features from raw pixel values as usually done in deep architectures.”
Occlusion-aware R-CNN: Detecting Pedestrians in a Crowd (2018, methodology): “Several methods [35,36,49,32,72,56,46,17,16] use part-based model to describe”
Occluded Pedestrian Detection Through Guided Attention in CNNs (2018, methodology): “Different features are employed, including hand-crafted features [7, 19] and deep convolutional features [21, 26].”
DeepID-Net: Deformable deep convolutional neural networks for object detection (2014, background): “Because of the power on learning feature representation, deep models have been widely used for object recognition, detection and other vision tasks [36, 54, 19, 37, 61, 17, 22, 14, 28, 30, 55, 56, 27, 23, 41, 43, 41, 42, 25, 26, 24, 58].”
Single-Pedestrian Detection Aided by Multi-pedestrian Detection (2013, methodology): “1) Classification approaches used include various boosting classifiers [32, 9, 37], SVM classifiers [4, 21, 13, 43], and grammar models [16] and deep model [23].”
Scale-Aware Fast R-CNN for Pedestrian Detection (2015, background): “Some recent works focus on improving the performance of pedestrian detection using deep learning methods [24], [32], [23], [35].”
A Comparative Analysis of Object Detection Metrics with a Companion Open-Source Toolkit (2021, background): “The human visual system can effectively distinguish objects in different environments and contexts, even under a variety of constraints such as low illumination [1], color differences [2], and occlusions [3,4].”