Detection of multiple, partially occluded humans in a single image by Bayesian combination of edgelet part detectors

By Bo Wu, Ramkant Nevatia. Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1, 2005

945 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/de1ac0baea1f907388ff5fe9fa22f25f406e2ca6

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

1. Luc Van Gool
2. Xiaogang Wang
3. Bernt Schiele
4. Li Fei-Fei
5. Wanli Ouyang
6. Trevor Darrell
7. Dacheng Tao
8. Andrew Zisserman

In Computer Vision and Pattern Recognition

1. Luc Van Gool
2. Xiaogang Wang
3. Dacheng Tao
4. Ming-Hsuan Yang
5. Bernt Schiele
6. Andrew Zisserman
7. Jitendra Malik
8. Yi Yang

Citations in the corpus

• Single-Pedestrian Detection Aided by Multi-pedestrian Detection (2013, background): “Features under investigation include Haar-like features [79], edgelets [87], shapelet [67], histogram of gradients (HOG) [10], dense SIFT [77], bag-of-words [43], integral histogram [66], color histogram [80], gradient histogram [99], covariance descriptor [76], co-occurrence features [69], local bi”
• Respectful cameras: detecting visual markers in real-time to address privacy concerns (2007, background): “[14], people detection [15], and people tracking [16], [17].”
• Real-Time Human Detection Using Relational Depth Similarity Features (2010, methodology): “There has been much research in the past into human detection, and various different methods have been proposed[1][2][3][4][5].”
• Joint Deep Learning for Pedestrian Detection (2013, methodology): “The widely used classification approaches include various boosting classifiers [9, 11, 53], linear SVM [5], histogram intersection kernel SVM [31], latent SVM [17], multiple kernel SVM [48], structural SVM [58], and probabilistic models [2, 32].”
• Context-Aware Crowd Counting (2018, methodology): “Early crowd counting methods [39, 38, 20] tended to rely on counting-by-detection, that is, explicitly detecting”
• Crowd Counting via Adversarial Cross-Scale Consistency Pursuit (2018, background): “Early works estimate the number of pedestrians via head or body detection [32, 18, 31].”
• Human detection from images and videos: A survey (2016, methodology): “The global approach focuses on the whole object (see for example the methods described in [48, 127, 22, 155]) while local methods organise an object as a set of parts constituting the whole (see for example the methods described in [107, 170, 88, 141]).”
• Vehicle detection in aerial imagery : A small target detection benchmark (2016, methodology): “The most efficient features are Haar-like wavelets ( e.g. [59]) computed from integral histograms ( e.g. [60]), edgelets ( e.g. [51]), shapelets ( e.g. [61]), but also histogram of gradients (HOG) ( e.g. [4, 62]), bag-of-words ( e.g. [63]), multi-scale spatial pyramids [64], covariance descriptors (…”
• Coupled Object Detection and Tracking from Static Cameras and Moving Vehicles (2008, background): “This has been helped by the considerable progress of object detection over the last few years [10], [31], [34], [43], [44], [45], which has resulted in state-of-the-art detectors that are applicable in complex outdoor scenes.”
• Learning Short-Cut Connections for Object Counting (2018, methodology): “An intuitive approach to object counting is through object detection [8, 9, 41].”
• Bi-box Regression for Pedestrian Detection and Occlusion Estimation (2018, background): “A common framework for occlusion handling is learning and integrating a set of part detectors to handle a variety of occlusions [36, 28, 12, 11, 22, 21, 25, 23, 43, 31, 44].”
• DeepID-Net: multi-stage and deformable deep convolutional neural networks for object detection (2014, methodology): “The widely used classification approaches include various boosting classifiers [14, 15, 56], linear SVM [9], histogram intersection kernel SVM [34], latent SVM [20], multiple kernel SVM [53], structural SVM [65], and probabilistic models [3, 36].”
• KGSNet: Key-Point-Guided Super-Resolution Network for Pedestrian Detection in the Wild (2020, background): “Driven by the great success of R-CNN [16] for general object detection [32]–[37], a series of CNN-based methods [28], [38]–[45] have been proposed for pedestrian detection in recent years.”