Informed Haar-Like Features Improve Pedestrian Detection

By Shanshan Zhang, Christian Bauckhage, Armin Bernd Cremers. 2014 IEEE Conference on Computer Vision and Pattern Recognition, 2014

315 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/d1719d36b08f8b6dad6f500ddc202fb74ef81caf

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

Scale-Aware Fast R-CNN for Pedestrian Detection (2015, methodology): “Hand-crafted Model: The models based on hand-crafted features have been widely used for object detection [5], [38], [40], [7], [46], [6], [45], [10], [47], [27], [26].”
Ten Years of Pedestrian Detection, What Have We Learned? (2014, methodology): “InformedHaar [43] obtains top results by using a set of Haar-like features manually designed for the pedestrian detection task.”
Virtual to Real Adaptation of Pedestrian Detectors (2020, background): “The first class of detectors is based on handcrafted features, such as ICF (Integral Channel Features) [14, 15, 16, 17, 18].”
Real-Time Pedestrian Detection with Deep Network Cascades (2015, methodology): “Some methods focus on improving the base features used [6, 9, 10, 42], whereas others focus on the learning algorithms [13, 25], or other techniques such as incorporating Deformable Parts Models [33, 40] or using context [13, 29, 40, 41].”
Occlusion-aware R-CNN: Detecting Pedestrians in a Crowd (2018, methodology): “, [11,53,3,64,39,63,32,31,33,26,62,51,8,2]), which demonstrates the effectiveness of the proposed method in pedestrian detection.”
Convolutional Channel Features (2015, background): “For comparison, we train an Aggregate Channel Features (ACF [11]) model and a Locally Decorrelated Channel Features (LDCF [39]) model as two baselines using the open source toolbox [10].”
Computer vision and deep learning techniques for pedestrian detection and tracking: A survey (2018, methodology): “Since occlusions are one of the most discussed problems in literature [25,26,6 8,82,93,14 9,193] , deep learning allowed to strengthen the detection of single parts in order to ﬁnd and correctly classify occluded pedestrian [82,88,115,116] .”
EuroCity Persons: A Novel Benchmark for Person Detection in Traffic Scenes (2018, methodology): “Deformable Part Models (DPM) using Histograms of Oriented Gradients (HOG) features [36], [37], [38], and Decision Forests using ICF features [39], [40], [41], [42] were until a few years ago the established pedestrian detection methods [12].”
Learning Complexity-Aware Cascades for Deep Pedestrian Detection (2015, methodology): “Instead of empirical filter design, Zhang et al [36] exploited prior knowledge about pedestrian shape to design informed filters.”
Pedestrian detection with a Large-Field-Of-View deep network (2015, background): “The InformedHaar [38] classiﬁer is the best so far with average miss rate at 34.6%.”
Filtered channel features for pedestrian detection (2015, methodology): “We propose a framework for filtered channel features (see figure 1) that unifies multiple top performing methods [8, 1, 45, 25], and that enables a systematic exploration of different filter banks.”
How Far are We from Solving Pedestrian Detection? (2016, background): “Following the success of integral channel feature detector (ICF) [6, 5], many variants [21, 23, 15, 17, 22] were proposed and showed significant improvement.”
Multispectral pedestrian detection: Benchmark dataset and baseline (2015, methodology): “In addition, the ACF pedestrian detector [9] is widely used as a basis algorithm for the concurrent state-of-the-art pedestrian detectors [20, 22, 29].”
Taking a deeper look at pedestrians (2015, methodology): “What is special about the resulting network is that it has not been trained by back-propagation, but by Adaboost [6].”