COUNT Forest: CO-Voting Uncertain Number of Targets Using Random Forest for Crowd Density Estimation

By Viet Quoc Pham, Tatsuo Kozakaya, Osamu Yamaguchi, Ryuzo Okada. 2015

337 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Ocean Engineering

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

In Ocean Engineering

Citations in the corpus

DeepSetNet: Predicting Sets with Deep Neural Networks (2016, methodology): “It is important to bear in mind that unlike many existing approaches that learn to count [1, 5, 12, 20, 24, 35, 50, 51], our main goal is not object counting.”
JHU-CROWD++: Large-Scale Crowd Counting Dataset and A Benchmark Method (2020, methodology): “[46] categorized these methods into (1) detection-based methods [47] (2) regression-based methods [3, 48, 49] and (3) density estimation-based methods [19, 50, 51].”
Attention Scaling for Crowd Counting (2020, methodology): “Recent years have witnessed progressive improvement in crowd counting from traditional methods [7, 10, 26, 39, 2] to CNN based methods [1, 24, 13, 14, 23, 29, 25].”
Iterative Crowd Counting (2018, methodology): “Pham et al. [14] learned a more robust mapping by using a random decision forest to estimate the crowd density map.”
Bayesian Loss for Crowd Count Estimation With Point Supervision (2019, methodology): “This kind of methods [20, 11, 31] take advantage of the location information to learn a map of density values for each training sample and the ﬁnal count estimation can be obtained by summing over the predicted density map.”
Composition Loss for Counting, Density Map Estimation and Localization in Dense Crowds (2018, background): “Crowd counting is active an area of research with works tackling the three aspects of the problem: counting-by-regression [23], [17], [12], [4], [28], density map estimation [17], [7], [29], [20], [30] and localization [18], [22].”
Crowd Counting and Density Estimation by Trellis Encoder-Decoder Networks (2019, methodology): “Earlier approaches strove to compute density maps with hand-crafted features [17, 7] and random forest regressions [7, 29, 49].”
Scale Aggregation Network for Accurate and Efficient Crowd Counting (2018, methodology): “[24] observed the difficulty of learning a linear mapping and used random forest regression to learn a non-linear mapping between local patch features and density maps.”
DecideNet: Counting Varying Density Crowds Through Attention Guided Detection and Density Estimation (2017, methodology): “liminary works directly learn the mapping between features of image patches to crowd counts [19, 23, 40].”
Learning to Count with CNN Boosting (2016, methodology): “[11] suggested additional improvements using modified random forests.”
A Survey of Recent Advances in CNN-based Single Image Crowd Counting and Density Estimation (2017, methodology): “These variety of applications has motivated researchers across various fields to develop sophisticated methods for crowd analysis and related tasks such as counting [15, 16, 20, 41, 17, 85, 35, 41], density estimation [52, 19, 111, 107, 75, 99, 11], segmentation [46, 27], behaviour analysis [6, 86, ”
ADCrowdNet: An Attention-Injective Deformable Convolutional Network for Crowd Understanding (2018, methodology): “[21] use random forest regression to learn a non-linear mapping instead of the linear one.”
CNN-Based cascaded multi-task learning of high-level prior and density estimation for crowd counting (2017, background): “Researchers have attempted to address various aspects of analyzing crowded scenes such as counting [3, 4, 23, 10], density estimation [12, 32, 31, 18, 29, 2], segmentation [11], behavior analysis [24], tracking [21], scene understanding [25] and anomaly detection [19].”
CSRNet: Dilated Convolutional Neural Networks for Understanding the Highly Congested Scenes (2018, methodology): “[33] use random forest regression to learn a non-linear mapping instead of the linear one.”
Generating High-Quality Crowd Density Maps Using Contextual Pyramid CNNs (2017, background): “in [24] proposed to learn a non-linear mapping between local patch features and density maps using a random forest framework.”
BiSeg: Simultaneous Instance Segmentation and Semantic Segmentation with Fully Convolutional Networks (2017, methodology): “Our approach can be applied to the problem of counting objects from crowded scenes [26].”