Extremely Overlapping Vehicle Counting

By Ricardo Guerrero-Gómez-Olmedo, Beatriz Torre-Jiménez, Roberto Javier López-Sastre, Saturnino Maldonado-Bascón, Daniel Oñoro-Rubio. 2015

266 citations recorded by the source corpus.

Subfields: 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 Computer Vision and Pattern Recognition

In Ocean Engineering

Citations in the corpus

Domain Adaptation for Traffic Density Estimation (2021, methodology): “Second, we take into account the TRANCOS dataset.”
ADCrowdNet: An Attention-Injective Deformable Convolutional Network for Crowd Understanding (2018, methodology): “We have evaluated ADCrowdNet on a popular vehicle counting dataset named TRANCOS [10], and ADCrowdNet achieves 32.”
STREETS: A Novel Camera Network Dataset for Traffic Flow (2019, methodology): “The TRANCOS dataset [11] does use a camera network in the highway system surrounding Madrid, Spain.”
Guided Attention Network for Object Detection and Counting on Drones (2019, unknown): “Object counting methods aim to predict the total number of objects in different categories existing in images, such as pedestrian counting [20, 26, 46, 50], vehicle counting [12, 49], goods counting [11, 21] and general object counting [2, 3, 18].”
CSRNet: Dilated Convolutional Neural Networks for Understanding the Highly Congested Scenes (2018, methodology): “TRANCOS [44] Fixed kernel: σ = 10”
Object Counting and Instance Segmentation With Image-Level Supervision (2019, methodology): “Mean absolute error (MAE) between the predicted and the ground-truth local counts are reported for n = 0, 1, 2 and 3, as in [9].”
Towards Perspective-Free Object Counting with Deep Learning (2016, methodology): “Vehicle counting results Table 1 shows a detailed comparison of our models with the state-of-the-art methods [5, 6] reported in [10].”
Learning Short-Cut Connections for Object Counting (2018, methodology): “However, it reports high errors for GAME ( 2 ) and GAME ( 3 ) .”
Rethinking Counting and Localization in Crowds: A Purely Point-Based Framework (2021, methodology): “Additionally, in terms of the evaluation metrics, some farsighted works [7, 32] encourage to adopt patch-level metrics for fine-grained evaluation, but they only provide a rough measure for localization.”
Understanding Traffic Density from Large-Scale Web Camera Data (2017, methodology): “The ground truth object density maps are generated by placing a Gaussian Kernel in the center of each annotated object[16].”