Published on Fri Apr 20 2018

An Aggregated Multicolumn Dilated Convolution Network for Perspective-Free Counting

Diptodip Deb, Jonathan Ventura

We propose the use of dilated filters to construct an aggregation module for perspective-free counting. Our experiments show that our proposed network outperforms the state-of-the-art on many benchmark datasets.

0
0
0
Abstract

We propose the use of dilated filters to construct an aggregation module in a multicolumn convolutional neural network for perspective-free counting. Counting is a common problem in computer vision (e.g. traffic on the street or pedestrians in a crowd). Modern approaches to the counting problem involve the production of a density map via regression whose integral is equal to the number of objects in the image. However, objects in the image can occur at different scales (e.g. due to perspective effects) which can make it difficult for a learning agent to learn the proper density map. While the use of multiple columns to extract multiscale information from images has been shown before, our approach aggregates the multiscale information gathered by the multicolumn convolutional neural network to improve performance. Our experiments show that our proposed network outperforms the state-of-the-art on many benchmark datasets, and also that using our aggregation module in combination with a higher number of columns is beneficial for multiscale counting.

Mon Sep 16 2019
Computer Vision
Perspective-Guided Convolution Networks for Crowd Counting
A novel perspective-guided convolution (PGC) for crowd counting. PGCNet uses perspective information to guide the spatially variant smoothing of feature maps.
0
0
0
Thu Jul 08 2021
Computer Vision
Crowd Counting via Perspective-Guided Fractional-Dilation Convolution
The proposed PFDNet is constructed by stacking multiple Perspective-guided Fractional-Dilation Convolutions (PFC) on a VGG16-BN backbone. By introducing a novel generalized dilation convolution operation, the PFC can handle fractional dilation ratios in the spatial domain.
2
0
0
Thu Jul 05 2018
Computer Vision
Revisiting Perspective Information for Efficient Crowd Counting
Crowd counting is the task of estimating people numbers in crowd images. A major challenge of this task lies in the perspective distortion, which results in drastic person scale change in an image. We propose a perspective-aware convolutional neural network (PACNN) for efficient crowd counting.
0
0
0
Mon Nov 21 2016
Computer Vision
Crowd Counting by Adapting Convolutional Neural Networks with Side Information
Computer vision tasks often have side information available that is helpful to solve the task. For crowd counting, the camera perspective gives a clue about the appearance and scale of people in the scene. In order to incorporate the available side information, we propose an adaptive convolutional neural network (ACNN)
0
0
0
Wed May 16 2018
Computer Vision
Crowd Counting by Adaptively Fusing Predictions from an Image Pyramid
Scale variations and perspective distortion can lead to huge scale changes of the object size. Hydra-CNN and MCNN uses three columns, each with different filter sizes, to extract features at different scales. It is more effective and efficient to progressivelyresize the input fed into the network.
0
0
0
Mon Nov 13 2017
Computer Vision
Crowd counting via scale-adaptive convolutional neural network
Crowd counting is to automatically estimate the pedestrian number in crowd images. State-of-the-art approaches employ multi-column CNN architectures to regress density maps. We propose a scale-adaptive CNN (SaCNN) architecture with a backbone of fixed small receptive fields.
0
0
0