NSSNet: Scale-Aware Object Counting With Non-Scale Suppression
- 20 October 2020
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 23 (4) , 3103-3114
Abstract
In object counting, objects often exhibit different sizes at different scales, even if they have similar physical sizes in reality. This is particularly true when targeting crowd counting and vehicle counting in intelligent transportation. Failing to model such variations leads to the mismatch between the object size and image scale. To address this problem, existing methods often extract multi-scale features, but they either still generate the single-scale prediction or lack an explicit suppression mechanism to eliminate predictions engendered by inappropriate scales. Our scale analysis manifests that, the single-scale estimation only works well for objects of certain sizes, and a suppression operator is required to isolate the estimation of a specific scale. In this work, we propose a scale-aware counting network termed NSSNet. NSSNet has two key features: it not only i) generates multi-scale predictions but also ii) applies a novel non-scale suppression (NSS) operator to suppress scale-mismatched estimations. NSS is inspired by the widely-used non-maximum suppression (NMS). In contrast to NMS that only reserves the maximum response, NSS filters out those clearly wrong predictions (the remaining predictions may still be from multiple scales). We evaluate NSSNet on four standard crowd and vehicle counting benchmarks and report state-of-the-art performance. We also show the scale adaptability of NSSNet through a controlled multi-scale experiment. Code and pretrained models are available at https://git.io/nssnet.Keywords
Funding Information
- Natural Science Foundation of China (61876211)
This publication has 59 references indexed in Scilit:
- CrowdNet2016
- Deep Residual Learning for Image Recognition2016
- Single-Image Crowd Counting via Multi-Column Convolutional Neural Network2016
- Extremely Overlapping Vehicle Counting2015
- Cross-scene crowd counting via deep convolutional neural networks2015
- Counting and Classification of Highway Vehicles by Regression AnalysisIEEE Transactions on Intelligent Transportation Systems, 2015
- Semisupervised Pedestrian Counting With Temporal and Spatial ConsistenciesIEEE Transactions on Intelligent Transportation Systems, 2014
- Portable Roadside Sensors for Vehicle Counting, Classification, and Speed MeasurementIEEE Transactions on Intelligent Transportation Systems, 2013
- Multi-source Multi-scale Counting in Extremely Dense Crowd Images2013
- Feature Mining for Localised Crowd Counting2012