# Counting dense object of multiple types based on feature enhancement

## TL;DR

This paper introduces a new method for counting multiple types of dense objects, like vehicles and pedestrians, in complex traffic scenes using feature enhancement.

## Contribution

The novel method enhances features for multi-class dense object counting in complex traffic scenes using a dual-subnet model.

## Key findings

- The proposed method achieves high-quality two-channel predicted density maps for counting vehicles and pedestrians.
- It outperforms state-of-the-art counting networks in dense object counting tasks.
- The model uses a classification subnet to assist regression subnets in distinguishing and counting multiple object types.

## Abstract

Accurately counting the number of dense objects in an image, such as pedestrians or vehicles, is a challenging and practical task. The existing density map regression methods based on CNN are mainly used to count a class of dense objects in a single scene. However, in complex traffic scenes, objects such as vehicles and pedestrians usually exist at the same time, and multiple classes of dense objects need to be counted simultaneously.

To solve the above issues, we propose a new multiple types of dense object counting method based on feature enhancement, which can enhance the features of dense counting objects in complex traffic scenes to realize the classification and regression counting of dense vehicles and people. The counting model consists of the regression subnet and the classification subnet. The regression subnet is primarily used to generate two-channel predicted density maps, mainly including the initial feature layer and the feature enhancement layer, in which the feature enhancement layer can enhance the classification features and regression counting features of dense objects in complex traffic scenes. The classification subnet mainly supervises classifying dense vehicles and people into two feature channels to assist the regression counting task of the regression subnets.

Our method is compared on VisDrone+ datasets, ApolloScape+ datasets, and UAVDT+ datasets. The experimental results show that the method counts two kinds of dense objects simultaneously and outputs a high-quality two-channel predicted density map. The counting performance is better than the state-of-the-art counting network in dense people and vehicle counting.

In future work, we will further improve the feature extraction ability of the model in complex traffic scenes to classify and count a variety of dense objects such as cars, pedestrians, and non-motor vehicles.