FCHD: Fast and accurate head detection in crowded scenes

TL;DR

FCHD introduces a lightweight, fully convolutional head detection model that achieves high accuracy and real-time performance in crowded scenes, suitable for practical applications.

Contribution

The paper presents a novel end-to-end fully convolutional network for head detection that balances accuracy and efficiency, outperforming existing methods in speed and precision.

Findings

Achieves 0.70 AP on a challenging dataset

Runs at 5 FPS on Nvidia Quadro M1000M

Uses anchor sizes based on receptive field for better accuracy

Abstract

In this paper, we propose FCHD-Fully Convolutional Head Detector, an end-to-end trainable head detection model. Our proposed architecture is a single fully convolutional network which is responsible for both bounding box prediction and classification. This makes our model lightweight with low inference time and memory requirements. Along with run-time, our model has better overall average precision (AP) which is achieved by selection of anchor sizes based on the effective receptive field of the network. This can be concluded from our experiments on several head detection datasets with varying head counts. We achieve an AP of 0.70 on a challenging head detection dataset which is comparable to some standard benchmarks. Along with this our model runs at 5 FPS on Nvidia Quadro M1000M for VGA resolution images. Code is available at https://github.com/aditya-vora/FCHD-Fully-Convolutional-Head-Detector.