DPDnet: A Robust People Detector using Deep Learning with an Overhead Depth Camera

TL;DR

DPDnet is a deep learning-based method for accurately detecting multiple people from overhead depth images, achieving high accuracy and real-time performance without retraining.

Contribution

Introduces DPDnet, a novel end-to-end trainable neural network architecture for people detection from overhead depth images, outperforming existing methods.

Findings

Achieves over 99% accuracy on three datasets

Operates in real-time on standard GPUs

Does not require retraining for new scenes

Abstract

In this paper we propose a method based on deep learning that detects multiple people from a single overhead depth image with high reliability. Our neural network, called DPDnet, is based on two fully-convolutional encoder-decoder neural blocks based on residual layers. The Main Block takes a depth image as input and generates a pixel-wise confidence map, where each detected person in the image is represented by a Gaussian-like distribution. The refinement block combines the depth image and the output from the main block, to refine the confidence map. Both blocks are simultaneously trained end-to-end using depth images and head position labels. The experimental work shows that DPDNet outperforms state-of-the-art methods, with accuracies greater than 99% in three different publicly available datasets, without retraining not fine-tuning. In addition, the computational complexity of our proposal is independent of the number of people in the scene and runs in real time using conventional GPUs.