MPSN: Motion-aware Pseudo Siamese Network for Indoor Video Head Detection in Buildings

TL;DR

The paper introduces MPSN, a motion-aware deep network that improves indoor head detection by leveraging head motion cues, effectively suppressing background clutter and enhancing detection accuracy in complex indoor scenes.

Contribution

It presents a novel end-to-end motion-aware pseudo Siamese network that utilizes pixel-wise frame differences to improve indoor head detection performance.

Findings

MPSN outperforms prior methods on indoor video datasets.

The approach effectively suppresses static background objects.

MPSN demonstrates robustness against adversarial perturbations.

Abstract

Head detection in the indoor video is an essential component of building occupancy detection. While deep models have achieved remarkable progress in general object detection, they are not satisfying enough in complex indoor scenes. The indoor surveillance video often includes cluttered background objects, among which heads have small scales and diverse poses. In this paper, we propose Motion-aware Pseudo Siamese Network (MPSN), an end-to-end approach that leverages head motion information to guide the deep model to extract effective head features in indoor scenarios. By taking the pixel-wise difference of adjacent frames as the auxiliary input, MPSN effectively enhances human head motion information and removes the irrelevant objects in the background. Compared with prior methods, it achieves superior performance on the two indoor video datasets. Our experiments show that MPSN successfully suppresses static background objects and highlights the moving instances, especially human heads in indoor videos. We also compare different methods to capture head motion, which demonstrates the simplicity and flexibility of MPSN. To validate the robustness of MPSN, we conduct adversarial experiments with a mathematical solution of small perturbations for robust model selection. Finally, for confirming its potential in building control systems, we apply MPSN to occupancy counting. Code is available at https://github.com/pl-share/MPSN.