Graph CNN for Moving Object Detection in Complex Environments from Unseen Videos

Abstract

Moving Object Detection (MOD) is a fundamental step for many computer vision applications. MOD becomes very challenging when a video sequence captured from a static or moving camera suffers from the challenges: camouflage, shadow, dynamic backgrounds, and lighting variations, to name a few. Deep learning methods have been successfully applied to address MOD with competitive performance. However, in order to handle the overfitting problem, deep learning methods require a large amount of labeled data which is a laborious task as exhaustive annotations are always not available. Moreover, some MOD deep learning methods show performance degradation in the presence of unseen video sequences because the testing and training splits of the same sequences are involved during the network learning process. In this work, we pose the problem of MOD as a node classification problem using Graph Convolutional Neural Networks (GCNNs). Our algorithm, dubbed as GraphMOD-Net, encompasses instance segmentation, background initialization, feature extraction, and graph construction. GraphMOD-Net is tested on unseen videos and outperforms state-of-the-art methods in unsupervised, semi-supervised, and supervised learning in several challenges of the Change Detection 2014 (CDNet2014) and UCSD background subtraction datasets.

References in corpus (12)

• Adam: A Method for Stochastic Optimization
• TensorFlow: A system for large-scale machine learning
• Semi-Supervised Classification with Graph Convolutional Networks
• Inductive Representation Learning on Large Graphs
• Discrete Signal Processing on Graphs: Sampling Theory
• ResNeSt: Split-Attention Networks
• Decomposition into Low-rank plus Additive Matrices for Background/Foreground Separation: A Review for a Comparative Evaluation with a Large-Scale Dataset
• Learning Multi-scale Features for Foreground Segmentation
• A Sampling Theory Perspective of Graph-based Semi-supervised Learning
• Fast Graph Fourier Transforms Based on Graph Symmetry and Bipartition
• Camera-trap images segmentation using multi-layer robust principal component analysis
• Deep Neural Network Concepts for Background Subtraction: A Systematic Review and Comparative Evaluation

Cited by in corpus (1)

• On the Trade-off between Over-smoothing and Over-squashing in Deep Graph Neural Networks