An Adaptive Threshold for the Canny Edge Detection with Actor-Critic Algorithm

TL;DR

This paper introduces a spatio-temporal fusion network with an adaptive threshold for Canny edge detection, enhancing foreground object detection in varying environments and demonstrating superior performance over existing methods.

Contribution

It proposes a novel STFN that effectively combines spatial and temporal information for robust foreground detection, especially in environments different from training data.

Findings

Achieves 11.28% higher FM on LASIESTA dataset.

Achieves 18.33% higher FM on SBI dataset.

Operates in real-time on GPU-based desktops.

Abstract

Visual surveillance aims to perform robust foreground object detection regardless of the time and place. Object detection shows good results using only spatial information, but foreground object detection in visual surveillance requires proper temporal and spatial information processing. In deep learning-based foreground object detection algorithms, the detection ability is superior to classical background subtraction (BGS) algorithms in an environment similar to training. However, the performance is lower than that of the classical BGS algorithm in the environment different from training. This paper proposes a spatio-temporal fusion network (STFN) that could extract temporal and spatial information using a temporal network and a spatial network. We suggest a method using a semi-foreground map for stable training of the proposed STFN. The proposed algorithm shows excellent performance in an environment different from training, and we show it through experiments with various public datasets. Also, STFN can generate a compliant background image in a semi-supervised method, and it can operate in real-time on a desktop with GPU. The proposed method shows 11.28% and 18.33% higher FM than the latest deep learning method in the LASIESTA and SBI dataset, respectively.