Moving Object Detection Method via ResNet-18 With Encoder–Decoder Structure in Complex Scenes

Xianfeng Ou,Guoyun Zhang,Jianhui Wu,Yiming Zhang,Wujing Li,Pengcheng Yan,Bing Tu

doi:10.1109/access.2019.2931922

Xianfeng Ou, Guoyun Zhang + Show 5 more

Open Access

https://doi.org/10.1109/access.2019.2931922

Copy DOI

Abstract

In complex scenes, dynamic background, illumination variation, and shadow are important factors, which make conventional moving object detection algorithms suffer from poor performance. To solve this problem, a moving object detection method via ResNet-18 with encoder-decoder structure is proposed to segment moving objects from complex scenes. ResNet-18 with encoder-decoder structure possesses pixel-level classification capability to divide pixels into foreground and background, and it performs well in feature extraction because of its layers are so shallow that many more low-scale features will be retained. First, the object frames and their corresponding artificial labels are input to the network. Then, feature vectors will be generated by the encoder, and they are converted into segmentation maps by the decoder through deconvolution processing. Third, a rough matching of the moving object regions will be obtained, and finally, the Euclidean distance is used to match the moving object regions accurately. The proposed method is suitable for the scenes where dynamic background, illumination variation, and shadow exist, and experimental results on the public standard CDnet2014 and I2R datasets, from both qualitative and quantitative comparison aspects, demonstrate that the proposed method outperforms state-of-the-art algorithms significantly, and its mean F-measure increased by 1.99%~29.17%.

Highlights

Moving object detection is one of the most extensively studied topics in computer vision and the digital image processing [1]–[3], which is usually used as a preprocessing step in numerous vision applications including object tracking [4], object detection [5], behavior analysis [6] and so on
Moving object detection is still a challenging problem, since some background regions are contained in complex scenes, where water surface, shaking leaves, light changing and moving cloud exist
The moving object detection algorithms should adapt to some factors, such as illumination variation and the shadow

Summary

Introduction

Moving object detection is one of the most extensively studied topics in computer vision and the digital image processing [1]–[3], which is usually used as a preprocessing step in numerous vision applications including object tracking [4], object detection [5], behavior analysis [6] and so on. The purpose of moving object detection is to extract the motion regions (foreground objects) in the image sequences from the backgrounds. Moving object detection is still a challenging problem, since some background regions are contained in complex scenes, where water surface, shaking leaves, light changing and moving cloud exist. The moving object detection algorithms should adapt to some factors, such as illumination variation and the shadow The associate editor coordinating the review of this manuscript and approving it for publication was Huanqing Wang.

Methods

Results

Conclusion