IEEE Access · 2019 · 134 citations · 35 references
ComputingComputer ScienceComputer VisionDigital ImagingMachine VisionImage SegmentationMotion AnalysisObject DetectionScene UnderstandingSemantic SegmentationVideo AnalysisConvolutional Neural Network SegmentationDeconvolutionEncoder-decoder ArchitecturesFramesMotion SegmentationMulti-scale FeaturesNetwork DeconvolutionPixel-based Classification
In complex scenes, dynamic background, illumination variation, and shadow degrade conventional moving‑object detection algorithms. The authors propose a moving‑object detection method using ResNet‑18 with an encoder‑decoder structure to segment moving objects from such complex scenes. The method encodes input frames with ResNet‑18, decodes the resulting feature vectors into segmentation maps via deconvolution, and refines rough moving‑object matches using Euclidean distance. On CDnet2014 and I2R datasets, the method outperforms state‑of‑the‑art algorithms, achieving a mean F‑measure increase of 1.99%–29.17%.
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%.
35
Deep Residual Learning for Image Recognition
Kaiming He, Xiangyu Zhang, Shaoqing Ren et al. · 2016 · 222.1K citations · Full text
Fully convolutional networks for semantic segmentation
Jonathan Long, Evan Shelhamer, Trevor Darrell · 2015 · 36.9K citations