Crime scene investigation(CSI)image is key evidence carrier during criminal investiga-tion,in which CSI image retrieval can assist the public police to obtain criminal clues.Moreover,with the rapid development of deep...Crime scene investigation(CSI)image is key evidence carrier during criminal investiga-tion,in which CSI image retrieval can assist the public police to obtain criminal clues.Moreover,with the rapid development of deep learning,data-driven paradigm has become the mainstreammethod of CSI image feature extraction and representation,and in this process,datasets provideeffective support for CSI retrieval performance.However,there is a lack of systematic research onCSI image retrieval methods and datasets.Therefore,we present an overview of the existing worksabout one-class and multi-class CSI image retrieval based on deep learning.According to theresearch,based on their technical functionalities and implementation methods,CSI image retrievalis roughly classified into five categories:feature representation,metric learning,generative adversar-ial networks,autoencoder networks and attention networks.Furthermore,We analyzed the remain-ing challenges and discussed future work directions in this field.展开更多
We present an experimental demonstration of ghost imaging of reflective objects with different surface roughness.The influence of the surface roughness, the transverse size of the test detector, and the reflective ang...We present an experimental demonstration of ghost imaging of reflective objects with different surface roughness.The influence of the surface roughness, the transverse size of the test detector, and the reflective angle on the signal-to-noise ratio(SNR) is analyzed by measuring the second-order correlation of the light field based on classical statistical optics. It is shown that the SNR decreases with an increment of the surface roughness and the detector's transverse size or a decrease of the reflective angle. Additionally, the comparative studies between the rough object and the smooth one under the same conditions are also discussed.展开更多
文摘Crime scene investigation(CSI)image is key evidence carrier during criminal investiga-tion,in which CSI image retrieval can assist the public police to obtain criminal clues.Moreover,with the rapid development of deep learning,data-driven paradigm has become the mainstreammethod of CSI image feature extraction and representation,and in this process,datasets provideeffective support for CSI retrieval performance.However,there is a lack of systematic research onCSI image retrieval methods and datasets.Therefore,we present an overview of the existing worksabout one-class and multi-class CSI image retrieval based on deep learning.According to theresearch,based on their technical functionalities and implementation methods,CSI image retrievalis roughly classified into five categories:feature representation,metric learning,generative adversar-ial networks,autoencoder networks and attention networks.Furthermore,We analyzed the remain-ing challenges and discussed future work directions in this field.
基金National Natural Science Foundation of China(NSFC)(61372102,61571183)Natural Science Foundation of Hunan Province(2017JJ1014)
文摘We present an experimental demonstration of ghost imaging of reflective objects with different surface roughness.The influence of the surface roughness, the transverse size of the test detector, and the reflective angle on the signal-to-noise ratio(SNR) is analyzed by measuring the second-order correlation of the light field based on classical statistical optics. It is shown that the SNR decreases with an increment of the surface roughness and the detector's transverse size or a decrease of the reflective angle. Additionally, the comparative studies between the rough object and the smooth one under the same conditions are also discussed.
