A patch-based method for detecting vehicle logos using prior knowledge is proposed.By representing the coarse region of the logo with the weight matrix of patch intensity and position,the proposed method is robust to ...A patch-based method for detecting vehicle logos using prior knowledge is proposed.By representing the coarse region of the logo with the weight matrix of patch intensity and position,the proposed method is robust to bad and complex environmental conditions.The bounding-box of the logo is extracted by a thershloding approach.Experimental results show that 93.58% location accuracy is achieved with 1100 images under various environmental conditions,indicating that the proposed method is effective and suitable for the location of vehicle logo in practical applications.展开更多
A novel unsupervised ship detection and extraction method is proposed. A combination model based on visual saliency is constructed for searching the ship target regions and suppressing the false alarms. The salient ta...A novel unsupervised ship detection and extraction method is proposed. A combination model based on visual saliency is constructed for searching the ship target regions and suppressing the false alarms. The salient target regions are extracted and marked through segmentation. Radon transform is applied to confirm the suspected ship targets with symmetry profiles. Then, a new descriptor, improved histogram of oriented gradient(HOG), is introduced to discriminate the real ships. The experimental results on real optical remote sensing images demonstrate that plenty of ships can be extracted and located successfully, and the number of ships can be accurately acquired. Furthermore, the proposed method is superior to the contrastive methods in terms of both accuracy rate and false alarm rate.展开更多
This study developed a method to perform the simultaneous concentration and selective separation of 66 (ultra) trace persistent toxic substances in Antarctic waters. The substances included 30 polychlorinated biphen...This study developed a method to perform the simultaneous concentration and selective separation of 66 (ultra) trace persistent toxic substances in Antarctic waters. The substances included 30 polychlorinated biphenyls, 17 organochlorine pesticides, 16 polycyclic aromatic hydrocarbons, 3 hexabromocyclododecanes. Solid phase extraction was performed using a C18 membrane and silica gel column. Gradient elution was conducted using organic solvents with different polarities; as a result, the efficiency of the C18 film is improved and the interferences from impurities and target compounds are eliminated. Extracts were subsequently analyzed through gas chromatography or liquid and gas chromatography coupled to tandem mass spectrometry. Method validation yielded the following values: recoveries of all target analytes in the Antarctic water ranged from 87.3% to 117.6% and reproducibility as percent relative standard deviation was lower than 5%. Quantification limits ranged from 0.004 μg L^-1 to 0.030 μg L^-1. The established method improved the recoveries and reduced the limits of detection. Results indicated the method exhibited good performance in the simultaneous concentration and selective separation of 66 (ultra) trace organic pollutants; Therefore, the proposed sample pretreatment can potentially eliminate the effects of various classes of impurities to some extent.展开更多
文摘A patch-based method for detecting vehicle logos using prior knowledge is proposed.By representing the coarse region of the logo with the weight matrix of patch intensity and position,the proposed method is robust to bad and complex environmental conditions.The bounding-box of the logo is extracted by a thershloding approach.Experimental results show that 93.58% location accuracy is achieved with 1100 images under various environmental conditions,indicating that the proposed method is effective and suitable for the location of vehicle logo in practical applications.
基金supported by the National Natural Science Foundation of China(No.60902067)the Key Programs for Science and Technology Development of Jilin Province of China(No.11ZDGG001)
文摘A novel unsupervised ship detection and extraction method is proposed. A combination model based on visual saliency is constructed for searching the ship target regions and suppressing the false alarms. The salient target regions are extracted and marked through segmentation. Radon transform is applied to confirm the suspected ship targets with symmetry profiles. Then, a new descriptor, improved histogram of oriented gradient(HOG), is introduced to discriminate the real ships. The experimental results on real optical remote sensing images demonstrate that plenty of ships can be extracted and located successfully, and the number of ships can be accurately acquired. Furthermore, the proposed method is superior to the contrastive methods in terms of both accuracy rate and false alarm rate.
基金financially supported by the National Natural Science Foundation of China(No.21377032)the Chinese Polar Environment Comprehensive Investigation and Assessment Program(Nos.2014-02-01,2014-03-04,2014-04-01,2014-04-03)+1 种基金the Marine Public Welfare Scientific Research Projects(No.201105013)the Foundation of Polar Science Key Laboratory,SOA,China(No.KP201208)
文摘This study developed a method to perform the simultaneous concentration and selective separation of 66 (ultra) trace persistent toxic substances in Antarctic waters. The substances included 30 polychlorinated biphenyls, 17 organochlorine pesticides, 16 polycyclic aromatic hydrocarbons, 3 hexabromocyclododecanes. Solid phase extraction was performed using a C18 membrane and silica gel column. Gradient elution was conducted using organic solvents with different polarities; as a result, the efficiency of the C18 film is improved and the interferences from impurities and target compounds are eliminated. Extracts were subsequently analyzed through gas chromatography or liquid and gas chromatography coupled to tandem mass spectrometry. Method validation yielded the following values: recoveries of all target analytes in the Antarctic water ranged from 87.3% to 117.6% and reproducibility as percent relative standard deviation was lower than 5%. Quantification limits ranged from 0.004 μg L^-1 to 0.030 μg L^-1. The established method improved the recoveries and reduced the limits of detection. Results indicated the method exhibited good performance in the simultaneous concentration and selective separation of 66 (ultra) trace organic pollutants; Therefore, the proposed sample pretreatment can potentially eliminate the effects of various classes of impurities to some extent.