|
|
|
题名
|
作者
|
年代
|
出处
|
被引量
|
| 1 | Online Unsupervised Learning Classification of Pedestrian and Vehicle for Video Surveillance显示文摘This paper presents an online unsupervised learning classification of pedestrians and vehicles for video surveillance. Different from traditional methods depending on offline training, our method adopts the online label strategy based on temporal and morphological features,which saves time and labor to a large extent. It extract the moving objects with their features from the original video.An online filtering procedure is adopted to label the moving objects according to certain threshold of speed and area feature. The labeled objects are sent into a SVM classifier to generate the pedestrian & vehicle classifier. Experimental results illustrate that our unsupervised learning algorithm is adapted to polymorphism of the pedestrians and diversity of the vehicles with high classification accuracy. | HE Yi SANG Nong GAO Changxin HAN Jun | 2017 | Chinese Journal of Electronics2017，26，1： | 5 |
| 2 | Chronological Video Synopsis via Events Rearrangement Optimization显示文摘Video synopsis aims at retrieving interested events and reducing human labor on browsing long surveillance video. Traditional video synopsis methods based on energy function minimization is high computational and time consuming. Besides, the unchronological tubes shifting strategy may cause chaotic temporality and uncomfortable collisions. We propose a spatiotemporal events rearrangement optimization algorithm,which formulates the events rearrangement problem as iteration judgment on trajectory correlation and events compactability to generate the output synopsis video. An events subsection modification strategy has been presented to solve the spatial incompleteness of certain single event caused by imperfect object tracking. The experimental results have shown that the output synopsis video reserves the chronological order and avoids collisions of events. | HE Yi HAN Jun SANG Nong QU Zhiguo GAO Changxin | 2018 | Chinese Journal of Electronics2018，27，2： | 2 |
| 3 | On Selection and Combination of Weak Learners in AdaBoost显示文摘 | Gao Changxin Sang Nong Tang Qiling | 2010 | Pattern Recognition Letters2010，31，9： | 1 |
| 4 | Djrho2 is involved in regeneration of visual nerves in Dugesia japonica显示文摘The freshwater planarian is a powerful animal model for studying regeneration and stem cell activity in vivo.During regeneration,stem cells(neoblasts in planarian) migrated to the wounding edge to re-build missing parts of the body.However,proteins involved in regulating cell migration during planarian regeneration have not been studied extensively.Here we report two small GTPase genes(Djrho2 and Djrho3) of Dugesia japonica(strain Pek-1).In situ hybridization results indicated that Djrho2 was expressed throughout the body with the exception of the pharynx region while Djrho3 was specifically expressed along the gastro-vascular system.Djrho2 was largely expressed in neoblasts since its expression was sensitive to X-ray irradiation.In Djrho2-RNAi planarians,smaller anterior blastemas were observed in tail fragments during regeneration.Consistently,defective regeneration of visual nerve was detected by immunostainning with VC-1 antibody.These results suggested that Djrho2 is required for proper anterior regeneration in planairan.In contrast,no abnormality was observed after RNAi of Djrho3.We compared protein compositions of control and Djrho2-RNAi planarians using an optimized proteomic approach.Twenty-two up-regulated and 26 de-regulated protein spots were observed in the two-dimensional electrophoresis gels,and 17 proteins were successfully identified by Mass Spectrometry(MS) analysis.Among them,6 actin-binding or cytoskeleton-related proteins were found de-expressed in Djrho2-RNAi animals,suggesting that abnormal cytoskeleton assembling and cell migration were likely reasons of defected regeneration. | Changxin Ma Yang Gao Guoliang Chai Hanxia Su Niejun Wang Yigang Yang Chunbo Li Di Miao Wei Wu | 2010 | Journal of Genetics and Genomics2010，37，11： | 1 |
| 5 | Integrating climate,biodiversity,and sustainable land-use strategies:innovations from China显示文摘To reverse the accelerating degradation of biodiversity and ecosystem services(‘nature')and climate[1,2],the Convention on Biological Diversity(CBD)and the UN Framework Convention on Climate Change(UNFCCC)will hold major meetings in 2021.We argue that,as a critical priority,countries need to design and implement integrated national strategies to achieve the goals of the three Rio Conventions(including the UN Convention to Combat Desertification-UNCCD)using spatially explicit analyses and policies.This integration can maximize co-benefits and help manage trade-offs to meet the Sustainable Development Goals(SDGs). | Guido Schmidt-Traub Harvey Locke Jixi Gao Zhiyun Ouyang Justin Adams Lin Li Enric Sala M.Rebecca Shaw Sebastian Troëng Jing Xu Chunquan Zhu Changxin Zou Tianxiao Ma Fuwen Wei | 2021 | National Science Review2021，8，7： | 1 |
| 6 | Semantic segmentation via pixel-to-center similarity calculation显示文摘Since the fully convolutional network has achieved great success in semantic segmentation,lots of works have been proposed to extract discriminative pixel representations.However,the authors observe that existing methods still suffer from two typical challenges:(i)The intra-class feature variation between different scenes may be large,leading to the difficulty in maintaining the consistency between same-class pixels from different scenes;(ii)The inter-class feature distinction in the same scene could be small,resulting in the limited performance to distinguish different classes in each scene.The authors first rethink se-mantic segmentation from a perspective of similarity between pixels and class centers.Each weight vector of the segmentation head represents its corresponding semantic class in the whole dataset,which can be regarded as the embedding of the class center.Thus,the pixel-wise classification amounts to computing similarity in the final feature space between pixels and the class centers.Under this novel view,the authors propose a Class Center Similarity(CCS)layer to address the above-mentioned challenges by generating adaptive class centers conditioned on each scenes and supervising the similarities between class centers.The CCS layer utilises the Adaptive Class Center Module to generate class centers conditioned on each scene,which adapt the large intra-class variation between different scenes.Specially designed Class Distance Loss(CD Loss)is introduced to control both inter-class and intra-class distances based on the predicted center-to-center and pixel-to-center similarity.Finally,the CCS layer outputs the processed pixel-to-center similarity as the segmentation prediction.Extensive experiments demonstrate that our model performs favourably against the state-of-the-art methods. | Dongyue Wu Zilin Guo Aoyan Li Changqian Yu Nong Sang Changxin Gao | 2024 | CAAI Transactions on Intelligence Technology2024，9，1： | 0 |
| 7 | Benefit Assessment of Forest Function in Reducing Soil Erosion and Nutrient Loss in Anji County of Taihu Lake Basin显示文摘The non-point source pollution arising from soil erosion is one of the main reasons for the deterioration of the water quality of the Taihu Lake Basin. Forest plays an important role in controlling soil erosion and reducing nutrient loss. Based on the survey data on forest resources in Anji County, we estimate the amount of soil erosion and nutrient loss of nitrogen and phosphorus reduced by forest, using soil erosion modulus method and soil nutrient content. In accordance with the degradation coefficient of pollutant and regional compensation standards of environmental resources, we assess the ecological benefits of forest function in reducing nutrient loss of nitrogen and phosphorus in Anji County. The results show that the forest in Anji County can reduce the soil erosion amount at 1.51 million t annually on the average, so as to control the nutrient loss of 1 409 t of total nitrogen and 577 t of total phosphorus in soil, equivalent to annually avoiding the flow of 824 t of total nitrogen and 410 t of total phosphorus into river water; this ecological service function can make forests in Anji County get 92.55 million yuan of ecological compensation funds (about 688 yuan/hm2·a), equivalent to 15 times of the current ecological compensation standard (47 yuan/hm2). The study reveals the importance of forest function in controlling soil erosion and nutrient loss in the upper reaches of Taihu Lake Basin to water environment protection in the basin, conducive to carrying out pollution control and protection work of the water environment in the basin. | Biao ZHANG Jixi GAO Gaodi XIE Changxin ZOU Bin WANG | 2013 | Asian Agricultural Research2013，5，4： | 0 |
您所在的机构暂未开通此部分的功能，请联系管理员