原创 論文Depth Information Guided Crowd Counting for Complex Crowd Scenes

Depth Information Guided Crowd Counting for Complex Crowd Scenes摘要出於城市安全的考慮,監控和分析人羣擁擠事件是非常重要的。在一張擁塞場景的景深圖像(EDOF: extend

原创 論文理解Leveraging Unlabeled Data for Crowd Counting by Learning to Rank

論文:Leveraging Unlabeled Data for Crowd Counting by Learning to Rank作者:Xialei Liu、Joost van de Weijer、Andrew D. Bagdanov

原创 論文理解《Dense crowd counting from still images with convolutional neural networks》

論文《Dense crowd counting from still images with convolutional neural networks》創新點:使用深度學習方法估計一張圖片中中等、高度擁塞程度的人羣;解決問題:    人

原创 《Densely Connected Convolutional Networks》論文閱讀筆記

原文代碼: https://github.com/liuzhuang13/DenseNet pytorch實現 https://github.com/liuzhuang13/DenseNet/tree/master/models 論文動機