Box-level Segmentation Supervised Deep Neural Networks for Multispectral Pedestrian Detection(19)綜述
摘要：本文提出了一種新穎的在檢測框層面做語義分割的監督學習框架，能夠實現準確且實時地多光譜（可見光和紅外光）行人檢測。具體來說就是將已經獲得的行人檢測框的普通圖像和紅外圖像(已對齊)作爲輸入，然後估計出準確的預測熱力圖來表徵行人的存在。 比之前的用anchor來做的多光譜檢測方法，本文方法有兩個有點： 1） 拋棄anchor的方法，避免了複雜的anchor超參數設置，而且提高了準確率，對小目標和遮
相關文章
- 1. 《Constrained Convolutional Neural Networks for Weakly Supervised Segmentation》翻譯
- 2. Multispectral Pedestrian Detection using Deep Fusion Convolutional Neural Networks （深度學習多光譜行人檢測綜述）
- 3. Brain tumor segmentation with Deep Neural Networks
- 4. 【Semantic Segmentation】語義分割綜述 - - Semi-supervised
- 5. Aggregated Residual Transformations for Deep Neural Networks
- 6. Deep Convolutional Neural Networks for Sentiment Analysis of Short Texts
- 7. Deep Neural Networks for Object Detection
- 8. Fully Convolutional Adaptation Networks for Semantic Segmentation
- 9. ROLO:Spatially Supervised Recurrent Convolutional Neural Networks for Visual Object Tracking
- 10. Illumination-aware Faster R-CNN for Robust Multispectral Pedestrian Detection
- 更多相關文章...
- • Swift for 循環 - Swift 教程
- • Scala for循環 - Scala教程
- • Java Agent入門實戰（二）-Instrumentation源碼概述
- • 算法總結-股票買賣
相關標籤/搜索
每日一句
-
每一个你不满意的现在，都有一个你没有努力的曾经。
歡迎關注本站公眾號,獲取更多信息
相關文章
- 1. 《Constrained Convolutional Neural Networks for Weakly Supervised Segmentation》翻譯
- 2. Multispectral Pedestrian Detection using Deep Fusion Convolutional Neural Networks （深度學習多光譜行人檢測綜述）
- 3. Brain tumor segmentation with Deep Neural Networks
- 4. 【Semantic Segmentation】語義分割綜述 - - Semi-supervised
- 5. Aggregated Residual Transformations for Deep Neural Networks
- 6. Deep Convolutional Neural Networks for Sentiment Analysis of Short Texts
- 7. Deep Neural Networks for Object Detection
- 8. Fully Convolutional Adaptation Networks for Semantic Segmentation
- 9. ROLO:Spatially Supervised Recurrent Convolutional Neural Networks for Visual Object Tracking
- 10. Illumination-aware Faster R-CNN for Robust Multispectral Pedestrian Detection