A Light CNN based Method for Hand Detection and Orientation Estimation
Abstract 最近，使用CNN模型的物體檢測方法以高計算費用顯着提高了手檢測的準確性。 在本文中，我們提出了一個輕型CNN網絡，它使用改進的MobileNet作爲SSD框架的特徵提取器，以實現對手部位置和方向的穩健和快速檢測。 網絡生成一組不同分辨率的特徵圖，以檢測不同尺寸的手。 爲了提高健壯性，我們還採用了一種自頂向下的功能融合體系結構，該體系結構集成了跨功能級別的上下文信息。 爲了準確估計
相關文章
- 1. A Robust Hand Detection Method Based on Skin Probability Map
- 2. A Hybrid Method Using Haar-like and SkinColor Algorithm for Hand Posture Detection Recognition Track
- 3. A New Hand Segmentation Method Based on Fully Convolutional Network
- 4. HOPE-Net: A Graph-based Model for Hand-Object Pose Estimation
- 5. 學習總結《HOPE-Net: A Graph-based Model for Hand-Object Pose Estimation》
- 6. 《A Multilayer Fusion Light-Head Detector for SAR Ship Detection》
- 7. 論文A CNN-based prototype method of unstructured surgical state perception and navigation
- 8. 手勢估計- Hand Pose Estimation
- 9. CNN-based Cascaded Multi-task Learning of High-level Prior and Density Estimation for Crowd Counting
- 10. Region-Based Convolutional Networks for Accurate Object Detection and Segmentation
- 更多相關文章...
- • Scala for循環 - Scala教程
- • Lua for 循環 - Lua 教程
- • RxJava操作符（七）Conditional and Boolean
- • Flink 數據傳輸及反壓詳解
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. A Robust Hand Detection Method Based on Skin Probability Map
- 2. A Hybrid Method Using Haar-like and SkinColor Algorithm for Hand Posture Detection Recognition Track
- 3. A New Hand Segmentation Method Based on Fully Convolutional Network
- 4. HOPE-Net: A Graph-based Model for Hand-Object Pose Estimation
- 5. 學習總結《HOPE-Net: A Graph-based Model for Hand-Object Pose Estimation》
- 6. 《A Multilayer Fusion Light-Head Detector for SAR Ship Detection》
- 7. 論文A CNN-based prototype method of unstructured surgical state perception and navigation
- 8. 手勢估計- Hand Pose Estimation
- 9. CNN-based Cascaded Multi-task Learning of High-level Prior and Density Estimation for Crowd Counting
- 10. Region-Based Convolutional Networks for Accurate Object Detection and Segmentation