中文版 | ENGLISH

   个人简介
浙江理工大学虚拟现实实验室简介
杨文珍
    杨文珍,男,博士,教授,机械设计及理论专业硕导,控制工程专业硕导,计算机应用技术专业硕导。浙江大学机械设计及理论专业硕士,浙江大学CAD&CG国家重点实验室计算机科学与技术专业博士,浙江大学控制科学与工程流动站博士后出站,美国乔治梅森大学访问学者。
长期致力于人机交互、机器人和虚拟现实领域的研究,在盲文点显器、计算机触觉、计算机嗅觉、灵巧机械手、运动健康等方面,形成了研究特色。
研究方向:
    
学历情况:
    
留学经历:
    
查看详细>>
  当前位置:首页{urlsectionname}

2019 会议论文CCF A类 Monocular Depth Estimation as Regression of Classi_cation using Piled Residual Networks
时间:2019-12-31 15:05:29    浏览次数:1191        

Monocular Depth Estimation as Regression of Classi_cation using Piled Residual Networks
 
Abstract: Predicting depth from single monocular image is a challenging task in scene understanding. Most existing work predicts depth by regression or classification with features extracted from local neighborhood area. However, neither regression nor classification achieves the final satisfying solution and local context can be insufficient to predict the depth. This paper innovatively addresses this problem as regression of class related features on a piled residual convolutional neural network. Our framework works at two stages. First, a well-designed deep convolutional neural network model is employed to classify the depths in difference-scale invariance space. The model utilizes all scales of context though piled residual paths. The deeper layers that capture high-level semantic features with long-range context can be directly refined using fine-grained features with local context from earlier convolutions. We then apply centered information gain loss to the model to produce intra-class compact and interclass discriminative features. Second, to obtain depths instead of class labels, we infer depth regression with convolutional layers which model the mapping from class discriminative features to continuous depth values. Experiments on the popular indoor and outdoor datasets show competitive results compared with the recent state of the art methods.

In Proceedings of the 27th ACM International Conference on Multimedia (MM '19), October 21-25, 2019, Nice, France. ACM, New York, NY, USA, 9 pages. https://doi.org/10.1145/3343031.3350930.

版权所有©虚拟现实   地址:浙江省杭州市下沙高教园区浙江理工大学机械与自动控制学院15-348  邮编:310018
E-mail:ywz@zstu.edu.cn  QQ:点击这里给我发消息  浙ICP备05151518号  技术支持:燎扬网络

您是第 位访问者