Huiyan Wang
Zhejiang Gongshang University
22 Papers
159 Citations
Huiyan Wang is an academic researcher from Zhejiang Gongshang University. The author has contributed to research in topics: Computer science & Feature extraction. The author has an hindex of 9, co-authored 22 publications.
Chat about Author
Papers
Spatio-Temporal Video Segmentation of Static Scenes and Its Applications
TL;DR: An iterative optimization scheme is introduced by first initializing segmentation maps for each frame independently, and then linking the correspondences among different frames and iteratively refine them with the collected statistics, so that a set of spatio-temporally consistent volume segments are finally achieved.
Hybrid deep learning for automated lepidopteran insect image classification
Leqing Zhu,Meng-Yuan Ma,Zhen Zhang,Pei-Yi Zhang,Wei Wu,Dadong Wang,Daxing Zhang,Xun Wang,Huiyan Wang +8 more
TL;DR: A cascade architecture which combines the methods of deep convolutional neural network (DCNNs) and Supported Vector Machines (SVMs) to identify Lepidoptera species from their images can achieve an accuracy of 100% with the testing data-set and it takes only about 200 ms to recognize insect species from an image.
40
Recognition of Low-Resolution Logos in Vehicle Images Based on Statistical Random Sparse Distribution
TL;DR: Experiments showed that the proposed VLR method outperforms classical VLR methods for low-resolution and inferior quality images and is very suitable for on-site supervision in ITSs.
38
Patent
Monocular image depth estimation method based on multi-scale CNN and continuous CRF
Xun Wang,Leqing Zhu,Huiyan Wang +2 more
- 23 Nov 2016
TL;DR: In this article, a monocular image depth estimation method based on multi-scale CNN and continuous CRF is proposed, where a CRF model is used to calculate single-point potential energy according to an output depth map of DCNN, paired sparse potential energy is calculated according to RGB image, and finally an optimized depth map is deduced using a maximized posterior probability (MAP) algorithm.
35
Object localization via evaluation multi-task learning
Yan Tian,Huiyan Wang,Xun Wang +2 more
TL;DR: This paper developed an algorithm for the nontrivial end-to-end training of this causal, cascaded structure on convolution neural network for object localization and demonstrated performance on the PASCAL VOC 2007 dataset and traffic scene dataset.
23