Computer Vision: Second CCF Chinese Conference, CCCV 2017, Tianjin, China, October 11–14, 2017, Proceedings, Part III

Description

This three volume set, CCIS 771, 772, 773, constitutes the refereed proceedings of the CCF Chinese Conference on Computer Vision, CCCV 2017, held in Tianjin, China, in October 2017. The total of 174 revised full papers presented in three volumes were carefully reviewed and selected from 465 submissions. The papers are organized in the following topical sections: biological vision inspired visual method; biomedical image analysis; computer vision applications; deep neural network; face and posture analysis; image and video retrieval; image color and texture; image composition; image quality assessment and analysis; image restoration; image segmentation and classification; image-based modeling; object detection and classification; object identification; photography and video; robot vision; shape representation and matching; statistical methods and learning; video analysis and event recognition; visual salient detection. Front Matter ....Pages I-XXIII Front Matter ....Pages 1-1 Classification of Foreign Object Debris Using Integrated Visual Features and Extreme Learning Machine (Kai Hu, Dongshun Cui, Yuan Zhang, Chunhong Cao, Fen Xiao, Guangbin Huang)....Pages 3-13 Two Novel Image-Based CAPTCHA Schemes Based on Visual Effects (Ping Zhang, Haichang Gao, Zhouhang Cheng, Fang Cao)....Pages 14-25 An Unsupervised Domain Adaptation Algorithm Based on Canonical Correlation Analysis (Pan Xiao, Bo Du, Xue Li)....Pages 26-37 UAV-Based Vehicle Detection by Multi-source Images (Shangjie Jiang, Bin Luo, Jun Liu, Yun Zhang, LiangPei Zhang)....Pages 38-49 Moving Object Detection via Integrating Spatial Compactness and Appearance Consistency in the Low-Rank Representation (Minghe Xu, Chenglong Li, Hanqin Shi, Jin Tang, Aihua Zheng)....Pages 50-60 MFRPN: Towards High-Quality Region Proposal Generation in Object Detection (Dingqian Zhang, Hui Zhang, Wanling Zeng, Zhongxing Han, Xiaohui Hu)....Pages 61-72 Pedestrian Detection by Using CNN Features with Skip Connection (Peng Zhang, Zengfu Wang)....Pages 73-83 Edge-Preserving Background Estimation Using Most Similar Neighbor Patch for Small Target Detection (Yuehuan Wang, Xueping Xu, Nuoning Yue, Jie Chen)....Pages 84-95 Space Target Detection in Video Satellite Image via Prior Information (Xueyang Zhang, Junhua Xiang)....Pages 96-107 Scene Recognition with Sequential Object Context (Yuelian Wang, Wei Pan)....Pages 108-119 Associated Metric Coding Network for Pedestrian Detection (Shuai Chen, Bo Ma)....Pages 120-131 Large-Scale Slow Feature Analysis Using Spark for Visual Object Recognition (Da Li, Zhang Zhang, Tieniu Tan)....Pages 132-142 Fine-Grained Visual Classification Based on Image Foreground and Sub-category Similarity (Xianjin Jiang, Xin Lin, Yi Ji, Jianyu Yang, Chunping Liu)....Pages 143-154 Faster R-CNN for Small Traffic Sign Detection (Zhuo Zhang, Xiaolong Zhou, Sixian Chan, Shengyong Chen, Honghai Liu)....Pages 155-165 S-OHEM: Stratified Online Hard Example Mining for Object Detection (Minne Li, Zhaoning Zhang, Hao Yu, Xinyuan Chen, Dongsheng Li)....Pages 166-177 ScratchNet: Detecting the Scratches on Cellphone Screen (Zhao Luo, Xiaobing Xiao, Shiming Ge, Qiting Ye, Shengwei Zhao, Xin Jin)....Pages 178-186 Small UAV Detection in Videos from a Single Moving Camera (Lian Du, Chenqiang Gao, Qi Feng, Can Wang, Jiang Liu)....Pages 187-197 A More Efficient CNN Architecture for Plankton Classification (Jiangpeng Yan, Xiu Li, Zuoying Cui)....Pages 198-208 Zero-Shot Learning with Deep Canonical Correlation Analysis (Zhong Ji, Xuejie Yu, Yanwei Pang)....Pages 209-219 A Novel Level Set Model for Image Segmentation with Interactive Label Regularization Term (Huang Tan, Ming Chen, Qiaoliang Li, Shaojun Qu)....Pages 220-232 Modified Object Detection Method Based on YOLO (Xia Zhao, Yingting Ni, Haihang Jia)....Pages 233-244 Scene Text Detection with Text Statistical Characteristics and Deep Neural Network (Yanyun Qu, Xiaodong Yang, Li Lin)....Pages 245-254 Front Matter ....Pages 255-255 Palmprint Recognition Using Sparse Representation of Variable Window-Width Real-Valued Gabor Feature (Mengwen Li, Huabin Wang, Jian Zhou, Liang Tao)....Pages 257-267 Robust Multi-view Common Component Learning (Jiamiao Xu, Xinge You, Shi Yin, Peng Zhang, Wei Yuan)....Pages 268-279 Person Re-identification on Heterogeneous Camera Network (Jiaxuan Zhuo, Junyong Zhu, Jianhuang Lai, Xiaohua Xie)....Pages 280-291 Multiple Metric Learning in Kernel Space for Person Re-identification (Tongwen Xu, Yonghong Song, Yuanlin Zhang)....Pages 292-302 Multi-angle Insulator Recognition Method in Infrared Image Based on Parallel Deep Convolutional Neural Networks (Zhenbing Zhao, Xiaoqing Fan, Yincheng Qi, Yongjie Zhai)....Pages 303-314 Enhanced Deep Feature Representation for Person Search (Jinfu Yang, Meijie Wang, Mingai Li, Jingling Zhang)....Pages 315-327 Joint Temporal-Spatial Information and Common Network Consistency Constraint for Person Re-identification (Zhaoxi Cheng, Hua Yang, Lin Chen)....Pages 328-339 Building Extraction by Stroke Width Transform from Satellite Imagery (Li Xu, Mingming Kong, Bing Pan)....Pages 340-351 Siamese Cosine Network Embedding for Person Re-identification (Jiabao Wang, Yang Li, Zhuang Miao)....Pages 352-362 Person Re-identification with End-to-End Scene Text Recognition ( Kamlesh, Pei Xu, Yang Yang, Yongchao Xu)....Pages 363-374 Hierarchical Structure Construction Based on Hyper-sphere Granulation for Finger-Vein Recognition (Jinfeng Yang, Yuqing Yang, Zhiyuan Liu, Yihua Shi)....Pages 375-386 Front Matter ....Pages 387-387 Imaging Model and Calibration of Lytro Light Field Camera (Huixian Duan, Jun Wang, Lei Song, Na Liu, Lin Mei)....Pages 389-400 Bayesian Inference Based Choquet Integral Method (Chunxiao Ren)....Pages 401-415 Front Matter ....Pages 417-417 Statistical Degradation Analysis for Real-Time Tracking in Severely Degraded Videos (Yuan Feng, Sheng Liu, Chao Wang, Gaoxuan Ying, Kejie Yin, ShengYong Chen)....Pages 419-429 A Two-Layered Pipeline for Topological Place Recognition Based on Topic Model (Xingliang Dong, Jing Yuan, Fengchi Sun, Yalou Huang)....Pages 430-441 Monocular Dense Reconstruction Based on Direct Sparse Odometry (Libing Mao, Jiaxin Wu, Jianhua Zhang, Shengyong Chen)....Pages 442-452 Three Dimensional Object Segmentation Based on Spatial Adaptive Projection for Solid Waste (Yeqiang Qiu, Jiawei Chen, Jianshuang Guo, Jianhua Zhang, Sheng Liu, Shengyong Chen)....Pages 453-464 RGB-D Based Object Segmentation in Severe Color Degraded Environment (Chao Wang, Sheng Liu, Jianhua Zhang, Yuan Feng, Shengyong Chen)....Pages 465-476 Structure-Aware SLAM with Planes in Man-Made Environment (Jiyuan Zhang, Gang Zeng, Hongbin Zha)....Pages 477-489 Key Words Extraction and Semantic-Based Image Retrieval on RNNs (Lifei Han, Guanghua Gu)....Pages 490-499 Learning the Frame-2-Frame Ego-Motion for Visual Odometry with Convolutional Neural Network (Mingqi Qiao, Zilei Wang)....Pages 500-511 Front Matter ....Pages 513-513 A Progressive Method of Simplifying Polylines with Multi-bends Simplification Templates (Jiawei Du, Fang Wu, Jinghan Li, Haiwei He)....Pages 515-528 Infrared and Visible Image Registration Based on Hypercolumns (Zhenbing Zhao, Lingling Zhao, Yincheng Qi, Ke Zhang, Lei Wang)....Pages 529-539 4 Collinear Points: Robust Point Set Registration Using Cross Ratio Invariance (Yiru Wang, Yinlong Liu, Zhijian Song, Manning Wang)....Pages 540-550 A Kind of Affine Weighted Moment Invariants (Hanlin Mo, Shirui Li, You Hao, Hua Li)....Pages 551-564 Front Matter ....Pages 565-565 A Weighted Locally Linear KNN Model for Image Recognition (Yu-Lan Xu, Sibao Chen, Bin Luo)....Pages 567-578 Analysis of Positioning Performance of the Algorithm of Time Sum of Arrival with RMSE (Fengxun Gong, Ma Yanqiu)....Pages 579-591 A Novel Automatic Grouping Algorithm for Feature Selection (Qiulong Yuan, Yuchun Fang)....Pages 592-603 Front Matter ....Pages 605-605 Deep Key Frame Extraction for Sport Training (Meng Jian, Shijie Zhang, Xiangdong Wang, Yudi He, Lifang Wu)....Pages 607-616 Human Action Recognition Based on Sub-data Learning (Yang Chen, Tian Wang, Jiakun Li, Xiaowei Lv, Hichem Snoussi)....Pages 617-626 Hashing Based State Variation for Human Motion Segmentation (Yang Liu, Lin Feng, Muxin Sun, Shenglan Liu)....Pages 627-638 Improvement on Tracking Based on Motion Model and Model Updater (Tong Liu, Chao Xu, Zhaopeng Meng, Wanli Xue, Chao Li)....Pages 639-650 Learning Zeroth Class Dictionary for Human Action Recognition (Jiaxin Cai, Xin Tang, Lifang Zhang, Guocan Feng)....Pages 651-666 Global Motion Pattern Based Event Recognition in Multi-person Videos (Lifang Wu, Jiaoyu He, Meng Jian, Siyuan Liu, Yaowen Xu)....Pages 667-676 Hierarchical Convolutional Features for Long-Term Correlation Tracking (Huizhi Chen, Baojie Fan)....Pages 677-686 Front Matter ....Pages 687-687 Saliency Detection Using Texture and Local Cues (Qiang Qi, Muwei Jian, Yilong Yin, Junyu Dong, Wenyin Zhang, Hui Yu)....Pages 689-699 An Improved Saliency Detection Method Using Hypergraphs on Adaptive Multiscales (Feilin Han, Aili Han, Jing Hao)....Pages 700-710 Visual Saliency Detection via Prior Regularized Manifold Ranking (Yun Xiao, Bo Jiang, Zhengzheng Tu, Jin Tang)....Pages 711-722 Back Matter ....Pages 723-729