TY - GEN
T1 - Selective Multi-Convolutional Region Feature Extraction based Iterative Discrimination CNN for Fine-Grained Vehicle Model Recognition
AU - Tian, Yanling
AU - Zhang, Weitong
AU - Zhang, Qieshi
AU - Lu, Gang
AU - Wu, Xiaojun
N1 - Funding Information:
ACKNOWLEDGMENT This work was supported by Natural Science Basic Research Plan in Shaanxi Province of China (Grant No. 2017JM6060, 2017JQ6077, 2017JM6101, 2017JM6103), Fundamental Research Funds for the Central Universities (Grant No. GK201703060, GK201801004), Teaching Reform and Research Project of Shaanxi Normal University (Grant No. 17JG33), National Natural Science Foundation of China (Grant No. 61772508, U1713213), Guangdong Technology Project (Grant No. 2016B010108010, 2016B010125003, 2017B010110007), Shenzhen Technology Project (Grant No. JCYJ20170413152535587, JSGG20160331185256983, JSGG20160229115709109), CAS Key Technology Talent Program, Shenzhen Engineering Laboratory for 3D Content Generating Technologies (Grant No. [2017]476) and Key Laboratory of Human-Machine Intelligence-Synergy Systems, Shen-zhen Institutes of Advanced Technology, Chinese Academy of Sciences (Grant No. 2014DP173025).
Publisher Copyright:
© 2018 IEEE.
PY - 2018/11/26
Y1 - 2018/11/26
N2 - With the rapid rise of computer vision and driverless technology, vehicle model recognition plays a huge role in the common application and industry field. While fine-grained vehicle model recognition is often influenced by multi-level information, such as the image perspective, inter-feature similarity, vehicle details. Furthermore, pivotal regions extraction and fine-grained feature learning have become a vital obstacle to the fine-grained recognition of vehicle models. In this paper, we propose an iterative discrimination CNN (ID-CNN) based on selective multi-convolutional region (SMCR) feature extraction. The SMCR features, which consist of global and local SMCR features, are extracted from the original image with higher activation response value. As for ID-CNN, we use the global and local SMCR features iteratively to localize deep pivotal features and concatenate them together into a fully-connected fusion layer to predict the vehicle categories. We get better results and improve the accuracy to 91.8% on Stanford Cars-196 dataset and to 96.2% on CompCars dataset.
AB - With the rapid rise of computer vision and driverless technology, vehicle model recognition plays a huge role in the common application and industry field. While fine-grained vehicle model recognition is often influenced by multi-level information, such as the image perspective, inter-feature similarity, vehicle details. Furthermore, pivotal regions extraction and fine-grained feature learning have become a vital obstacle to the fine-grained recognition of vehicle models. In this paper, we propose an iterative discrimination CNN (ID-CNN) based on selective multi-convolutional region (SMCR) feature extraction. The SMCR features, which consist of global and local SMCR features, are extracted from the original image with higher activation response value. As for ID-CNN, we use the global and local SMCR features iteratively to localize deep pivotal features and concatenate them together into a fully-connected fusion layer to predict the vehicle categories. We get better results and improve the accuracy to 91.8% on Stanford Cars-196 dataset and to 96.2% on CompCars dataset.
UR - http://www.scopus.com/inward/record.url?scp=85059065985&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85059065985&partnerID=8YFLogxK
U2 - 10.1109/ICPR.2018.8545375
DO - 10.1109/ICPR.2018.8545375
M3 - Conference contribution
AN - SCOPUS:85059065985
T3 - Proceedings - International Conference on Pattern Recognition
SP - 3279
EP - 3284
BT - 2018 24th International Conference on Pattern Recognition, ICPR 2018
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 24th International Conference on Pattern Recognition, ICPR 2018
Y2 - 20 August 2018 through 24 August 2018
ER -