Fine-grained vehicle type classification using lightweight convolutional neural network with feature optimization and joint learning strategy

• Published in: Multimedia tools and applications Vol. 80; no. 20; pp. 30803 - 30816
• Main Authors: Sun, Wei, Zhang, Guoce, Zhang, Xiaorui, Zhang, Xu, Ge, Nannan
• Format: Journal Article
• Language: English
• Published: New York Springer US 01.08.2021; Springer Nature B.V
• Subjects: Accuracy; Artificial neural networks; Classification; Complexity; Computer Communication Networks; Computer Science; Data Structures and Information Theory; Learning; Lightweight; Mathematical models; Multimedia Information Systems; Neural networks; Optimization; Parameters; Special Purpose and Application-Based Systems; Transport buildings, stations and terminals; Fine-grained vehicle type classification; Contrastive-center loss; Lightweight; Feature optimization
• DOI: 10.1007/s11042-020-09171-3
• ISSN: 1380-7501

Vehicle type classification (VTC) plays an important role in today’s intelligent transportation. Previous VTC systems usually run on a monitoring center’s host machine due to the models’ complexity, which consume lots of computing resources and have poor real-time performance. If these systems are deployed to embedded terminals by making the model lightweight while ensuring accuracy, then the problem can be addressed. To this end, we propose a fine-grained VTC method using lightweight convolutional neural network with feature optimization and joint learning strategy. Firstly, a lightweight convolutional network with feature optimization (LWCNN-FO) is designed. We use depthwise separable convolution to reduce network parameters. Besides, the SENet module is added to obtain the important degree of each feature channel automatically through the sample-based self-learning, which can improve recognition accuracy with less network parameters growth. In addition, considering both between-class similarity and intra-class variance, this paper adopts the joint learning strategy combining softmax loss and contrastive-center loss to class vehicle types, thereby improving model’s fine-grained classification ability. We also build a dataset, called Car-159, consisting of 7998 pictures for 159 vehicle types, to evaluate our method. Compared with the state-of-the-art methods, experimental results show that our method can effectively decrease model’s complexity while maintaining accuracy.