The increasingly dense traffic is becoming a challenge in our local settings, urging the need for a better traffic monitoring and management system. Fine-grained vehicle classification appears to be a challenging task as compared to vehicle coarse classification. Exploring a robust approach for vehicle detection and classification into fine-grained categories is therefore essentially required. Existing Vehicle Make and Model Recognition (VMMR) systems have been developed on synchronized and controlled traffic conditions. Need for robust VMMR in complex, urban, heterogeneous, and unsynchronized traffic conditions still remain an open research area. In this paper, vehicle detection and fine-grained classification are addressed using deep learning. To perform fine-grained classification with related complexities, local dataset THS-10 having high intraclass and low interclass variation is exclusively prepared. The dataset consists of 4250 vehicle images of 10 vehicle models, i.e., Honda City, Honda Civic, Suzuki Alto, Suzuki Bolan, Suzuki Cultus, Suzuki Mehran, Suzuki Ravi, Suzuki Swift, Suzuki Wagon R and Toyota Corolla. This dataset is available online. Due to having almost no design variation in some make and models over the years, vehicle models are not separated by their year of generation. Two approaches have been explored and analyzed for classification of vehicles i.e., fine-tuning, and feature extraction from deep neural networks. A comparative study is performed, and it is demonstrated that simpler approaches can produce good results in local environment to deal with complex issues such as dense occlusion and lane departures. Hence reducing computational load and time, e.g. finetuning Inception-v3 produced highest accuracy of 97.4% with lowest misclassification rate of 2.08%. Finetuning MobileNet-v2 and ResNet-18 produced 96.8% and 95.7% accuracies, respectively. Extracting features from fc6 layer of AlexNet produces an accuracy of 93.5% with a misclassification rate of 6.5%.
Fine-Grained Vehicle Classification in Urban Traffic Scenes Using Deep Learning
Lect. Notes Electrical Eng.
Proceedings of the 11th International Conference on Robotics, Vision, Signal Processing and Power Applications ; Chapter : 138 ; 902-908
2022-02-11
7 pages
Article/Chapter (Book)
Electronic Resource
English
Vehicle detection , Vehicle classification , Fine-grained classification , Deep learning , Transfer learning , Deep neural networks , Urban traffic scenario Engineering , Control, Robotics, Mechatronics , Signal, Image and Speech Processing , Power Electronics, Electrical Machines and Networks , Artificial Intelligence , Computational Intelligence
Fine-Grained Road Quality Monitoring Using Deep Learning
IEEE | 2023
|Privacy protection method for fine-grained urban traffic modeling using mobile sensors
Online Contents | 2013
|A survey on deep learning-based fine-grained object classification and semantic segmentation
British Library Online Contents | 2017
|