Abstract
Vehicle Logo Recognition (VLR) is an important part of vehicle behavior analysis and can provide supplementary information for vehicle identification, which is an essential research topic in robotic systems. However, the inaccurate extraction of vehicle logo candidate regions will affect the accuracy of logo recognition. Additionally, the existing methods have low recognition rate for most small vehicle logos and poor performance under complicated environments. A VLR method based on enhanced matching, constrained region extraction and SSFPD network is proposed in this paper to solve the aforementioned problems. A constrained region extraction method based on segmentation of the car head and car tail is proposed to accurately extract the candidate region of logo. An enhanced matching method is proposed to improve the detection performance of small objects, which augment each of training images by copy-pasting small objects many times in the unconstrained region. A single deep neural network based on a reduced ResNeXt model and Feature Pyramid Networks is proposed in this paper, which is named as Single Shot Feature Pyramid Detector (SSFPD). The SSFPD uses the reduced ResNeXt to improve classification performance of the network and retain more detailed information for small-sized vehicle logo detection. Additionally, it uses the Feature Pyramid Networks module to bring in more semantic context information to build several high-level semantic feature maps, which effectively improves recognition performance. Extensive evaluations have been made on self-collected and public vehicle logo datasets. The proposed method achieved 93.79% accuracy on the Common Vehicle Logos Dataset and 99.52% accuracy on another public dataset, respectively, outperforming the existing methods.
Highlights
Vehicle Logo Recognition (VLR) is an important part of vehicle behavior analysis and can provide supplementary information for vehicle identification, which is an essential research topic in robotic systems
An enhanced matching approach based on constrained region segmentation and copy-pasting strategy is proposed to improve the contribution of small objects to feature learning in network training, which is verified in the experiment
The second part is enhanced matching for small objects, which consist of constrained region segmentation and copy-pasting strategy
Summary
Vehicle Logo Recognition (VLR) is an important part of vehicle behavior analysis and can provide supplementary information for vehicle identification, which is an essential research topic in robotic systems. The low match rate between small ground-truth logos and predicted anchors will result in small objects contributing less to feature learning during network training To alleviate this problem, an enhanced matching method based on constrained region segmentation and copy-pasting strategy is proposed to improve match rate of small logos. An enhanced matching approach based on constrained region segmentation and copy-pasting strategy is proposed to improve the contribution of small objects to feature learning in network training, which is verified in the experiment. In order to further improve the detection accuracy, the proposed SSFPD network uses a better feature network to improve the capability of feature extraction, and adds more semantic information about the small object for the prediction process.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have