A Multilayer Pyramid Network Based on Learning for Vehicle Logo Recognition
نویسندگان
چکیده
In this paper, we present a novel learning-based scheme for vehicle logo recognition (VLR). This is termed Multilayer Pyramid Network Based on Learning (MLPNL) and based the principle that considering multiple resolutions helpful extracting valuable features benefit final performance. The innovations of include (1) multilayer pyramid network, with pixel difference matrices (PDMs) as its input output feature parameters mapping one PDM to another; (2) an objective function corresponding optimization method designed facilitate learning proposed network; (3) multi-codebook-based encoding makes best use extracted from PDMs different resolutions. Extensive experiments conducted open dataset, HFUT-VL, demonstrate MLPNL outperforms state-of-the-art handcrafted descriptors non-deep-learning-based methods when fewer training samples exist. Experiments benchmark XMU, existing VLR methods. both HFUT-VL XMU faster than most deep-learning-based while maintaining nearly same rate. Code has been made available at: https://github.com/HFUT-CV/MLPNL .
منابع مشابه
Vehicle Logo Recognition Using Image Matching and Textural Features
In recent years, automatic recognition of vehicle logos has become one of the important issues in modern cities. This is due to the unlimited increase of cars and transportation systems that make it impossible to be fully managed and monitored by human. In this research, an automatic real-time logo recognition system for moving cars is introduced based on histogram manipulation. In the proposed...
متن کاملDeep learning for logo recognition
In this paper we propose a method for logo recognition using deep learning. Our recognition pipeline is composed of a logo region proposal followed by a Convolutional Neural Network (CNN) specifically trained for logo classification, even if they are not precisely localized. Experiments are carried out on the FlickrLogos-32 database, and we evaluate the effect on recognition performance of synt...
متن کاملdesigning unmanned aerial vehicle based on neuro-fuzzy systems
در این پایان نامه، کنترل نرو-فازی در پرنده هدایت پذیر از دور (پهپاد) استفاده شده است ابتدا در روش پیشنهادی اول، کنترل کننده نرو-فازی توسط مجموعه اطلاعات یک کنترل کننده pid به صورت off-line آموزش دیده است و در روش دوم یک کنترل کننده نرو-فازی on-line مبتنی بر شناسایی سیستم توسط شبکه عصبی rbf پیشنهاد شده است. سپس کاربرد این کنترل کننده در پهپاد بررسی شده است و مقایسه ای ما بین کنترل کننده های معمو...
Multilayer bootstrap network for unsupervised speaker recognition
We apply multilayer bootstrap network (MBN), a recent proposed unsupervised learning method, to unsupervised speaker recognition. The proposed method first extracts supervectors from an unsupervised universal background model, then reduces the dimension of the high-dimensional supervectors by multilayer bootstrap network, and finally conducts unsupervised speaker recognition by clustering the l...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: IEEE Transactions on Intelligent Transportation Systems
سال: 2021
ISSN: ['1558-0016', '1524-9050']
DOI: https://doi.org/10.1109/tits.2020.2981737