The problem of vehicle licence plate re-identification is generally considered as a one-shot image retrieval problem. The objective of this task is to learn a feature representation (called a "signature") for licence plates. Incoming licence plate images are converted to signatures and matched to a previously collected template database through a distance measure. Then, the input image is recognized as the template whose signature is "nearest" to the input signature. The template database is restricted to contain only a single signature per unique licence plate for our problem.
We measure the performance of deep convolutional net-based features adapted from face recognition on this task. In addition, we also test a hybrid approach combining the Fisher vector with a neural network-based embedding called "f2nn" trained with the Triplet loss function. We find that the hybrid approach performs comparably while providing computational benefits. The signature generated by the hybrid approach also shows higher generalizability to datasets more dissimilar to the training corpus.
A Two-Stream Siamese Neural Network for Vehicle Re-Identification by Using Non-Overlapping Cameras
Federal University of Technology - Paran\' a (UTFPR), Curitiba, Brazil
本文描述了一种用于车辆再识别的双流连体神经网络。所提出的网络同时被馈送有车辆形状的小的粗糙补丁,在一个流中具有96 x 96像素,并且在另一个流中具有96 x 48像素,从车牌补丁中提取的精细特征,容易被人类读取。然后,我们通过将Siamese距离描述符与一系列完全连接的层合并,将两个流的优势结合起来,试图解决该领域的一个主要问题,即由大量外观几乎相同的汽车设计和模型或相似的车牌字符串引起的误报。在我们的实验中,从546英尺外的同一条道路上的两个低成本摄像机中提取了包含2982辆汽车的2小时视频,我们分别实现了92.6%和98.7%的F测量和准确度。我们表明,建议的网络,可在https://github.com/siamofua/siamese-two-stream,优于其他单流架构,即使他们使用更高分辨率的图像功能。
GSAlign: Geometric and Semantic Alignment Network for Aerial-Ground Person Re-Identification
Key Laboratory of Aerospace Information Security and Trusted Computing, Ministry of Education, School of Cyber Science and Engineering, Wuhan University(航天信息安全部与可信计算重点实验室,教育部,武汉大学计算机科学与工程学院);Xiamen University(厦门大学);National University of Singapore(新加坡国立大学)
Trends in Vehicle Re-identification Past, Present, and Future: A Comprehensive Review
University of Electronic Science and Technology of China(电子科技大学);Jiangsu University(江苏大学);National University of Computer and Emerging Sciences(国立计算机与新兴科学大学)
Towards Automated Solar Panel Integrity: Hybrid Deep Feature Extraction for Advanced Surface Defect Identification
Artificial Intelligence Technology Centre (AITeC), National Centre for Physics (NCP)(人工智能技术中心,国家物理中心);School of Computing, Pak-Austria Fachhochschule: Institute of Applied Sciences and Technology (PAFIAST)(计算学院,巴奥应用科学与技术学院);Faculty of IT and Computer Sciences, University of Central Punjab Lahore(信息技术与计算机科学学院,中央旁遮普大学拉合尔校区)