Veri-Car可精准识别车辆多维度信息，支持新车型持续更新。
Veri-Car: Towards Open-world Vehicle Information Retrieval
- 融合预训练模型与分层多相似性损失，应对开放世界挑战。
- 在已见和未见数据上均实现高精度分类，性能稳定可靠。
- 集成车牌检测与识别，可准确提取车牌号码，适合工业应用。
许多工业和服务领域需要从图像中提取车辆特征，但这一任务因噪声多样、类别繁多以及新车型不断上市而极具挑战。本文提出Veri-Car，一种集成式信息检索方法，能准确识别车辆的品牌、类型、型号、年份、颜色及车牌信息。该方法通过结合预训练模型与分层多相似性损失，有效应对开放世界问题，即频繁出现的新车型和变体。Veri-Car在已见和未见数据上均表现出高精度和高鲁棒性。此外，其集成了集成式车牌检测与OCR模型，可实现高精度的车牌号码提取。
原文摘要 · Abstract (English)
Many industrial and service sectors require tools to extract vehicle characteristics from images. This is a complex task not only by the variety of noise, and large number of classes, but also by the constant introduction of new vehicle models to the market. In this paper, we present Veri-Car, an information retrieval integrated approach designed to help on this task. It leverages supervised learning techniques to accurately identify the make, type, model, year, color, and license plate of cars. The approach also addresses the challenge of handling open-world problems, where new car models and variations frequently emerge, by employing a sophisticated combination of pre-trained models, and a hierarchical multi-similarity loss. Veri-Car demonstrates robust performance, achieving high precision and accuracy in classifying both seen and unseen data. Additionally, it integrates an ensemble license plate detection, and an OCR model to extract license plate numbers with impressive accuracy.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。