CNRPark Patches, PKLot, 自定义数据集
收藏资源简介:
该研究使用了CNRPark Patches、PKLot以及一个针对雾天停车场景的自定义数据集。CNRPark Patches和PKLot是公开的停车位检测数据集,广泛用于智能停车系统的研究中。自定义数据集则专门针对雾天条件下的停车位分类问题,旨在解决传统方法在雾天环境下性能下降的问题。这些数据集包含了不同天气条件下的停车位图像,数据量较大,涵盖了多种复杂的停车场景。数据集的创建过程包括图像采集、标注和预处理,旨在提高模型在雾天条件下的分类准确性。该数据集的应用领域主要集中在智能停车系统和自动驾驶领域,旨在通过提高停车位检测的准确性,减少驾驶员寻找停车位的时间,提升交通效率。
This study employs three datasets: CNRPark Patches, PKLot, and a custom dataset designed for foggy parking scenarios. Both CNRPark Patches and PKLot are publicly available parking space detection datasets that have been widely adopted in research on intelligent parking systems. The custom dataset is specifically developed for the parking space classification task under foggy conditions, aiming to address the performance degradation issue of traditional methods in foggy environments. These datasets contain large-scale parking space images captured under diverse weather conditions, covering a wide range of complex parking scenarios. The dataset construction process includes image collection, annotation and preprocessing, with the goal of improving the classification accuracy of models under foggy conditions. The application fields of these datasets mainly focus on intelligent parking systems and autonomous driving, aiming to reduce the time drivers spend searching for parking spaces and enhance traffic efficiency by improving the accuracy of parking space detection.

- 1Atmospheric Noise-Resilient Image Classification in a Real-World Scenario: Using Hybrid CNN and Pin-GTSVM印度理工学院比拉校区 · 2025年



