Truck Axle Detection

This dataset was created to train a neural network to recognize truck axles, applied to videos recorded in a highway in the State of São Paulo, Brazil. This is still a work in progress and will be updated regularly. More info can be found in our Researchgate Lab Page or on our OrcID Profiles. The dataset includes 1737 cropped images of truck axles, divided in two folders: Axle_Dark - Images of shadowed or dark truck axles, with few features and details visible. 1034 images Format: JPEG Resolution: Various, 96dpi Axle_Clear - Images of clear truck axles, with visible details and features. 703 images Format: JPEG Resolution: Various, 96dpi Naming pattern: <video_name>_<color|gray>-<Region_of_Interest_ID>-<truck_ID>_<axle_number>.jpg If this dataset helps in any way your research, please feel free to contact the authors. We really enjoy knowing about other researcher's projects and how everybody is making use of the images on this dataset. We are also open for collaborations and to answer any questions.

本数据集旨在训练用于识别卡车车轴的神经网络，其应用数据源自巴西圣保罗州某高速公路录制的视频。目前本数据集仍处于开发阶段，将定期进行更新。更多详细信息可查阅我们的Researchgate实验室页面或个人开放研究者与贡献者标识 (ORCID) 档案。

本数据集包含1737张裁剪后的卡车车轴图像，分为两个文件夹：
1. Axle_Dark（阴影车轴图像集）：包含处于阴影覆盖或整体偏暗状态的卡车车轴图像，此类图像的特征与细节可见度较低，共包含1034张图像，格式为JPEG，分辨率各异，均为96dpi；
2. Axle_Clear（清晰车轴图像集）：包含细节与特征清晰可见的卡车车轴图像，共包含703张图像，格式为JPEG，分辨率各异，均为96dpi。

图像命名遵循以下格式：<视频名称>_<彩色|灰度>-<感兴趣区域ID>-<卡车ID>_<车轴编号>.jpg。

若本数据集对您的研究有所助益，欢迎随时与作者联系。我们十分乐意了解其他研究者的项目进展，以及该数据集图像的实际使用场景。我们亦欢迎合作意向，并乐于解答相关疑问。