Vehicle detection in aerial imagery : A small target detection benchmark
Vehicle detection in aerial imagery : A small target detection benchmark
复制标题
DOI：
10.1016/j.jvcir.2015.11.002
复制
发表时间：
2016-01-01
影响因子：
2.6
通讯作者：
Jurie, Frederic
中科院分区：
文献类型：
--
作者：
Razakarivony, Sebastien;Jurie, Frederic
本文介绍了VEDAI：航空图像中的车辆检测，这是一个新的航空图像数据库，提供了一个在非约束环境中对自动目标识别算法进行基准测试的工具。数据库中包含的车辆除了小之外，还表现出不同的变化，如多个方向、照明/阴影变化、投射或遮挡。此外，每一幅图像都有几个光谱波段和分辨率。给出了精确的实验方案，保证了不同人的实验结果可以正确地重现和比较。最后，本文还给出了基线算法在该数据集上的性能，针对这些算法的不同设置，说明了任务的难度，并提供了基线比较。(C)2015 Elsevier Inc.保留所有权利。
This paper introduces VEDAI: Vehicle Detection in Aerial Imagery a new database of aerial images provided as a tool to benchmark automatic target recognition algorithms in unconstrained environments. The vehicles contained in the database, in addition of being small, exhibit different variabilities such as multiple orientations, lighting/shadowing changes, specularities or occlusions. Furthermore, each image is available in several spectral bands and resolutions. A precise experimental protocol is also given, ensuring that the experimental results obtained by different people can be properly reproduce and compared. Finally, the paper also gives the performance of baseline algorithms on this dataset, for different settings of these algorithms, to illustrate the difficulties of the task and provide baseline comparisons. (c) 2015 Elsevier Inc. All rights reserved.