MARS: A Video Benchmark for Large-Scale Person Re-Identification
MARS: A Video Benchmark for Large-Scale Person Re-Identification
复制标题
DOI：
10.1007/978-3-319-46466-4_52
复制
发表时间：
2016-10
期刊：
影响因子：
--
通讯作者：
Liang Zheng;Zhi Bie;Yifan Sun;Jingdong Wang;Chi Su;Shengjin Wang;Q. Tian
中科院分区：
文献类型：
--
作者：
Liang Zheng;Zhi Bie;Yifan Sun;Jingdong Wang;Chi Su;Shengjin Wang;Q. Tian
本文研究视频中的人物再识别（re-id）问题。我们引入了一个新的视频重新识别数据集，名为运动分析和重新识别集（MARS），它是市场-1501数据集的视频扩展。据我们所知，MARS是迄今为止最大的视频重新识别数据集。与基于图像的数据集相比，它包含1,261个id和大约20,000个轨道，提供了丰富的视觉信息。与此同时，火星离实践又近了一步。轨迹由可变形部件模型（DPM）作为行人检测器和GMMCP跟踪器自动生成。一些错误的检测/跟踪结果也被列入干扰，这些干扰主要存在于实际的视频数据库中。对包括时空描述符和CNN在内的最先进的方法进行了广泛的评估。我们证明了分类模式下的CNN可以使用每个身份的连续边界框从零开始训练。学习后的CNN嵌入方法明显优于其他竞争方法，并且经过微调后对其他视频重识别数据集具有良好的泛化能力。
This paper considers person re-identification (re-id) in videos. We introduce a new video re-id dataset, namedMotionAnalysis andRe-identificationSet (MARS), a video extension of the Market-1501 dataset. To our knowledge, MARS is the largest video re-id dataset to date. Containing 1,261 IDs and around 20,000 tracklets, it provides rich visual information compared to image-based datasets. Meanwhile, MARS reaches a step closer to practice. The tracklets are automatically generated by the Deformable Part Model (DPM) as pedestrian detector and the GMMCP tracker. A number of false detection/tracking results are also included as distractors which would exist predominantly in practical video databases. Extensive evaluation of the state-of-the-art methods including the space-time descriptors and CNN is presented. We show that CNN in classification mode can be trained from scratch using the consecutive bounding boxes of each identity. The learned CNN embedding outperforms other competing methods considerably and has good generalization ability on other video re-id datasets upon fine-tuning.