Online Multi-target Tracking by Large Margin Structured Learning
Online Multi-target Tracking by Large Margin Structured Learning
复制标题
DOI：
10.1007/978-3-642-37431-9_8
复制
发表时间：
2012-11
期刊：
影响因子：
--
通讯作者：
Suna Kim;Suha Kwak;Jan Feyereisl;Bohyung Han
中科院分区：
文献类型：
--
作者：
Suna Kim;Suha Kwak;Jan Feyereisl;Bohyung Han
提出了一种基于结构化预测的多目标在线数据关联算法。该问题被描述为一个二部匹配问题，并采用一种广义分类方法，即结构支持向量机(S-支持向量机)进行求解。我们的结构分类器是基于匹配结果训练的，给出了两个连续帧中识别的所有对象对之间的相似性，其中相似性可以由外观、位置、运动等各种特征来定义。在S支持向量机中，通过适当的联合特征映射和损失函数，在训练中找到最违反的约束并在测试中预测结构化标签，利用二部图中简单高效的Kuhn-Munkres(匈牙利)算法建模。该结构分类器可以有效地推广到多个序列，而无需重新训练。我们的算法还提供了一种方法，通过引入虚拟代理-二部图中的额外节点-来处理进入/离开对象、短期遮挡和误检测。我们在多个数据集上测试了我们的算法，获得了与最先进的方法相当的结果，具有很高的效率和简单性。
We present an online data association algorithm for multi-object tracking using structured prediction. This problem is formulated as a bipartite matching and solved by a generalized classification, specifically, Structural Support Vector Machines (S-SVM). Our structural classifier is trained based on matching results given the similarities between all pairs of objects identified in two consecutive frames, where the similarity can be defined by various features such as appearance, location, motion, etc. With an appropriate joint feature map and loss function in the S-SVM, finding the most violated constraint in training and predicting structured labels in testing are modeled by the simple and efficient Kuhn-Munkres (Hungarian) algorithm in a bipartite graph. The proposed structural classifier can be generalized effectively for many sequences without re-training. Our algorithm also provides a method to handle entering/leaving objects, short-term occlusions, and misdetections by introducing virtual agents—additional nodes in a bipartite graph. We tested our algorithm on multiple datasets and obtained comparable results to the state-of-the-art methods with great efficiency and simplicity.