Online Tracking by Learning Discriminative Saliency Map with Convolutional Neural Network
Online Tracking by Learning Discriminative Saliency Map with Convolutional Neural Network
复制标题
DOI：
--
复制
发表时间：
2015-02
期刊：
影响因子：
--
通讯作者：
Seunghoon Hong;Tackgeun You;Suha Kwak;Bohyung Han
中科院分区：
文献类型：
--
作者：
Seunghoon Hong;Tackgeun You;Suha Kwak;Bohyung Han
提出了一种基于卷积神经网络学习判别显著图的在线视觉跟踪算法。给定一个离线在大规模图像库上预训练的CNN，我们的算法将网络隐藏层的输出作为特征描述符，因为它们在各种一般视觉识别问题中表现出出色的表示性能。使用在线支持向量机（SVM）的功能来学习判别目标外观模型。此外，我们通过在SVM的指导下对CNN特征进行反向投影来构建特定于目标的显著性图，并基于显著性图生成的外观模型来获得每帧的最终跟踪结果。由于显著图有效地揭示了目标的空间结构，提高了目标定位精度，使我们能够实现像素级的目标分割。我们验证了我们的跟踪算法的有效性，通过广泛的实验上具有挑战性的基准，我们的方法说明了出色的性能相比，国家的最先进的跟踪算法。
We propose an online visual tracking algorithm by learning discriminative saliency map using Convolutional Neural Network (CNN). Given a CNN pre-trained on a large-scale image repository in offline, our algorithm takes outputs from hidden layers of the network as feature descriptors since they show excellent representation performance in various general visual recognition problems. The features are used to learn discriminative target appearance models using an online Support Vector Machine (SVM). In addition, we construct target-specific saliency map by backprojecting CNN features with guidance of the SVM, and obtain the final tracking result in each frame based on the appearance model generatively constructed with the saliency map. Since the saliency map reveals spatial configuration of target effectively, it improves target localization accuracy and enables us to achieve pixel-level target segmentation. We verify the effectiveness of our tracking algorithm through extensive experiment on a challenging benchmark, where our method illustrates outstanding performance compared to the state-of-the-art tracking algorithms.