当前位置: X-MOL 学术Pattern Anal. Applic. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Target re-aware deep tracking based on correlation filters updated online
Pattern Analysis and Applications ( IF 3.7 ) Pub Date : 2021-05-15 , DOI: 10.1007/s10044-021-00982-0
Yunji Zhao , Cunliang Fan , Xinliang Zhang , Xiangjun Chen

Deep trackers often use convolutional neural networks (CNNs) pre-trained to extract features. The training dataset always does not contain the tracking objects. Even the objects appearing in the training dataset may always be in arbitrary forms. Therefore, the pre-trained convolutional neural networks extract features with less effectiveness in describing the tracking object. Target-aware deep tracking (TADT) algorithm proposes a scheme to acquire target-aware deep features by an improved regression loss and a ranking loss. Target awareness is achieved by calculating the back-propagation gradients at each pixel in the regression. Multi-channel deep features gradients captured in the first frame affect the efficiency of the tracking in subsequent frames. If the target-aware scheme is updated online, the tracking efficiency can be further improved. In this work, we present a target-aware scheme updated online to re-select deep features generalizing the object appearance more effectively. The base deep features are extracted by the pre-trained VGG16 and further processed to acquire the target awareness deep features. The awareness deep features are re-selected as re-awareness deep features in the framework of correlation filters with parameters updated online. Correlation filters updated online replace improved regression loss to re-identify the importance of features by global average pooling deep features weights. The re-awareness deep features are integrated with a Siamese matching network to determine the target's location and scale in the subsequent frame. Experimental results demonstrate the effectiveness of our presented algorithm compared with TADT in terms of accuracy and speed.



中文翻译:

基于在线更新的相关过滤器进行目标重新感知深度跟踪

深度跟踪器通常使用经过预训练的卷积神经网络(CNN)来提取特征。训练数据集始终不包含跟踪对象。即使出现在训练数据集中的对象也可能始终是任意形式。因此,预训练的卷积神经网络提取的特征在描述跟踪对象方面效率较低。目标感知深度跟踪(TADT)算法提出了一种通过改善回归损失和排名损失来获取目标感知深度特征的方案。通过计算回归中每个像素的反向传播梯度,可以实现目标感知。在第一帧中捕获的多通道深度特征梯度会影响后续帧中的跟踪效率。如果目标识别方案是在线更新的,则跟踪效率可以进一步提高。在这项工作中,我们提出了一种在线更新的目标感知方案,以重新选择更有效地概括对象外观的深层特征。基本的深度特征由预先训练的VGG16提取,并进行进一步处理以获取目标意识的深度特征。在具有在线更新的参数的相关性过滤器框架中,意识深层特征被重新选择为意识深层特征。在线更新的相关过滤器替代了改进的回归损失,以通过全局平均汇总深度特征权重来重新确定特征的重要性。重新感知深度功能与暹罗匹配网络集成在一起,可以确定目标在后续帧中的位置和规模。实验结果表明,与TADT相比,本文提出的算法在准确性和速度上均有效。

更新日期:2021-05-15
down
wechat
bug