当前位置: X-MOL 学术J. Circuits Syst. Comput. › 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.)
Object Tracking in Satellite Videos Based on a Lightweight Network
Journal of Circuits, Systems and Computers ( IF 1.5 ) Pub Date : 2021-01-07 , DOI: 10.1142/s0218126621500997
Bing Sui 1 , Meng Xu 2 , Dongdong Li 3
Affiliation  

Object tracking is a hot topic in computer vision. The significantly developed satellite video technology makes object tracking in satellite videos possible. In recent years, Convolutional Neural Network (CNN)-based trackers have achieved satisfying performance in the visual object tracking field. However, CNN cannot be directly applied to object tracking in satellite videos due to the following two reasons. First, the feature map size generally decreases as the network layer deepens, which is unsuitable for the small targets in satellite videos. Second, CNN-based trackers commonly need extensive data to train the network parameters, while few labeled satellite videos are available. Therefore, in this paper, we design a lightweight network for the satellite video tracking task. On one hand, the network generates a response map with the same size as the input image and reserves the spatial resolution of targets. On the other hand, the network parameters are transferred from an existing network and trained with the initial annotated frame, thus no extra data are needed. To make a fair comparison between existing trackers, we further propose a simulated benchmark based on the UAV123 dataset according to the imaging characteristics of satellite videos. Experiments are conducted to compare our method with other state-of-the-art trackers on both the simulated benchmark and real satellite videos and experimental results demonstrate the superiority of our proposed algorithm.

中文翻译:

基于轻量级网络的卫星视频目标跟踪

对象跟踪是计算机视觉领域的热门话题。显着发展的卫星视频技术使卫星视频中的对象跟踪成为可能。近年来,基于卷积神经网络(CNN)的跟踪器在视觉对象跟踪领域取得了令人满意的性能。然而,由于以下两个原因,CNN 不能直接应用于卫星视频中的目标跟踪。首先,特征图的大小通常随着网络层的加深而减小,这不适合卫星视频中的小目标。其次,基于 CNN 的跟踪器通常需要大量数据来训练网络参数,而可用的标记卫星视频很少。因此,在本文中,我们为卫星视频跟踪任务设计了一个轻量级网络。一方面,网络生成与输入图像大小相同的响应图,并保留目标的空间分辨率。另一方面,网络参数是从现有网络传输的,并使用初始注释帧进行训练,因此不需要额外的数据。为了对现有跟踪器进行公平比较,我们进一步根据卫星视频的成像特征提出了基于 UAV123 数据集的模拟基准。进行实验以在模拟基准和真实卫星视频上将我们的方法与其他最先进的跟踪器进行比较,实验结果证明了我们提出的算法的优越性。网络参数从现有网络转移并使用初始注释帧进行训练,因此不需要额外的数据。为了对现有跟踪器进行公平比较,我们进一步根据卫星视频的成像特征提出了基于 UAV123 数据集的模拟基准。进行实验以在模拟基准和真实卫星视频上将我们的方法与其他最先进的跟踪器进行比较,实验结果证明了我们提出的算法的优越性。网络参数从现有网络传输并使用初始注释帧进行训练,因此不需要额外的数据。为了对现有跟踪器进行公平比较,我们进一步根据卫星视频的成像特征提出了基于 UAV123 数据集的模拟基准。进行实验以在模拟基准和真实卫星视频上将我们的方法与其他最先进的跟踪器进行比较,实验结果证明了我们提出的算法的优越性。
更新日期:2021-01-07
down
wechat
bug