论文标题
SFTRACK ++：一种快速学习的光谱分割方法，用于时空一致跟踪
SFTrack++: A Fast Learnable Spectral Segmentation Approach for Space-Time Consistent Tracking
论文作者
论文摘要
我们提出了一种对象跟踪方法SFTRACK ++，该方法顺利学习，通过在视频中使用光谱群集方法在图像图上采用光谱群集方法来保留在空间和时间维度上的跟踪对象一致性，并使用快速的3D滤波表述，以找到该图邻接矩阵的主要特征向量的快速3D过滤公式。为了更好地捕获轨道对象的复杂方面，我们将我们的公式丰富到多通道输入，这允许相同输入的不同观点。通道输入是在我们的实验中，即多种跟踪方法的输出。将它们结合在一起后，我们不仅依靠隐藏的图层表示预测一个良好的跟踪边界框，还明确地学习了一个中间体，更精致的框，即跟踪对象的分割图。这样可以防止在学习过程中引入噪音和干扰因素的粗糙共同边界框方法。我们在五个跟踪基准上测试了我们的方法SFTRACK ++：OTB，UAV，NFS，GOT-10K和TRACKINGNET，使用五个顶级跟踪器作为输入。我们的实验结果验证了预注册的假设。我们获得了一致，强大的结果，这是在三个传统基准（OTB，UAV，NFS）上竞争的，并且在GOT-10K和TrackingNet上，在其他基准（准确性上$ 1.1 \％$ $ 1.1 \％$）上都显着，它们是新的，更大的，更大的数据集。
We propose an object tracking method, SFTrack++, that smoothly learns to preserve the tracked object consistency over space and time dimensions by taking a spectral clustering approach over the graph of pixels from the video, using a fast 3D filtering formulation for finding the principal eigenvector of this graph's adjacency matrix. To better capture complex aspects of the tracked object, we enrich our formulation to multi-channel inputs, which permit different points of view for the same input. The channel inputs are in our experiments, the output of multiple tracking methods. After combining them, instead of relying only on hidden layers representations to predict a good tracking bounding box, we explicitly learn an intermediate, more refined one, namely the segmentation map of the tracked object. This prevents the rough common bounding box approach to introduce noise and distractors in the learning process. We test our method, SFTrack++, on five tracking benchmarks: OTB, UAV, NFS, GOT-10k, and TrackingNet, using five top trackers as input. Our experimental results validate the pre-registered hypothesis. We obtain consistent and robust results, competitive on the three traditional benchmarks (OTB, UAV, NFS) and significantly on top of others (by over $1.1\%$ on accuracy) on GOT-10k and TrackingNet, which are newer, larger, and more varied datasets.
