论文标题
PatchTrack：使用框架补丁的多个对象跟踪
PatchTrack: Multiple Object Tracking Using Frame Patches
论文作者
论文摘要
对象运动和对象外观是多个对象跟踪（MOT）应用程序中常用的信息，要么是为了在逐段追踪方法中跨帧的检测而进行检测，要么是针对关节检测和跟踪方法的直接跟踪预测。但是，这两种类型的信息不仅经常单独考虑，而且它们也无助于直接从目前关注的框架中优化视觉信息的使用。在本文中，我们提出了PatchTrack，这是一种基于变压器的关节检测和跟踪系统，可使用当前感兴趣框架的贴片预测轨道。我们使用Kalman过滤器来预测上一个帧中当前帧中现有轨道的位置。从预测的边界框中裁剪的补丁发送到变压器解码器，以推断新轨道。通过利用贴片中编码的对象运动和对象外观信息，提出的方法更加注意更可能发生新曲目的地方。我们显示了PatchTrack对最近的MOT基准的有效性，包括MOT16（MOTA 73.71％，IDF1 65.77％）和MOT17（MOTA 73.59％，IDF1 65.23％）。结果发表在https://motchallenge.net/method/mot=4725&chl=10上。
Object motion and object appearance are commonly used information in multiple object tracking (MOT) applications, either for associating detections across frames in tracking-by-detection methods or direct track predictions for joint-detection-and-tracking methods. However, not only are these two types of information often considered separately, but also they do not help optimize the usage of visual information from the current frame of interest directly. In this paper, we present PatchTrack, a Transformer-based joint-detection-and-tracking system that predicts tracks using patches of the current frame of interest. We use the Kalman filter to predict the locations of existing tracks in the current frame from the previous frame. Patches cropped from the predicted bounding boxes are sent to the Transformer decoder to infer new tracks. By utilizing both object motion and object appearance information encoded in patches, the proposed method pays more attention to where new tracks are more likely to occur. We show the effectiveness of PatchTrack on recent MOT benchmarks, including MOT16 (MOTA 73.71%, IDF1 65.77%) and MOT17 (MOTA 73.59%, IDF1 65.23%). The results are published on https://motchallenge.net/method/MOT=4725&chl=10.
