Detection-based tracking is one of the main methods of multi-object tracking. It can obtain good tracking results when using excellent detectors but it may associate wrong targets when facing overlapping and low-confidence detections. To address this issue, this paper proposes a multi-object tracker based on shape constraint and confidence named SCTracker. In the data association stage, an Intersection of Union distance with shape constraints is applied to calculate the cost matrix between tracks and detections, which can effectively avoid the track tracking to the wrong target with the similar position but inconsistent shape, so as to improve the accuracy of data association. Additionally, the Kalman Filter based on the detection confidence is used to update the motion state to improve the tracking performance when the detection has low confidence. Experimental results on MOT 17 dataset show that the proposed method can effectively improve the tracking performance of multi-object tracking.

翻译：基于检测的跟踪是多目标跟踪的主要方法之一。当使用优秀检测器时，该方法可获得良好的跟踪效果，但在面对遮挡和低置信度检测时可能错误关联目标。针对这一问题，本文提出一种基于形状约束和置信度的多目标跟踪器SCTracker。在数据关联阶段，采用带有形状约束的交并比距离来计算轨迹与检测之间的代价矩阵，从而有效避免轨迹跟踪到位置相近但形状不一致的错误目标，进而提升数据关联的准确性。此外，基于检测置信度的卡尔曼滤波器被用于更新运动状态，以改善检测置信度较低情况下的跟踪性能。在MOT 17数据集上的实验结果表明，所提方法能够有效提升多目标跟踪的跟踪性能。