In this paper, we view multiple object tracking as a graph partitioning problem. Given any object detector, we build the graph of all detections and aim to partition it into trajectories. To quantify the similarity of any two detections, we consider local cues such as point tracks and speed, global cues such as appearance, as well as intermediate ones such as trajectory straightness. These different clues are dealt jointly to make the approach robust to detection mistakes (missing or extra detections). We thus define a Conditional Random Field and optimize it using an efficient combination of message passing and move-making algorithms. Our approach is fast on video batch sizes of hundreds of frames. Competitive and stable results on varied videos demonstrate the robustness and efficiency of our approach.
Paper
Full text
Multiple Object Tracking by Efficient Graph Partitioning
Semantic Scholar · Computer Science · 2014
Abstract
In this paper, we view multiple object tracking as a graph partitioning problem. Given any object detector, we build the graph of all detections and aim to partition it into trajectories. To quantify the similarity of any two detections, we consider local cues such as point tracks and speed, global cues such as appearance, as well as intermediate ones such as trajectory straightness. These different clues are dealt jointly to make the approach robust to detection mistakes (missing or extra detections). We thus define a Conditional Random Field and optimize it using an efficient combination of message passing and move-making algorithms. Our approach is fast on video batch sizes of hundreds of frames. Competitive and stable results on varied videos demonstrate the robustness and efficiency of our approach.