From Certain to Uncertain: Toward Optimal Solution for Offline Multiple Object Tracking

Zhao, Kaikai; Imaseki, Takashi; Mouri, Hiroshi; Suzuki, Einoshin; Matsukawa, Tetsu

doi:10.1109/icpr48806.2021.9413215

Cited by 3 publications

(1 citation statement)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The data association problem can be solving using either online or offline approaches. In offline approaches, all the frames are required and analyzed to associate detections [19,39,40,45], whereas in online approaches, only adjacent frames are used [7,16,36,43]. For instance, [3] combines the Kalman Filter and Hungarian algorithm to effiicently associate objects.…”

Section: Related Workmentioning

confidence: 99%

Towards PAC Multi-Object Detection and Tracking

Li¹,

Park²,

Ji³

et al. 2022

Preprint

View full text Add to dashboard Cite

Accurately detecting and tracking multi-objects is important for safety-critical applications such as autonomous navigation. However, it remains challenging to provide guarantees on the performance of state-of-the-art techniques based on deep learning. We consider a strategy known as conformal prediction, which predicts sets of labels instead of a single label; in the classification and regression settings, these algorithms can guarantee that the true label lies within the prediction set with high probability. Building on these ideas, we propose multi-object detection and tracking algorithms that come with probably approximately correct (PAC) guarantees. They do so by constructing both a prediction set around each object detection as well as around the set of edge transitions; given an object, the detection prediction set contains its true bounding box with high probability, and the edge prediction set contains its true transition across frames with high probability. We empirically demonstrate that our method can detect and track objects with PAC guarantees on the COCO and MOT-17 datasets.

show abstract