Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Instance flow based online multiple object tracking

: Bullinger, Sebastian; Bodensteiner, Christoph; Arens, Michael

Postprint urn:nbn:de:0011-n-4701527 (604 KByte PDF)
MD5 Fingerprint: f6d556fc1041b096df95a5d43ccbcfc7
© IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.
Created on: 24.10.2017

Institute of Electrical and Electronics Engineers -IEEE-; IEEE Signal Processing Society:
IEEE International Conference on Image Processing, ICIP 2017. Proceedings : 17-20 September 2017, Beijing, China
Piscataway, NJ: IEEE, 2017
ISBN: 978-1-5090-2175-8
ISBN: 978-1-5090-2174-1
ISBN: 978-1-5090-2176-5
International Conference on Image Processing (ICIP) <2017, Beijing>
Conference Paper, Electronic Publication
Fraunhofer IOSB ()
online multiple object tracking; instance segmentation; optical flow

We present a method to perform online Multiple Object Tracking (MOT) of known object categories in monocular video data. Current Tracking-by-Detection MOT approaches build on top of 2D bounding box detections. In contrast, we exploit state-of-the-art instance aware semantic segmentation techniques to compute 2D shape representations of target objects in each frame. We predict position and shape of segmented instances in subsequent frames by exploiting optical flow cues. We define an affinity matrix between instances of subsequent frames which reflects locality and visual similarity. The instance association is solved by applying the Hungarian method. We evaluate different configurations of our algorithm using the MOT 2D 2015 train dataset. The evaluation shows that our tracking approach is able to track objects with high relative motions. In addition, we provide results of our approach on the MOT 2D 2015 test set for comparison with previous works. We achieve a MOTA score of 32:1.