Similarity Mapping with Enhanced Siamese Network for Multi-Object Tracking

Minyoung E. Kim, Stefano Alletto, Luca Rigazio

Abstract:

Multi-object tracking has recently become an important area of computer vision,
especially for Advanced Driver Assistance Systems (ADAS). Despite growing
attention, achieving high performance tracking is still challenging, with state-of-theart systems resulting in high complexity with a large number of hyper parameters.
In this paper, we focus on reducing overall system complexity and the number
hyper parameters that need to be tuned to a specific environment. We introduce a
novel tracking system based on similarity mapping by Enhanced Siamese Neural
Network (ESNN), which accounts for both appearance and geometric information,
and is trainable end-to-end. Our system achieves competitive performance in both
speed and accuracy on MOT16 challenge and KITTI benchmarks, compared to
known state-of-the-art methods.