Similarity Mapping with Enhanced Siamese Network for Multi-Object Tracking

TL;DR

This paper presents a novel multi-object tracking system using an Enhanced Siamese Neural Network that combines appearance and geometric data, reducing system complexity while maintaining competitive accuracy and speed.

Contribution

The paper introduces an end-to-end trainable similarity mapping system with an Enhanced Siamese Network that simplifies hyper parameter tuning and improves tracking performance.

Findings

Achieves competitive speed and accuracy on MOT16 benchmark.

Reduces system complexity and hyper parameter tuning.

Combines appearance and geometric information effectively.

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-the- art 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, compared to known state-of-the-art methods.