Enhancing vehicle-mountable multiple object tracking systems with embeddable Ising machines

Kosuke Tatsumura, Yohei Hamakawa, Masaya Yamasaki, Koji Oya, Hiroshi Fujimoto · 2025

Read Enhancing vehicle-mountable multiple object tracking systems with embeddable Ising machines by Kosuke Tatsumura, Yohei Hamakawa, Masaya Yamasaki, Koji Oya, Hiroshi Fujimoto (2025) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-12808164.txt.

Description

Kosuke Tatsumura and four co-authors put a quantum-inspired chip to work tracking many objects for cars, in a 2025 paper. Self-driving rigs must follow each car and walker across video frames. Matching this frame's finds to the last frame's is a hard puzzle with many combos. The team's system hands that puzzle to an embedded Ising machine, a chip built for such matching tasks, running a quantum-inspired method.

The setup lets the matching rules bend to cover long blocks, where a walker hides behind a truck and returns. On a car-mountable platform, the whole chain ran past 20 frames per second in real time. That pace meets the needs of live driving aids. The authors say pairing sharp detectors with solver chips, not just bigger networks, is a sound path for tracking that must not lose its targets.

Catalog record

CREATORKosuke Tatsumura, Yohei Hamakawa, Masaya Yamasaki, Koji Oya, Hiroshi Fujimoto
YEAR2025
COLLECTIONPAPERS
FORMATTXT
FILE SIZE82 KB
VERSION1.0
LICENSECC BY 4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/articles/PMC12808164

Browse the full library · About the Tower of Babel