日本フィジカルAI新聞

世界のフィジカルAIを、日本語で。

マルチオブジェクト追跡arXiv:1907.12887

関係推論を備えたエンドツーエンドの再帰型マルチオブジェクト追跡と軌道予測

End-to-end Recurrent Multi-Object Tracking and Trajectory Prediction with Relational Reasoning

シェア:XThreadsFacebookLINEはてブBluesky

物体間の相互作用を考慮しながら追跡と将来軌道予測をエンドツーエンドで同時に学習するMOHARTを提案し、注意機構ベースの関係推論が追跡・予測精度を一貫して向上させることを示した。

著者: Fabian B. Fuchs, Adam R. Kosiorek, Li Sun, Oiwi Parker Jones, Ingmar Posner

分類: cs.CV, cs.AI, cs.LG, cs.RO, stat.ML

原文アブストラクト

The majority of contemporary object-tracking approaches do not model interactions between objects. This contrasts with the fact that objects' paths are not independent: a cyclist might abruptly deviate from a previously planned trajectory in order to avoid colliding with a car. Building upon HART, a neural class-agnostic single-object tracker, we introduce a multi-object tracking method MOHART capable of relational reasoning. Importantly, the entire system, including the understanding of interactions and relations between objects, is class-agnostic and learned simultaneously in an end-to-end fashion. We explore a number of relational reasoning architectures and show that permutation-invariant models outperform non-permutation-invariant alternatives. We also find that architectures using a single permutation invariant operation like DeepSets, despite, in theory, being universal function approximators, are nonetheless outperformed by a more complex architecture based on multi-headed attention. The latter better accounts for complex physical interactions in a challenging toy experiment. Further, we find that modelling interactions leads to consistent performance gains in tracking as well as future trajectory prediction on three real-world datasets (MOTChallenge, UA-DETRAC, and Stanford Drone dataset), particularly in the presence of ego-motion, occlusions, crowded scenes, and faulty sensor inputs.

関連論文

  1. 1Boston Dynamics、車輪付きAtlasの研究試作機を紹介研究・技術
  2. 2GXOとApptronik、Apolloの物流現場試験を拡大 最大1,000台の展開を構想量産・展開
  3. 3newmoとKDDIが資本業務提携 2028年に堺市で自動運転タクシー商用化目指す提携・買収
  4. 4NVIDIA、CoRLでGR00T 2とIsaac Lab 3.0を発表新製品・発表
  5. 5UC BerkeleyとNVIDIAの研究者、AIエージェントでロボット制御コードを仮想環境で改善研究・技術

PR・アフィリエイト広告

MINISFORUM(ミニPC)

MINISFORUM(ミニPC)の公式広告バナーMINISFORUM公式ストアを見る ↗
PR本紙発行元 EmplifAI