English  |  正體中文  |  简体中文  |  全文筆數/總筆數 : 96218/96218 (100%)
造訪人次 : 93570868      線上人數 : 11477
RC Version 7.0 © Powered By DSPACE, MIT. Enhanced by NTU Library IR team.
搜尋範圍 查詢小技巧:
  • 您可在西文檢索詞彙前後加上"雙引號",以獲取較精準的檢索結果
  • 若欲以作者姓名搜尋,建議至進階搜尋限定作者欄位,可獲得較完整資料
  • 進階搜尋


    請使用永久網址來引用或連結此文件: https://ir.lib.ncu.edu.tw/handle/987654321/110304


    題名: Human Trajectory Prediction Model: A Lightweight Latent-Variable Framework For Efficient Multi-Agent Motion Forecasting;Human Trajectory Prediction Model: A Lightweight Latent-Variable Framework For Efficient Multi-Agent Motion Forecasting
    作者: 何瑞曼;IFTIKHAR, AHMAD RAZA
    貢獻者: 機械工程學系光機電工程研究所
    關鍵詞: 軌跡預測;行人運動;潛在變數模型;變分推論;LSTM;GRU;ETH-UCY;Stanford Drone Dataset;BYTETracker;運動分類;自主系統。;Trajectory Prediction;Pedestrian Motion;Latent Variable Model;Variational Inference;LSTM;GRU;ETH-UCY;Stanford Drone Dataset;BYTETracker;Motion Classification;Autonomous Systems
    日期: 2026-08-25
    上傳時間: 2026-10-20 15:31:05 (UTC+8)
    出版者: 國立中央大學
    摘要: 摘要
    準確預測行人軌跡,是自主系統在與人類共享的環境中運作時的一項基本需求。本論文提出
    人類軌跡預測模型(Human Trajectory Prediction Model, HTPM),這是一種用於多智能體行人
    軌跡預測的機率式潛在變數架構。HTPM 使用具有時間注意力池化的長短期記憶網路(Long
    Short-Term Memory, LSTM)局部時間編碼器,對每一位智能體的觀測運動歷史進行編碼。情境
    投影層將所得的智能體嵌入映射為精簡表示,而輕量化全域聚合器則透過跨智能體的注意力池
    化形成場景層級描述子。條件式潛在模組參數化一個對角高斯先驗,並在訓練期間參數化一個
    變分對角高斯後驗。取樣得到的潛在碼由自迴歸門控循環單元(Gated Recurrent Unit, GRU)解
    碼器進行解碼;該解碼器以涵蓋完整預測時間範圍的多步負對數似然目標進行訓練。
    本模型在 ETH-UCY 基準上進行評估,使用五個標準行人場景:ETH、Hotel、Univ、Zara-1
    與 Zara-2。在留一法(leave-one-out)best-of-20 協定下,HTPM 在五個資料分割上的平均 ADE
    為 0.1174 m,平均 FDE 為 0.1969 m;場景層級 ADE 的範圍從 Zara-2 的 0.099 m 到 ETH 的
    0.145 m。另於 Stanford Drone Dataset(SDD)上進行額外評估,並採用 PECNet/Y-Net 的像素
    空間前處理慣例(÷20),得到 ADE = 5.97 ± 0.03 pixels 與 FDE = 9.12 ± 0.08 pixels,結果來自
    100 次獨立測試執行。這些結果顯示,在所述前處理設定下,隨機取樣具有穩定性;然而,更
    廣泛的跨資料集泛化仍取決於資料集尺度與攝影機幾何條件。
    本論文亦提出一套運動感知視覺化流程,結合 YOLOv12x 行人偵測、BYTETracker 身分追
    蹤與 HTPM 軌跡預測。三層級運動分類器會對靜止智能體抑制預測扇形,對慢速移動智能體繪
    製精簡扇形,並對步行智能體顯示五假設扇形。ETH Hotel 與 Zara-1 上的定性範例顯示,在所
    選影格中,該方法能減少視覺雜訊,並改善預測扇形與觀測運動方向之間的對齊。HTPM 含有
    516 K 個參數,需要 28 M 次乘加運算(multiply-accumulate operations, MACs),並在 NVIDIA
    RTX 3090 GPU 上達到每位智能體平均 23 µs 的推論延遲,支持即時桌上型 GPU 推論,並為未
    來與機器人導航系統整合提供動機。
    關鍵詞:軌跡預測、行人運動、潛在變數模型、變分推論、LSTM、GRU、ETH-UCY、Stanford
    Drone Dataset、BYTETracker、運動分類、自主系統。;Abstract
    Accurate prediction of pedestrian trajectories is a fundamental requirement for autonomous
    systems operating in shared human environments. This thesis presents the Human Trajectory
    Prediction Model (HTPM), a probabilistic latent-variable architecture for multi-agent pedestrian
    trajectory prediction. HTPM encodes each agent’s observed motion history using a Long Short-
    Term Memory (LSTM) local temporal encoder with temporal attention pooling. A context
    projection layer maps the resulting agent embedding into a compact representation, and a
    lightweight global aggregator forms a scene-level descriptor through attentive pooling across
    agents. A conditional latent module parameterises a diagonal Gaussian prior and, during training,
    a variational diagonal Gaussian posterior. Sampled latent codes are decoded by an autoregressive
    Gated Recurrent Unit (GRU) decoder trained with a multi-step negative log-likelihood objective
    over the full prediction horizon.
    The model is evaluated on the ETH-UCY benchmark using the five standard pedestrian scenes:
    ETH, Hotel, Univ, Zara-1, and Zara-2. Under the leave-one-out best-of-20 protocol, HTPM
    obtains a mean ADE of 0.1174 m and a mean FDE of 0.1969 m across the five splits, with scene-
    level ADE ranging from 0.099 m on Zara-2 to 0.145 m on ETH. Additional evaluation on the
    Stanford Drone Dataset (SDD), using the PECNet/Y-Net pixel-space preprocessing convention
    (÷20), gives ADE = 5.97 ± 0.03 pixels and FDE = 9.12 ± 0.08 pixels over 100 independent
    test runs. These results indicate stable stochastic sampling under the stated preprocessing
    settings, while broader cross-dataset generalisation remains dependent on dataset scale and
    camera geometry.
    The thesis also introduces a motion-aware visualisation pipeline that combines YOLOv12x
    pedestrian detection, BYTETracker identity tracking, and HTPM trajectory prediction. A three-
    tier motion classifier suppresses prediction fans for stationary agents, renders compact fans
    for slow-moving agents, and displays five-hypothesis fans for walking agents. Qualitative
    examples on ETH Hotel and Zara-1 illustrate reduced visual clutter and improved alignment
    between predicted fans and observed motion direction in selected frames. HTPM contains
    516 K parameters, requires 28 M multiply-accumulate operations (MACs), and achieves a mean
    inference latency of 23 µs per agent on an NVIDIA RTX 3090 GPU, supporting real-time
    desktop-GPU inference and motivating future integration with robotic navigation systems.
    Keywords: Trajectory Prediction, Pedestrian Motion, Latent Variable Model, Variational Infer-
    ence, LSTM, GRU, ETH-UCY, Stanford Drone Dataset, BYTETracker, Motion Classification,
    Autonomous Systems.
    顯示於類別:[光機電工程研究所 ] 博碩士論文

    文件中的檔案:

    檔案 描述 大小格式瀏覽次數
    index.html0KbHTML5檢視/開啟


    在NCUIR中所有的資料項目都受到原著作權保護.

    社群 sharing

    ::: Copyright National Central University. | 國立中央大學圖書館版權所有 | 收藏本站 | 設為首頁 | 最佳瀏覽畫面: 1024*768 | 建站日期:8-24-2009 :::
    DSpace Software Copyright © 2002-2004  MIT &  Hewlett-Packard  /   Enhanced by   NTU Library IR team Copyright ©   - 隱私權政策聲明