視覺多物件追蹤技術廣泛應用於環境監測、無人機監控及國防安全等 領域。在遠距離監控與高空觀測等應用場景中，目標物件通常僅占影像中 極少數像素，且常伴隨低解析度、低對比度、邊界模糊、紋理資訊不足以 及目標外觀相似等問題，使得小目標偵測與多物件追蹤成為極具挑戰性的 研究課題。現有多物件追蹤方法多採用偵測式追蹤 (Tracking-by-Detection) 架構，先透過物件偵測模型取得目標位置，再進行跨幀的物件關聯。然 而，傳統偵測模型在多層下採樣過程中容易造成小目標特徵流失，而依賴 外觀特徵的關聯方法則容易受到目標尺度過小及外觀差異不明顯等因素影 響，導致錯誤匹配、身分切換及軌跡中斷等問題。 本研究提出 STARTrack(Small-object Trajectory-Aware Robust Tracking)， 一套基於方向一致性軌跡關聯之小目標多物件追蹤方法，從目標偵測與軌 跡追蹤兩個層面進行改進。在目標偵測方面，本研究以 YOLOv11 為基礎 架構，引入高解析度特徵層並擴展多尺度偵測頭設計，以強化淺層空間資 訊的保留能力，使模型能更有效擷取小尺度目標特徵，提升極小目標的辨 識能力與定位精度。在目標關聯方面，本研究提出結合交集比 (Intersection over Union，IoU) 與歷史軌跡中心距離之匹配成本函數，使關聯過程同時考 量目標間的空間重疊程度與運動連續性，降低因輕微位移或偵測誤差所造 成的匹配不穩定。此外，本研究亦針對卡爾曼濾波之量測噪聲模型進行調 整，透過重新配置量測噪聲權重，使狀態估測更符合小目標場景特性，進 一步減少追蹤過程中的邊界框漂移現象。最後，為提升追蹤軌跡管理的可 靠性，本研究提出基於方向一致性的重複軌跡移除機制，藉由分析軌跡運 動方向與方向相似度，有效降低目標交叉或短暫重疊時所產生的誤刪與身 分交換問題。 實驗結果顯示，本研究所提出之小目標偵測模型於 Anti-UAV Challenge Track3 資料集上，在 Precision、Recall、mAP50 與 mAP50-95 等評估指標 皆優於現有主流偵測模型，展現優異的小目標偵測能力。在多物件追蹤方 面，STARTrack 於紅外線地面目標追蹤資料集與 Anti-UAV Challenge Track3 資料集上皆取得最佳的 MOTA、IDF1 與 HOTA 表現，有效降低身分切換 次數，驗證 STARTrack 在小目標監控場景下兼具高偵測準確率、優異的追 蹤穩定性與身分一致性，具備即時追蹤之應用潛力。;Visual multi-object tracking (MOT) techniques have been widely applied in fields such as environmental monitoring， unmanned aerial vehicle (UAV) surveillance， and national defense. In applications involving long-distance surveillance and high-altitude observation， targets typically occupy only a small number of pixels in an image and are often affected by low resolution， low contrast， blurred boundaries， insufficient texture information， and similar target appearances. These factors make small-object detection and multi-object tracking highly challenging research problems. Existing multi-object tracking methods commonly adopt a Tracking-by-Detection framework， in which an object detection model is first used to obtain target locations， followed by cross-frame object association. However， conventional detection models tend to lose small-object features during successive downsampling operations. Meanwhile， association methods that rely on appearance features are susceptible to factors such as extremely small target sizes and insignificant appearance differences， resulting in incorrect matching， identity switches， and fragmented trajectories. This study proposes STARTrack (Small-object Trajectory-Aware Robust Tracking)， a small-object multi-object tracking method based on direction-consistent trajectory association， with improvements made at both the object detection and trajectory tracking levels. For object detection， YOLOv11 is adopted as the base architecture， with high-resolution feature layers introduced and multi-scale detection heads extended to enhance the preservation of shallow spatial information. This design enables the model to more effectively extract features from small-scale targets， thereby improving the detection capability and localization accuracy of extremely small objects. For target association， a matching cost function that combines Intersection over Union (IoU) and the center distance of historical trajectories is proposed. The association process simultaneously considers the degree of spatial overlap and motion continuity between targets， thereby reducing matching instability caused by slight target displacement or detection errors. In addition， the measurement noise model of the Kalman Filter is adjusted by reconfiguring the measurement noise weights， enabling state estimation to better accommodate the characteristics of small-object scenarios and further reducing bounding-box drift during tracking. Finally， to improve the reliability of trajectory management， a direction-consistency-based duplicate trajectory removal mechanism is proposed. By analyzing the motion directions and directional similarities of trajectories， the proposed mechanism effectively reduces incorrect trajectory removal and identity switches caused by target crossing or temporary overlap. Experimental results demonstrate that the proposed small-object detection model outperforms existing mainstream object detection models on the Anti-UAV Challenge Track 3 dataset in terms of Precision， Recall， mAP50， and mAP50-95， demonstrating its excellent small-object detection capability. For multi-object tracking， STARTrack achieves the highest MOTA， IDF1， and HOTA performance on both the infrared ground-target tracking dataset and the Anti-UAV Challenge Track 3 dataset. The proposed method effectively reduces the number of identity switches， demonstrating that STARTrack provides high detection accuracy， excellent tracking stability， and strong identity consistency in small-object surveillance scenarios， while demonstrating its potential for real-time tracking applications.
