隨著第五代行動通訊技術與整合式感測與通訊（Integrated Sensing and Communication， ISAC）演進，正交分頻多工（Orthogonal Frequency Division Multiplexing， OFDM）波形在未來車聯網（Vehicle-to-Everything， V2X）之雷達感測應用中備受關注。然而，在實際的交通場景中，目標本體的雷達截面積（Radar Cross Section， RCS）差異，以及距離所引發之自由空間路徑損耗（Free Space Path Loss， FSPL），加以強弱目標間懸殊之功率差異，導致接收端獲取之目標回波訊號能量產生極大的落差。 二維快速傅立葉變換（2D-FFT）偵測方法極度依賴循環前綴（Cyclic Prefix， CP）以維持子載波正交性；目標回波之延遲若超過 CP 長度，將引發符號間干擾（Inter-Symbol Interference， ISI）破壞訊號的正交性，致使距離資訊無法正確估計。儘管導入匹配追蹤（Matching Pursuit）之壓縮感測演算法能有效克服CP 長度之距離偵測限制，然因高能量強目標之旁瓣（Side-lobe）能量往往會遮蔽低能量弱目標之主瓣（Main-lobe），仍存在弱目標無法被偵測的問題。為有效解決此強弱目標混合場景中之遮蔽效應，提出基於匹配追蹤之有序逐次干擾消除（Matching Pursuit-based Ordered Successive Interference Cancellation）演算法。本研究所提之演算法架構分為初始偵測與迭代修正兩個階段。第一階段透過匹配追蹤並結合有序逐次干擾消除機制進行初始偵測，依據回波能量由強至弱之順序初步估計目標延遲；接著，為避免強目標估測偏差引發之誤差傳遞（Error Propagation）效應，本演算法於第二階段根據初始偵測的結果，將個別目標從原始訊號中隔離，進行無干擾之訊號重建與估計。 以 5G NR FR2 參數為基礎，並建構V2X 場景進行模擬驗證。實驗結果顯示，所提演算法成功偵測所有目標，有效抑制強目標旁瓣。相較於 2D-FFT 與匹配追蹤方法，本演算法在弱目標偵測完整性方面展現顯著優勢，驗證了將 OSIC 機制引入 OFDM 雷達感測領域之可行性與有效性。;With the advancement of fifth-generation (5G) mobile communication technologies and the evolution toward Integrated Sensing and Communication (ISAC)， Orthogonal Frequency Division Multiplexing (OFDM) waveforms have attracted considerable attention for radar sensing applications in future Vehicle-to-Everything (V2X) systems. However， in realistic traffic scenarios， differences in target Radar Cross Section (RCS) and the Free Space Path Loss (FSPL) induced by varying target ranges collectively result in a large dynamic range of received echo signal power across multiple targets. The two-dimensional Fast Fourier Transform (2D-FFT) detection method relies critically on the Cyclic Prefix (CP) to maintain subcarrier orthogonality. When the propagation delay of a target echo exceeds the CP length， Inter-Symbol Interference (ISI) is introduced， destroying signal orthogonality and preventing accurate range estimation. Although Matching Pursuit (MP)-based compressed sensing algorithms can overcome the range detection limitation imposed by the CP length， the Side-lobe energy of high-power strong targets tends to mask the Main-lobe of low-power weak targets， leaving weak targets undetectable. To effectively address this masking effect in mixed strong-and-weak target scenarios， this study proposes a Matching Pursuit-based Ordered Successive Interference Cancellation (MP-Based OSIC) algorithm. The proposed algorithm operates in two stages: initial detection and refined estimation. In the first stage， Matching Pursuit combined with the ordered successive interference cancellation mechanism sequentially estimates target delays in descending order of echo energy. Subsequently， to mitigate error propagation caused by estimation bias of strong targets， the second stage isolates each individual target from the original received signal based on the initial detection results， enabling interference-free signal reconstruction and parameter re-estimation. Simulations are conducted based on 5G NR FR2 system parameters under a constructed V2X scenario. Experimental results demonstrate that the proposed algorithm successfully detects all targets and effectively suppresses strong target sidelobes. Compared with the 2D-FFT and Matching Pursuit methods， the proposed algorithm exhibits significant advantages in weak target detection completeness， validating the feasibility and effectiveness of incorporating the OSIC mechanism into OFDM radar sensing.
