Target tracking is crucial to many applications in wireless sensor networks (WSNs). Existing tracking schemes used in WSNs can basically be classified two categories, clustering and predicting. Considering network clustering consumes much energy for limited-energy WSNs, a predicting target tracking scheme is proposed called MC-MPMC (measurement compensation-based mixture population Monte Carlo) which tracks the target based on predicted locations in this work. Adaptive mixture PMC model for generating proposals varying from each iteration is proposed to guarantee sampling diversity. And also, extra measurements or observations generating method is introduced to compensate missed prediction locations or false estimations, avoiding tracking behavior degradation. Firstly, samples drawn from the proposals of next iteration can be generated by a mixture method to avoid sample degeneracy. Secondly, sample weights are jointly computed based on adaptive fusion of compensation measurement and true measurements. Thirdly, HTC method is combined to MC-MPMC scheme to decrease energy consumption in WSNs. Then, the proposed method is verified through comprehensive experiments about tracking error, delay and consumption predictions. Moreover, performance comparisons of MC-MPMC with other tracking schemes are also proposed.

目标跟踪对于无线传感器网络 (WSN) 中的许多应用至关重要。WSN中使用的现有跟踪方案基本上可以分为两类，聚类和预测。考虑到网络聚类对能量有限的 WSN 消耗大量能量，提出了一种预测目标跟踪方案，称为 MC-MPMC（基于测量补偿的混合种群蒙特卡罗），该方案在这项工作中基于预测位置跟踪目标。提出了自适应混合 PMC 模型，用于生成随每次迭代变化的提议，以保证采样的多样性。此外，还引入了额外的测量或观察生成方法来补偿错过的预测位置或错误估计，避免跟踪行为退化。首先，可以通过混合方法生成从下一次迭代的提议中提取的样本，以避免样本退化。其次，基于补偿测量和真实测量的自适应融合，联合计算样本权重。第三，将 HTC 方法与 MC-MPMC 方案相结合，以降低 WSN 的能耗。然后，通过关于跟踪误差、延迟和消耗预测的综合实验验证了所提出的方法。此外，还提出了 MC-MPMC 与其他跟踪方案的性能比较。通过跟踪误差、延迟和消耗预测的综合实验验证了所提出的方法。此外，还提出了 MC-MPMC 与其他跟踪方案的性能比较。通过跟踪误差、延迟和消耗预测的综合实验验证了所提出的方法。此外，还提出了 MC-MPMC 与其他跟踪方案的性能比较。