With the development of economy, more and more attention has been paid to the monitoring system, which provides a reliable and powerful guarantee for people’s daily life, property security, and national security. The intelligent video surveillance introduces computer vision-related technologies into traditional video surveillance and realizes the analysis and understanding of video data without artificial dependence to obtain valuable target information in the perceived video data. On this basis, functions such as abnormal event monitoring and real-time alarm are realized. Distributed streaming media monitoring has changed the manual-based monitoring and content analysis modes of traditional monitoring, but the high-complexity calculations such as motion estimation and motion compensation in the encoding process increase the burden of monitoring and sensing equipment. Especially with the development of wireless multimedia technology, the traditional video coding has been unable to meet the requirements of monitoring and sensing equipment in the monitoring system based on wireless technology. This paper proposes an adaptive weighted tensor completion algorithm to complete the repair of streaming media data perceived by ordinary sensing devices. In the proposed algorithm, considering the unbalanced information distribution and data redundancy problems that may exist in the data, the tensor data is adjusted according to the approximate solution algorithm to obtain tensor data that only retains important information and the information distribution is more balanced and reasonable. In the iterative solution process, in order to better map the impact of each dimension of data in the repair process, an adaptive weighting mechanism is proposed according to the data characteristics to obtain the corresponding weight value of each dimension of data. Finally, the proposed approximate tensor solving algorithm and adaptive weighting mechanism are applied to a simple low-rank tensor completeness algorithm based on tensor columns to form the algorithm of this paper, and it is used to repair perceptual streaming media data with data missing problems. The experimental results show that the algorithm in this paper can improve the perceived streaming media data quality by 3% based on the known data information and maintain an advantage of 2% in average processing time. It avoids the replacement of sensing equipment and also provides data quality assurance for subsequent sensing streaming media content analysis. It has certain research significance for the development of monitoring system with artificial intelligence management for target perception and tracking.