Collecting network traffic is becoming a more challenging task in passive network measurement due to the rapid growth of link speed. Flow-based network traffic capture and storage provides an efficient way for high-speed network measurement. The paper concentrates on the flow detection issue which is also the premise for further flow-based traffic analysis and modeling in such challenging environment. Based on the statistical investigation of the correlations between flow size and the maximum packet interarrival time within a flow, we obtain the empirical conditional distribution functions for some popular TCP protocol-based application flows, and then propose a Probability-Guaranteed Adaptive Timeout algorithm (PGAT) for flow termination decision. The assessment criteria for flow termination decision algorithm is systematically developed. Comparisons on flow generation ratio, flow intact ratio, and mean flow extra retaining time metrics indicate that the PGAT algorithm can obtain more attractive performance than other related works.