The regional network border describes the topological border nodes in cyberspace among countries and regions in the real world. By combining active and passive measurement techniques, this study proposes a dual-stage method of discovering regional network border (RNB) nodes. The first stage is to discover the regional network border's candidate sets by using directed topology measurement and multi-source geolocation. The second stage is to accurately identify border nodes from the candidate sets by using multi-source information weighted geolocation and dual PING geolocation. The experiment took China as the target region and discovered 1 644 border nodes. Compared with the CAIDA data set, the proposed approach's results have 37% of exclusively discovered border nodes with only 2.5% of the measurement cost. The accuracy rate under manual verification is 99.3%, and that under the verification of an ISP operator is 75%.