지승도 교수의 연구실에서 인공지능 드론의 안전 시스템을 위한 이벤트 기반 지능 제어 기법을 연구하여 발표한 논문 "Event-Based Emergency Detection for Safe Drone"이 SCI급 국제 우수 등재 저널인 "Applied Sciences" 2022년 8월 호에 게재되었다.
Quadrotor drones have rapidly gained interest recently. Numerous studies are underway for the commercial use of autonomous drones, and distribution businesses especially are taking serious reviews on drone-delivery services. However, there are still many concerns about urban drone operations. The risk of failures and accidents makes it difficult to provide drone-based services in the real world with ease. There have been many studies that introduced supplementary methods to handle drone failures and emergencies. However, we discovered the limitation of the existing methods. Most approaches were improving PID-based control algorithms, which is the dominant drone-control method. This type of low-level approach lacks situation awareness and the ability to handle unexpected situations. This study introduces an event-based control methodology that takes a high-level diagnosing approach that can implement situation awareness via a time-window. While low-level controllers are left to operate drones most of the time in normal situations, our controller operates at a higher level and detects unexpected behaviors and abnormal situations of the drone. We tested our method with real-time 3D computer simulation environments and in several cases, our method was able to detect emergencies that typical PID controllers were not able to handle. We were able to verify that our approach can provide enhanced double safety and better ensure safe drone operations. We hope our discovery can possibly contribute to the advance of real-world drone services in the near future.
김선옥 교수의 연구실에서 발표한 논문 "Stereo Confidence Estimation via Locally Adaptive Fusion and Knowledge Distillation"이 "IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)"에 게재 승인되었다. IEEE TPAMI는 세계 최고 권위의 인공지능 학술지 중 하나로, Impact factor가 24.3점에 달한다. 본 연구는 김선옥 교수가 제 1 저자로 주도했으며, 스위스의 로잔 연방 공과대학교(EPFL), 연세대학교, 고려대학교, 이화여자대학교가 공동으로 참여하였다.
[Figure 1] Network configuration in knowledge distilation framework
Stereo confidence estimation aims to estimate the reliability of the estimated disparity by stereo matching. Different from the previous methods that exploit the limited input modality, we present a novel method that estimates confidence map of an initial disparity by making full use of tri-modal input, including matching cost, disparity, and color image through deep networks. The proposed network, termed as Locally Adaptive Fusion Networks (LAF-Net), learns locally-varying attention and scale maps to fuse the tri-modal confidence features. Moreover, we propose a knowledge distillation framework to learn more compact confidence estimation networks as student networks. By transferring the knowledge from LAF-Net as teacher networks, the student networks that solely take as input a disparity can achieve comparable performance. To transfer more informative knowledge, we also propose a module to learn the locally-varying temperature in a softmax function. We further extend this framework to a multiview scenario. Experimental results show that LAF-Net and its variations outperform the state-of-the-art stereo confidence methods on various benchmarks.
[Figure 2] Confidence maps on KITTI 2015 dataset
We presented LAF-Net that estimates confidence with tri-modal input, including matching cost, disparity, and color image through deep networks. The key idea of the proposed method is to design locally adaptive attention and scale inference networks to generate optimal fusion weights. In addition, the confidence estimation performance is further improved with recursive refinement networks. In addition, we presented an effective confidence estimator through knowledge distillation using the LAF-Net taking tri-modal input as teacher, where we learned the locally varying temperature which is effective in transferring more informative value to student networks. The proposed method has competitive accuracy with simpler networks than teacher. We further applied the proposed framework to multiview stereo confidence estimation which demonstrates the generalization ability of the proposed framework. A direction for further study is to examine how confidence estimation networks could be learned in an unsupervised manner.
엄태훈 교수의 연구실에서 발표한 논문 "CloudSafe: A Tool for an Automated Security Analysis for Cloud Computing"이 "IEEE Access" 2022년 호에 게재되었다.
논문 사이트로 이동
[Figure 1] Overall framework architecture
Cloud computing has become widely adopted by businesses for hosting applications with improved performance at a fraction of the operational costs and complexity. The rise of cloud applications has been coupled with an increase in security threat vectors and vulnerabilities. In this paper, we propose a new security assessment and enforcement tool for the cloud named CloudSafe, which provides an automated security assessment and enforce best security control for the cloud by collating various security tools. To demonstrate the applicability and usability of CloudSafe, we implemented CloudSafe and conducted security assessment in Amazon AWS. Also, we analyzed four different security countermeasure options in depth; Vulnerability Patching, Virtual Patching, Network Hardening and Moving Target Defence. Virtual Patching, Network Hardening and Moving Target Defence were determined to be feasible with regards to deployment implementation for the project. Proof of concepts were developed demonstrating the effectiveness of each feasible countermeasure option. These results indicate that the proposed tool CloudSafe is effective and efficient in helping security administrators to select optimal countermeasures to secure their cloud by conducting an in-depth security assessment.