The following video shows our work on All-weather Action Detection in UAV Rescue Scenarios.
Unmanned Aerial Vehicles (UAVs) possess significant advantages in terms of mobility and range compared to traditional surveillance cameras. Human action detection from UAV images has the potential to assist in various fields, including search and rescue operations. However, UAV images present challenges such as varying heights, angles, and the presence of small objects. Additionally, they can be affected by adverse illumination and weather conditions. In this paper, we propose a Multilevel Attention network with Weather Suppression for all-weather action detection in UAV rescue scenarios. The Weather Suppression module effectively mitigates the impact of illumination and weather, while the Multi-level Attention module enhances the model’s performance in detecting small objects. We conducted detection experiments under both normal and synthetic harsh conditions, and the results demonstrate that our model achieves state-of-the-art performance. Furthermore, a comparison of relevant metrics reveals that our model strikes a balance between size and complexity, making it suitable for deployment on UAV platforms. The conducted ablation experiments also highlight the significant contribution of our proposed modules.
Related Papers
Yao Liu, Binghao Li, Claude Sammut, and Lina Yao, Multi-level Attention Network with Weather Suppression for All-weather Action Detection in UAV Rescue Scenarios.The 30th International Conference on Neural Information Processing (ICONIP2023), Changsha, China, November 20-23, 2023.
The following videos show our work on anonymous robot systems.
In the first demonstration the robot navigates to the required unknown location as well as exploration and survey of the unknown area for map building. The robot equips 360° laser distance sensor for SLAM and navigation.
The second demonstration shows a scenario of domestic robot as intelligent assistant which intimately helps the subject with tasks. The system was trained to help certain tasks, such as pass spoon when bowl appears as the subject preparing food. Optical flow was used to predict the trajectory of active moving objects with RGB-D camera in 3D space.
The series of demos showcase a series of SmartHome practices under Intelligent systems and Intelligent sensing (Internet of Things), more demos will be added from time to time.
Related Papers
Lina Yao, Quan Z. Sheng, Boualem Benatallah, Schahram Dustdar, Xianzhi Wang, Ali Shemshadi and Salil Kanhere. Up in the Air: When Smart Homes Meet the Internet of ThingsWITS: An IoT-endowed Computational Framework for Activity Recognition in Personalized Smart Homes. Computing, Springer, 2017 (to appear).
Lina Yao, Quan Z. Sheng and Schahram Dustdar. Web-based Management of the Internet of Things. IEEE Internet Computing (IEEE Internet Computing),Vol 19, No 4, pp 60-67, July/August, 2015.
Lina Yao, Quan Z. Sheng, Anne. H. H. Ngu and Byron Gao. Keeping You in the Loop: Enabling Web-based Things Management in the Internet of Things. The 23rd ACM International Conference on Information and Knowledge Management (CIKM 2014) , November 3-7, 2014, Shanghai, China
We showcase a novel localization and tracking system based on the Received Signal Strength (RSS) field formed by cost-efficient Radio-Frequency Identification passive tags.(
Related Papers
Wenjie Ruan, Quan Z. Sheng,Lina Yao, Tao Gu, and Longfei Shangguan, Device-Free Indoor Localization and Tracking through Human-Object Interactions.The 17th International Symposium on a World of Wireless, Mobile and Multimedia Networks ( WoWMoM 2016), Coimbra, Portugal, June 21-24, 2016.
Lina Yao, Wenjie Ruan, Quan Z. Sheng, Xue Li and Nickolas J.G. Falkner. Exploring Tag-free RFID-based Passive Localization and Tracking via Learning-based Probabilistic Approaches. The 23rd ACM International Conference on Information and Knowledge Management (CIKM 2014) , November 3-7, 2014, Shanghai, China
Wenjie Ruan,Lina Yao, Quan Z. Sheng, Xue Li and Nickolas J.G. Falkner. TagTrack: Device-free Localization and Tracking Using Passive RFID Tags. The 11th International Conference on Mobile and Ubiquitous Systems: Computing, Networking and Services(MobiQuitous 2014) , December 2–5, 2014 London, Great Britain
“The Marauder's Map is a magical document that reveals all of Hogwarts School of Witchcraft and Wizardry. Not only does it show every classroom, every hallway, and every corner of the castle, but it also shows every inch of the grounds, as well as all the secret passages that are hidden within its walls and the location of every person in the grounds, portrayed by a dot….—— Harry Potter’s Wiki”
This project aims at developing a Web-based application built upon Internet of Things, through which we will not only know where everyone is but we will also know what they are doing.