|
A Novel Room Categorization Approach to Semantic Localization for Domestic Service Robots |
|
Felix Yustian Setiono, Armagan Elibol, Nak Young Chong(Japan Advanced Institute of Science and Technology, Japan) |
| This paper present a novel room categorization based on room association approach developed on the YOLOv2 object detection framework by using the prior knowledge information as the knowledge base of the possible object location inside the specific room categories. The paper propose a new technique of the room association via a room association score function. The paper showing a significant improvement from the previously conducted research. |
|
|
Fast Drone Detection using SSD and YoloV3 |
|
Ji Hao Yew, Koon Teck Lee, Ying Xiang Chua, Enoch Jeevanraj, Sutthiphong Srigrarom(National University of Singapore, Singapore) |
| This paper aims to introduce the method of detection of high-speed drones using both Single Shot Detector (SSD) and YOLOv3 (You Only Look Once)v3. After conducting experiments and obtaining footage of the fast-flying drones, the software and algorithms are being put to the test. In a motion detector, there are 3 main fundamentals - unmanned aerial vehicle (UAV) detection, UAV identification and tracking of the UAV, which will be introduced as a preliminary UAV detection system to spark of the use of other more advanced image recognition based detector. The alternative of using SSD
and YOLOv3 will be the main discussion to target high-speed drones. |
|
|
Shallow Depth SIFT Based Approach for Mapping underwater surfaces using AUV’s |
|
RAGHURAM C S, Sai Anoop Sadineni(BITS Pilani, Hyderabad Campus, India) |
| In our paper, we deal with underwater mapping, using pre-planned routes by using autonomous underwater vehicles. Autonomous underwater vehicles are great for exploring the sea, checking the underwater pipelines and machinery remotely with the engineers out of harm’s way. Our research paper deals with a mapping algorithm at shallow depth for autonomous underwater vehicles based on the SIFT(Scale-Invariant Feature Transform), which helps extract the features, and key point descriptors from the images captured by the AUV. Using the Brute Force Matcher Toolkit in OpenCV, we match the images producing the vertical segments and finally generating the final map. |
|
|
Detection Of Defective Videosurveillance Camera In Train Stations |
|
Claire NICODEME(SNCF, France) |
| Imaging sensors have known noteworthy improvements and a growing interest from academics and industries. In particular, video-surveillance cameras have widely spread, and many systems depends on their inputs. Either to provide visual information to human operators or to Artificial Intelligence algorithms, it is important to be able to assess the proper operation of sensors and the quality of images and videos they record. However, existing methods are either very specific or perform poorly in unpredictable environment. AI algorithms have proven to be useful to detect anomalies.In this work, the authors present a comparative study for defective camera detection, in video-surveillance. |
|