A5076571080- Advanced Vision and Imaging
- Robotics and Sensor-Based Localization
- Video Surveillance and Tracking Methods
- Autonomous Vehicle Technology and Safety
- Human Pose and Action Recognition
- Image Processing Techniques and Applications
- Advanced Neural Network Applications
- Smart Parking Systems Research
- Advanced Optical Imaging Technologies
- Remote Sensing and LiDAR Applications
- Hearing Impairment and Communication
- Vehicular Ad Hoc Networks (VANETs)
- Indoor and Outdoor Localization Technologies
- Hand Gesture Recognition Systems
- Image and Object Detection Techniques
- Robotic Path Planning Algorithms
- Augmented Reality Applications
- Image Processing and 3D Reconstruction
- Optical Coherence Tomography Applications
- Advanced Image Processing Techniques
- Optical measurement and interference techniques
Korea Advanced Institute of Science and Technology
2014-2021
We introduce the KAIST multi-spectral data set, which covers a great range of drivable regions, from urban to residential, for autonomous systems. Our set provides different perspectives world captured in coarse time slots (day and night), addition fine (sunrise, morning, afternoon, sunset, night, dawn). For all-day perception systems, we propose use spectral sensor, i.e., thermal imaging camera. Toward this goal, develop multi-sensor platform, supports co-aligned RGB/Thermal camera, RGB...
One of the most hazardous driving scenario is overtaking a slower vehicle, indeed, in this case front vehicle (being overtaken) can occlude an important part field view rear vehicle's driver. This lack visibility probable cause accidents context. Recent research works tend to prove that augmented reality applied assisted significantly reduce risk accidents. In paper, we present real-time marker-less system see through cars. For purpose, two cars are equipped with cameras and appropriate...
Autonomous driving technology has made significant advances in recent years. In order for self-driving cars to become practical, they are required operate safely and reliably even under adverse conditions. However, most current autonomous have only been shown be operational amiable weather conditions, i.e., on sunny days dry roads. enable handle conditions such as rain wet roads, the algorithm must able detect roads within a tolerable margin of error using sensors cameras laser scanners....
In this paper, we introduce a novel calibration pattern board for visible and thermal camera calibration. Our is easy to make, handy move efficient heat. Also, it preserves uniform radiance long time. Proposed method can be employed in single- multi- spectral system, also used the splitter or stereo system. As result, our shows good performance comparing with previous works, that calibrated system enough use ADAS systems.
Drivable region detection is challenging since various types of road, occlusion or poor illumination condition have to be considered in a outdoor environment, particularly at night. In the past decade, Many efforts been made solve these problems, however, most already existing methods are designed for visible light cameras, which inherently inefficient under low conditions. this paper, we present drivable algorithm thermal-infrared cameras order overcome aforementioned problems. The novelty...
In this paper, we introduce a new large-scale sidewalk dataset called SideGuide that could potentially help impaired people. Unlike most previous datasets, which are focused on road environments, paid attention to sidewalks, where understanding the environment provide potential for improved walking of humans, especially Concretely, interviewed people and carefully selected target objects from interviewees' feedback (objects they encounter sidewalks). We then acquired two different types...
In this paper, we introduce a low-cost multicamera synchronization approach. Our system is to make, easy handle and convenient use. Proposed can be employed in single- multi- spectral various cameras, also used any devices which support the external trigger. As result, our shows good performance comparing with hand-eye synchronization, that synchronized images are enough use ADAS systems.
Many advancements in computer vision and machine learning have shown potential for significantly improving the lives of people with disabilities. In particular, recent research has demonstrated that deep neural network models could be used to bridge gap between deaf who use sign language hearing people. The major impediment advancing such is lack high-quality large-scale training data. Moreover, previously released datasets include few or no interrogative sentences compared declarative...
We present a motion deblurring framework for wheeled mobile robot. Motion blur is an inevitable problem in robot, especially side-view cameras severely suffer from when robot moves forward. To handle we develop fast using the concept of coded exposure. estimate kernel by simple template matching between adjacent frames with prior and blind deconvolution algorithm Gaussian exploited deblurring. Our system implemented off-the-shelf machine vision camera enables us to achieve high-quality...
The large abundance of perspective camera datasets facilitated the emergence novel learning-based strategies for various tasks, such as localization, single image depth estimation, or view synthesis. However, panoramic omnidirectional datasets, including essential information, pose and depth, are mostly made with synthetic scenes. In this work, we introduce a scale 360$^{\circ}$ videos dataset in wild. This has been carefully scraped from Internet captured locations worldwide. Hence,...
Recently, the interest for autonomous driving and unmanned aerial vehicle has drastically increased in field of robotics. This very clear trend is now expending to everyday life devices, such as lawn mower. In this context we present an automatic mower vision system capable estimating its absolute pose using both a monocular camera embedded on robot external observing environment where functioning. configuration particularly desirable since estimation challenging. can be explained by fact...