Huai Yu - IEEE Xplore Author Profile

Showing 1-25 of 35 results

Results

Event cameras, also known as neuromorphic cameras, have garnered significant interest in recent years because of their high temporal resolution for capturing dynamic scenes. Their unique asynchronous triggering mechanism based on illumination changes offers a unique advantage in capturing edge information, particularly in line segment detection tasks. However, directly applying state-of-the-art im...Show More
Camera localization in LiDAR maps has become increasingly popular due to its promising ability to handle complex scenarios, surpassing the limitations of visual-only localization methods. However, existing approaches mostly focus on addressing the cross-modal 2D–3D gaps while overlooking the relationship between adjacent image frames, which results in fluctuations and unreliability of camera poses...Show More
This paper presents a novel framework to learn a concise geometric primitive representation for 3D point clouds. Different from representing each type of primitive individually, we focus on the challenging problem of how to achieve a concise and uniform representation robustly. We employ quadrics to represent diverse primitives with only 10 parameters and propose the first end-to-end learning-base...Show More
Keypoint detection and tracking in traditional image frames are often compromised by image quality issues such as motion blur and extreme lighting conditions. Event cameras offer potential solutions to these challenges by virtue of their high temporal resolution and high dynamic range. However, they have limited performance in practical applications due to their inherent noise in event data. This ...Show More
Robust keypoint detection and tracking are crucial for various robotic tasks. However, conventional cameras struggle under rapid motion and lighting changes, hindering local and edge feature extraction essential for keypoint detection and tracking. Event cameras offer advantages in such scenarios due to their high dynamic range and low latency. Yet, their inherent noise and motion dependence can l...Show More
Visual-inertial odometry (VIO) utilizing point and line features has become prevalent for state estimation in structured environments. The robustness of line segment detection and the efficiency of line feature matching significantly impact pose estimation performance. However, prevailing gradient-based line detection methods are prone to noise, and the existing line feature matching methods suffe...Show More
Cross-view geo-localization (CVGL) involves determining the geographical location of a query image by matching it with a corresponding GPS-tagged reference image. Current state-of-the-art methods predominantly rely on training models with labeled paired images, incurring substantial annotation costs and training burdens. In this study, we investigate the adaptation of frozen models for CVGL withou...Show More
Severe appearance changes represent a pervasive and intricate challenge within Visual Place Recognition (VPR) tasks, and the current best solution adopts a composite strategy encompassing global retrieval and reranking. However, these reranking techniques necessitate sophisticated considerations to extract and match local features, which leads to a notable escalation of computational resource dema...Show More
Buildings represent pivotal entities in remote sensing imagery for various applications such as urban planning and land resource management. Predominantly, methods for building footprint extraction in the literature focus on optical imagery with visual attributes that faithfully mirror the physical world. Nevertheless, the acquisition of high-quality optical images presents formidable challenges d...Show More
Making line segment detectors more reliable under motion blurs is one of the most important challenges for practical applications, such as visual SLAM and 3D line mapping. Existing line segment detection methods face severe performance degradation for accurately detecting and locating line segments when motion blur occurs. While event data shows strong complementary characteristics to images for m...Show More
This study addresses the problem of finding the optimal correspondence for a given synthetic aperture radar (SAR) image patch from a large collection of optical reference patches, which is crucial for various applications, including remote sensing, place recognition, and aircraft navigation. However, achieving one-to-one SAR-Optical patch correspondence is challenging due to the distinct modal dis...Show More
Visual localization plays an important role for intelligent robots and autonomous driving, especially when the accuracy of GNSS is unreliable. Recently, camera localization in LiDAR maps has attracted more and more attention for its low cost and potential robustness to illumination and weather changes. However, the commonly used pinhole camera has a narrow field-of-view, leading to limited informa...Show More
Detecting arbitrarily oriented tiny objects poses intense challenges to existing detectors, especially for label assignment. Despite the exploration of adaptive label assignment in recent oriented object detectors, the extreme geometry shape and limited feature of oriented tiny objects still induce severe mismatch and imbalance issues. Specifically, the position prior, positive sample feature, and...Show More
Deep learning has had remarkable success in robotic perception, but its data-centric nature suffers when it comes to generalizing to ever-changing environments. By contrast, physics-based optimization generalizes better, but it does not perform as well in complicated tasks due to the lack of high-level semantic information and reliance on manual parametric tuning. To take advantage of these two co...Show More
The event camera asynchronously produces the event stream with a high temporal resolution, discarding redundant visual information and bringing new possibilities for moving object detection. Nevertheless, the existing object detectors cannot make the most of the spatial-temporal asynchronous nature and high temporal resolution of the event stream. For one thing, existing methods fail to consider o...Show More
Robust object detection is hindered by various illumination conditions in real-world applications. Common practice introduces thermal modality to augment the detection capability of RGB images in poor illumination conditions. However, a major challenge for such work is how to leverage the complementary information of RGB and thermal images effectively. In this article, we tackle this by combining ...Show More
Fine-grained ship detection is an important task in high-resolution satellite remote sensing applications. However, large aspect ratios and severe category imbalance make fine-grained ship detection a challenging problem. Current methods usually extract square-like features that do not work well to detect ships with large aspect ratios, and the misalignments in feature representation will severely...Show More
We present a Visual-Inertial Odometry (VIO) algorithm with multiple non-overlapping monocular cameras aiming at improving the robustness of the VIO algorithm. An initialization scheme and tightly-coupled bundle adjustment for multiple non-overlapping monocular cameras are proposed. With more stable features captured by multiple cameras, VIO can maintain stable state estimation, especially when one...Show More
Detecting airplanes from high-resolution remote sensing images has a variety of applications. The characteristics of clear details, rich spatial, and texture information of objects in high-resolution remote sensing images make it possible to identify different types of airplanes from backgrounds. However, airplanes usually exhibit slight interclass discrepancy and unbalanced class distribution, wh...Show More
In recent years, object detection in high-resolution synthetic aperture radar (SAR) images has made significant progress, especially after the introduction of deep learning. However, objects such as dense oil tanks, which are compactly arranged in SAR images, are still challenging to recognize due to the unique imaging mechanism of SAR. Inspired by human learning from comparison, we propose a mult...Show More
A 2-D and 3-D sensor extrinsic calibration is the key prerequisite for multisensor-based robot perception and localization. However, such calibration is challenging due to the variety of sensor modalities and the requirement of special calibration targets and human intervention. In this article, we demonstrate a new targetless cross-modal calibration system focusing on the extrinsic transformation...Show More
In Simultaneous Localization And Mapping (SLAM) problems, high-level landmarks have the potential to build compact and informative maps compared to traditional point-based landmarks. In this work, we focus on the param-eterization of frequently used geometric primitives including points, lines, planes, ellipsoids, cylinders, and cones. We first present a unified representation based on quadrics, a...Show More
Stereo reconstruction models trained on small images do not generalize well to high-resolution data. Training a model on high-resolution image size faces difficulties of data availability and is often infeasible due to limited computing resources. In this work, we present the Occlusion-aware Recurrent binocular Stereo matching (ORStereo), which deals with these issues by only training on available...Show More
The task of matching between images acquired by terminal equipment and satellites is important and challenging due to the dramatic viewpoint changes and unknown orientations, especially with different imaging sensors. In this paper, we firstly present the task to match the optical/infrared images acquired by UAVs with satellite SAR images. Many previous works mainly focused on matching with the im...Show More
Light-weight camera localization in existing maps is essential for vision-based navigation. Currently, visual and visual-inertial odometry (VO&VIO) techniques are well-developed for state estimation but with inevitable accumulated drifts and pose jumps upon loop closure. To overcome these problems, we propose an efficient monocular camera localization method in prior LiDAR maps using direct 2D-3D ...Show More